MyArxiv
Robotics 30
☆ Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3\% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.
comment: Project page: https://jasper0314-huang.github.io/fast-thinkact/
☆ Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets
Vision-based policies for robot manipulation have achieved significant recent success, but are still brittle to distribution shifts such as camera viewpoint variations. Robot demonstration data is scarce and often lacks appropriate variation in camera viewpoints. Simulation offers a way to collect robot demonstrations at scale with comprehensive coverage of different viewpoints, but presents a visual sim2real challenge. To bridge this gap, we propose MANGO -- an unpaired image translation method with a novel segmentation-conditioned InfoNCE loss, a highly-regularized discriminator design, and a modified PatchNCE loss. We find that these elements are crucial for maintaining viewpoint consistency during sim2real translation. When training MANGO, we only require a small amount of fixed-camera data from the real world, but show that our method can generate diverse unseen viewpoints by translating simulated observations. In this domain, MANGO outperforms all other image translation methods we tested. Imitation-learning policies trained on data augmented by MANGO are able to achieve success rates as high as 60\% on views that the non-augmented policy fails completely on.
☆ Multimodal Signal Processing For Thermo-Visible-Lidar Fusion In Real-time 3D Semantic Mapping
In complex environments, autonomous robot navigation and environmental perception pose higher requirements for SLAM technology. This paper presents a novel method for semantically enhancing 3D point cloud maps with thermal information. By first performing pixel-level fusion of visible and infrared images, the system projects real-time LiDAR point clouds onto this fused image stream. It then segments heat source features in the thermal channel to instantly identify high temperature targets and applies this temperature information as a semantic layer on the final 3D map. This approach generates maps that not only have accurate geometry but also possess a critical semantic understanding of the environment, making it highly valuable for specific applications like rapid disaster assessment and industrial preventive maintenance.
comment: 5 pages,7 figures. Under review
☆ Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations
Enabling humanoid robots to physically interact with humans is a critical frontier, but progress is hindered by the scarcity of high-quality Human-Humanoid Interaction (HHoI) data. While leveraging abundant Human-Human Interaction (HHI) data presents a scalable alternative, we first demonstrate that standard retargeting fails by breaking the essential contacts. We address this with PAIR (Physics-Aware Interaction Retargeting), a contact-centric, two-stage pipeline that preserves contact semantics across morphology differences to generate physically consistent HHoI data. This high-quality data, however, exposes a second failure: conventional imitation learning policies merely mimic trajectories and lack interactive understanding. We therefore introduce D-STAR (Decoupled Spatio-Temporal Action Reasoner), a hierarchical policy that disentangles when to act from where to act. In D-STAR, Phase Attention (when) and a Multi-Scale Spatial module (where) are fused by the diffusion head to produce synchronized whole-body behaviors beyond mimicry. By decoupling these reasoning streams, our model learns robust temporal phases without being distracted by spatial noise, leading to responsive, synchronized collaboration. We validate our framework through extensive and rigorous simulations, demonstrating significant performance gains over baseline approaches and a complete, effective pipeline for learning complex whole-body interactions from HHI data.
☆ CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
To teach robots complex manipulation tasks, it is now a common practice to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for long-term operation in the real world, where robots must continually adapt to new tasks and environments while retaining the knowledge they have already acquired. Existing continual learning methods for robotics commonly require storing previous data (exemplars), struggle with long task sequences, or rely on task identifiers for deployment. To address these limitations, we propose CLARE, a general, parameter-efficient framework for exemplar-free continual learning with VLAs. CLARE introduces lightweight modular adapters into selected feedforward layers and autonomously expands the model only where necessary when learning a new task, guided by layer-wise feature similarity. During deployment, an autoencoder-based routing mechanism dynamically activates the most relevant adapters without requiring task labels. Through extensive experiments on the LIBERO benchmark, we show that CLARE achieves high performance on new tasks without catastrophic forgetting of earlier tasks, significantly outperforming even exemplar-based methods. Code and data are available at https://tum-lsy.github.io/clare.
comment: Project page: https://tum-lsy.github.io/clare. 9 pages, 5 figures
☆ Data Scaling for Navigation in Unknown Environments
Generalization of imitation-learned navigation policies to environments unseen in training remains a major challenge. We address this by conducting the first large-scale study of how data quantity and data diversity affect real-world generalization in end-to-end, map-free visual navigation. Using a curated 4,565-hour crowd-sourced dataset collected across 161 locations in 35 countries, we train policies for point goal navigation and evaluate their closed-loop control performance on sidewalk robots operating in four countries, covering 125 km of autonomous driving. Our results show that large-scale training data enables zero-shot navigation in unknown environments, approaching the performance of policies trained with environment-specific demonstrations. Critically, we find that data diversity is far more important than data quantity. Doubling the number of geographical locations in a training set decreases navigation errors by ~15%, while performance benefit from adding data from existing locations saturates with very little data. We also observe that, with noisy crowd-sourced data, simple regression-based models outperform generative and sequence-based architectures. We release our policies, evaluation setup and example videos on the project page.
☆ ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving AAAI 2026
Generating safe and reliable trajectories for autonomous vehicles in long-tail scenarios remains a significant challenge, particularly for high-lateral-acceleration maneuvers such as sharp turns, which represent critical safety situations. Existing trajectory planners exhibit systematic failures in these scenarios due to data imbalance. This results in insufficient modelling of vehicle dynamics, road geometry, and environmental constraints in high-risk situations, leading to suboptimal or unsafe trajectory prediction when vehicles operate near their physical limits. In this paper, we introduce ReflexDiffusion, a novel inference-stage framework that enhances diffusion-based trajectory planners through reflective adjustment. Our method introduces a gradient-based adjustment mechanism during the iterative denoising process: after each standard trajectory update, we compute the gradient between the conditional and unconditional noise predictions to explicitly amplify critical conditioning signals, including road curvature and lateral vehicle dynamics. This amplification enforces strict adherence to physical constraints, particularly improving stability during high-lateral-acceleration maneuvers where precise vehicle-road interaction is paramount. Evaluated on the nuPlan Test14-hard benchmark, ReflexDiffusion achieves a 14.1% improvement in driving score for high-lateral-acceleration scenarios over the state-of-the-art (SOTA) methods. This demonstrates that inference-time trajectory optimization can effectively compensate for training data sparsity by dynamically reinforcing safety-critical constraints near handling limits. The framework's architecture-agnostic design enables direct deployment to existing diffusion-based planners, offering a practical solution for improving autonomous vehicle safety in challenging driving conditions.
comment: Accepted by AAAI 2026
☆ Feedback-Based Mobile Robot Navigation in 3-D Environments Using Artificial Potential Functions Technical Report
This technical report presents the construction and analysis of polynomial navigation functions for motion planning in 3-D workspaces populated by spherical and cylindrical obstacles. The workspace is modeled as a bounded spherical region, and obstacles are encoded using smooth polynomial implicit functions. We establish conditions under which the proposed navigation functions admit a unique non-degenerate minimum at the target while avoiding local minima, including in the presence of pairwise intersecting obstacles. Gradient and Hessian analyses are provided, and the theoretical results are validated through numerical simulations in obstacle rich 3-D environments.
☆ Online Trajectory Optimization for Arbitrary-Shaped Mobile Robots via Polynomial Separating Hypersurfaces
An emerging class of trajectory optimization methods enforces collision avoidance by jointly optimizing the robot's configuration and a separating hyperplane. However, as linear separators only apply to convex sets, these methods require convex approximations of both the robot and obstacles, which becomes an overly conservative assumption in cluttered and narrow environments. In this work, we unequivocally remove this limitation by introducing nonlinear separating hypersurfaces parameterized by polynomial functions. We first generalize the classical separating hyperplane theorem and prove that any two disjoint bounded closed sets in Euclidean space can be separated by a polynomial hypersurface, serving as the theoretical foundation for nonlinear separation of arbitrary geometries. Building on this result, we formulate a nonlinear programming (NLP) problem that jointly optimizes the robot's trajectory and the coefficients of the separating polynomials, enabling geometry-aware collision avoidance without conservative convex simplifications. The optimization remains efficiently solvable using standard NLP solvers. Simulation and real-world experiments with nonconvex robots demonstrate that our method achieves smooth, collision-free, and agile maneuvers in environments where convex-approximation baselines fail.
☆ Vision-Conditioned Variational Bayesian Last Layer Dynamics Models
Agile control of robotic systems often requires anticipating how the environment affects system behavior. For example, a driver must perceive the road ahead to anticipate available friction and plan actions accordingly. Achieving such proactive adaptation within autonomous frameworks remains a challenge, particularly under rapidly changing conditions. Traditional modeling approaches often struggle to capture abrupt variations in system behavior, while adaptive methods are inherently reactive and may adapt too late to ensure safety. We propose a vision-conditioned variational Bayesian last-layer dynamics model that leverages visual context to anticipate changes in the environment. The model first learns nominal vehicle dynamics and is then fine-tuned with feature-wise affine transformations of latent features, enabling context-aware dynamics prediction. The resulting model is integrated into an optimal controller for vehicle racing. We validate our method on a Lexus LC500 racing through water puddles. With vision-conditioning, the system completed all 12 attempted laps under varying conditions. In contrast, all baselines without visual context consistently lost control, demonstrating the importance of proactive dynamics adaptation in high-performance applications.
comment: 9 pages, 7 figures, currently under review
☆ CEI: A Unified Interface for Cross-Embodiment Visuomotor Policy Learning in 3D Space
Robotic foundation models trained on large-scale manipulation datasets have shown promise in learning generalist policies, but they often overfit to specific viewpoints, robot arms, and especially parallel-jaw grippers due to dataset biases. To address this limitation, we propose Cross-Embodiment Interface (\CEI), a framework for cross-embodiment learning that enables the transfer of demonstrations across different robot arm and end-effector morphologies. \CEI introduces the concept of \textit{functional similarity}, which is quantified using Directional Chamfer Distance. Then it aligns robot trajectories through gradient-based optimization, followed by synthesizing observations and actions for unseen robot arms and end-effectors. In experiments, \CEI transfers data and policies from a Franka Panda robot to \textbf{16} different embodiments across \textbf{3} tasks in simulation, and supports bidirectional transfer between a UR5+AG95 gripper robot and a UR5+Xhand robot across \textbf{6} real-world tasks, achieving an average transfer ratio of 82.4\%. Finally, we demonstrate that \CEI can also be extended with spatial generalization and multimodal motion generation capabilities using our proposed techniques. Project website: https://cross-embodiment-interface.github.io/
☆ Vision Foundation Models for Domain Generalisable Cross-View Localisation in Planetary Ground-Aerial Robotic Teams
Accurate localisation in planetary robotics enables the advanced autonomy required to support the increased scale and scope of future missions. The successes of the Ingenuity helicopter and multiple planetary orbiters lay the groundwork for future missions that use ground-aerial robotic teams. In this paper, we consider rovers using machine learning to localise themselves in a local aerial map using limited field-of-view monocular ground-view RGB images as input. A key consideration for machine learning methods is that real space data with ground-truth position labels suitable for training is scarce. In this work, we propose a novel method of localising rovers in an aerial map using cross-view-localising dual-encoder deep neural networks. We leverage semantic segmentation with vision foundation models and high volume synthetic data to bridge the domain gap to real images. We also contribute a new cross-view dataset of real-world rover trajectories with corresponding ground-truth localisation data captured in a planetary analogue facility, plus a high volume dataset of analogous synthetic image pairs. Using particle filters for state estimation with the cross-view networks allows accurate position estimation over simple and complex trajectories based on sequences of ground-view images.
comment: 7 pages, 10 figures. Presented at the International Conference on Space Robotics (iSpaRo) 2025 in Sendai, Japan. Dataset available: https://doi.org/10.5281/zenodo.17364038
☆ Design Methodology of Hydraulically-driven Soft Robotic Gripper for a Large and Heavy Object
This paper presents a design methodology of a hydraulically-driven soft robotic gripper for grasping a large and heavy object -- approximately 10 - 20 kg with 20 - 30 cm diameter. Most existing soft grippers are pneumatically actuated with several hundred kPa pressure, and cannot generate output force sufficient for such a large and heavy object. Instead of pneumatic actuation, hydraulic actuation has a potential to generate much larger power by several MPa pressure. In this study, we develop a hydraulically-driven soft gripper, in which its basic design parameters are determined based on a mathematical model that represents the relationship among the driving pressure, bending angle, object mass and grasping force. Moreover, we selected materials suitable for grasping a heavier object, based on the finite element analysis result of the detailed design. We report experimental results on a 20 kg object grasping and closed-loop control of the finger bending angle.
♻ ☆ Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments
The growing integration of robots in shared environments - such as warehouses, shopping centres, and hospitals - demands a deep understanding of the underlying dynamics and human behaviours, including how, when, and where individuals engage in various activities and interactions. This knowledge goes beyond simple correlation studies and requires a more comprehensive causal analysis. By leveraging causal inference to model cause-and-effect relationships, we can better anticipate critical environmental factors and enable autonomous robots to plan and execute tasks more effectively. To this end, we propose a novel causality-based decision-making framework that reasons over a learned causal model to assist the robot in deciding when and how to complete a given task. In the examined use case - i.e., a warehouse shared with people - we exploit the causal model to estimate battery usage and human obstructions as factors influencing the robot's task execution. This reasoning framework supports the robot in making informed decisions about task timing and strategy. To achieve this, we developed also PeopleFlow, a new Gazebo-based simulator designed to model context-sensitive human-robot spatial interactions in shared workspaces. PeopleFlow features realistic human and robot trajectories influenced by contextual factors such as time, environment layout, and robot state, and can simulate a large number of agents. While the simulator is general-purpose, in this paper we focus on a warehouse-like environment as a case study, where we conduct an extensive evaluation benchmarking our causal approach against a non-causal baseline. Our findings demonstrate the efficacy of the proposed solutions, highlighting how causal reasoning enables autonomous robots to operate more efficiently and safely in dynamic environments shared with humans.
comment: Causal Discovery and Inference - Robot Autonomy - Human-Robot Spatial Interaction - Decision-Making
♻ ☆ SPARK: Safe Protective and Assistive Robot Kit
This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments. The physical structures of humanoid robots further add complexity to the design of general safety solutions. To facilitate safe deployment of complex robot systems, SPARK can be used as a toolbox that comes with state-of-the-art safe control algorithms in a modular and composable robot control framework. Users can easily configure safety criteria and sensitivity levels to optimize the balance between safety and performance. To accelerate humanoid safety research and development, SPARK provides simulation benchmarks that compare safety approaches in a variety of environments, tasks, and robot models. Furthermore, SPARK allows quick deployment of synthesized safe controllers on real robots. For hardware deployment, SPARK supports Apple Vision Pro (AVP) or a Motion Capture System as external sensors, while offering interfaces for seamless integration with alternative hardware setups at the same time. This paper demonstrates SPARK's capability with both simulation experiments and case studies with a Unitree G1 humanoid robot. Leveraging these advantages of SPARK, users and researchers can significantly improve the safety of their humanoid systems as well as accelerate relevant research. The open source code is available at: https://github.com/intelligent-control-lab/spark.
comment: Presented at IFAC Symposium on Robotics
♻ ☆ Environment as Policy: Learning to Race in Unseen Tracks ICRA
Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track configurations, always requiring complete retraining when presented with new track layouts. This work aims to develop RL agents that generalize effectively to novel track configurations without retraining. The naive solution of training directly on a diverse set of track layouts can overburden the agent, resulting in suboptimal policy learning as the increased complexity of the environment impairs the agent's ability to learn to fly. To enhance the generalizability of the RL agent, we propose an adaptive environment-shaping framework that dynamically adjusts the training environment based on the agent's performance. We achieve this by leveraging a secondary RL policy to design environments that strike a balance between being challenging and achievable, allowing the agent to adapt and improve progressively. Using our adaptive environment shaping, one single racing policy efficiently learns to race in diverse challenging tracks. Experimental results validated in both simulation and the real world show that our method enables drones to successfully fly complex and unseen race tracks, outperforming existing environment-shaping techniques. Project page: http://rpg.ifi.uzh.ch/env_as_policy.
comment: Accepted at IEEE International Conference on Robotics and Automation (ICRA), 2025
♻ ☆ Periodic robust robotic rock chop via virtual model control
Robotic cutting is a challenging contact-rich manipulation task where the robot must simultaneously negotiate unknown object mechanics, large contact forces, and precise motion requirements. We introduce a new active virtual-model control scheme that enables knife rocking motion for robot manipulators, without pre-planned trajectories or precise information of the environment. Motion is generated and controlled through switching virtual coupling with virtual mechanisms, given by virtual springs, dampers, and masses arranged in a suitable way. Through analysis and experiments, we demonstrate that the controlled robot behavior settles into a periodic motion. Experiments with a Franka manipulator demonstrate robust cuts with five different vegetables, and sub-millimeter slice accuracy from 1 mm to 6 mm at nearly one cut per second. The same controller survives changes in knife shape and cutting board height, and adaptation to a different humanoid manipulator, demonstrating robustness and platform independence.
♻ ☆ Shape-Space Graphs: Fast and Collision-Free Path Planning for Soft Robots
Soft robots, inspired by elephant trunks or octopus arms, offer extraordinary flexibility to bend, twist, and elongate in ways that rigid robots cannot. However, their motion planning remains a challenge, especially in cluttered environments with obstacles, due to their highly nonlinear and infinite-dimensional kinematics. Here, we present a graph-based path planning tool for an elephant-trunk-inspired soft robot designed with three artificial muscle fibers that allow for continuous deformation through contraction. Using a biomechanical model that integrates morphoelastic and active filament theories, we precompute a shape library and construct a k-nearest neighbor graph in \emph{shape space}, ensuring that each node corresponds to a valid robot shape. For the graph, we use signed distance functions to prune nodes and edges colliding with obstacles, and define multi-objective edge costs based on geometric distance and actuation effort, enabling energy-aware planning with collision avoidance. We demonstrate that our algorithm reliably avoids obstacles and generates feasible paths within milliseconds from precomputed graphs using Dijkstra's algorithm. We show that including energy costs can drastically reduce the actuation effort compared to geometry-only planning, at the expense of longer tip trajectories. Our results highlight the potential of shape-space graph search for fast and reliable path planning in the field of soft robotics, paving the way for real-time applications in surgical, industrial, and assistive settings.
comment: revised version
♻ ☆ UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of constraints, such as collision avoidance, actuation limits, and dynamic consistency, which are typically addressed individually or heuristically. In this work, we propose UniConFlow, a unified constrained flow matching-based framework for trajectory generation that systematically incorporates both equality and inequality constraints. Moreover, UniConFlow introduces a novel prescribed-time zeroing function that shapes a time-varying guidance field during inference, allowing the generation process to adapt to varying system models and task requirements. Furthermore, to further address the computational challenges of long-horizon and high-dimensional trajectory generation, we propose two practical strategies for the terminal constraint enforcement and inference process: a violation-segment extraction protocol that precisely localizes and refines only the constraint-violating portions of trajectories, and a trajectory compression method that accelerates optimization in a reduced-dimensional space while preserving high-fidelity reconstruction after decoding. Empirical validation across three experiments, including a double inverted pendulum, a real-to-sim car racing task, and a sim-to-real manipulation task, demonstrates that UniConFlow outperforms state-of-the-art generative planners and conventional optimization baselines, achieving superior performance on certified motion planning metrics such as safety, kinodynamic consistency, and action feasibility. Project page is available at: https://uniconflow.github.io.
♻ ☆ Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
Learning control policies in simulation enables rapid, safe, and cost-effective development of advanced robotic capabilities. However, transferring these policies to the real world remains difficult due to the sim-to-real gap, where unmodeled dynamics and environmental disturbances can degrade policy performance. Existing approaches, such as domain randomization and Real2Sim2Real pipelines, can improve policy robustness, but either struggle under out-of-distribution conditions or require costly offline retraining. In this work, we approach these problems from a different perspective. Instead of relying on diverse training conditions before deployment, we focus on rapidly adapting the learned policy in the real world in an online fashion. To achieve this, we propose a novel online adaptive learning framework that unifies residual dynamics learning with real-time policy adaptation inside a differentiable simulation. Starting from a simple dynamics model, our framework refines the model continuously with real-world data to capture unmodeled effects and disturbances such as payload changes and wind. The refined dynamics model is embedded in a differentiable simulation framework, enabling gradient backpropagation through the dynamics and thus rapid, sample-efficient policy updates beyond the reach of classical RL methods like PPO. All components of our system are designed for rapid adaptation, enabling the policy to adjust to unseen disturbances within 5 seconds of training. We validate the approach on agile quadrotor control under various disturbances in both simulation and the real world. Our framework reduces hovering error by up to 81% compared to L1-MPC and 55% compared to DATT, while also demonstrating robustness in vision-based control without explicit state estimation.
♻ ☆ JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
Aerial robots interacting with objects must perform precise, contact-rich maneuvers under uncertainty. In this paper, we study the problem of aerial ball juggling using a quadrotor equipped with a racket, a task that demands accurate timing, stable control, and continuous adaptation. We propose JuggleRL, the first reinforcement learning-based system for aerial juggling. It learns closed-loop policies in large-scale simulation using systematic calibration of quadrotor and ball dynamics to reduce the sim-to-real gap. The training incorporates reward shaping to encourage racket-centered hits and sustained juggling, as well as domain randomization over ball position and coefficient of restitution to enhance robustness and transferability. The learned policy outputs mid-level commands executed by a low-level controller and is deployed zero-shot on real hardware, where an enhanced perception module with a lightweight communication protocol reduces delays in high-frequency state estimation and ensures real-time control. Experiments show that JuggleRL achieves an average of $311$ hits over $10$ consecutive trials in the real world, with a maximum of $462$ hits observed, far exceeding a model-based baseline that reaches at most $14$ hits with an average of $3.1$. Moreover, the policy generalizes to unseen conditions, successfully juggling a lighter $5$ g ball with an average of $145.9$ hits. This work demonstrates that reinforcement learning can empower aerial robots with robust and stable control in dynamic interaction tasks.
♻ ☆ SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental connection: the flow rollout is algebraically equivalent to a residual recurrent computation, making it susceptible to the same vanishing and exploding gradients as RNNs. To address this, we reparameterize the velocity network using principles from modern sequential models, introducing two stable architectures: Flow-G, which incorporates a gated velocity, and Flow-T, which utilizes a decoded velocity. We then develop a practical SAC-based algorithm, enabled by a noise-augmented rollout, that facilitates direct end-to-end training of these policies. Our approach supports both from-scratch and offline-to-online learning and achieves state-of-the-art performance on continuous control and robotic manipulation benchmarks, eliminating the need for common workarounds like policy distillation or surrogate objectives.
♻ ☆ Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments
Robots deployed in real-world environments, such as homes, must not only navigate safely but also understand their surroundings and adapt to changes in the environment. To perform tasks efficiently, they must build and maintain a semantic map that accurately reflects the current state of the environment. Existing research on semantic exploration largely focuses on static scenes without persistent object-level instance tracking. In this work, we propose an open-vocabulary, semantic exploration system for semi-static environments. Our system maintains a consistent map by building a probabilistic model of object instance stationarity, systematically tracking semi-static changes, and actively exploring areas that have not been visited for an extended period. In addition to active map maintenance, our approach leverages the map's semantic richness with large language model (LLM)-based reasoning for open-vocabulary object-goal navigation. This enables the robot to search more efficiently by prioritizing contextually relevant areas. We compare our approach against state-of-the-art baselines using publicly available object navigation and mapping datasets, and we further demonstrate real-world transferability in three real-world environments. Our approach outperforms the compared baselines in both success rate and search efficiency for object-navigation tasks and can more reliably handle changes in mapping semi-static environments. In real-world experiments, our system detects 95% of map changes on average, improving efficiency by more than 29% as compared to random and patrol strategies.
♻ ☆ IKDiffuser: a Diffusion-based Generative Inverse Kinematics Solver for Kinematic Trees
Solving Inverse Kinematics (IK) for arbitrary kinematic trees presents significant challenges due to their high-dimensionality, redundancy, and complex inter-branch constraints. Conventional optimization-based solvers can be sensitive to initialization and suffer from local minima or conflicting gradients. At the same time, existing learning-based approaches are often tied to a predefined number of end-effectors and a fixed training objective, limiting their reusability across various robot morphologies and task requirements. To address these limitations, we introduce IKDiffuser, a scalable IK solver built upon conditional diffusion-based generative models, which learns the distribution of the configuration space conditioned on end-effector poses. We propose a structure-agnostic formulation that represents end-effector poses as a sequence of tokens, leading to a unified framework that handles varying numbers of end-effectors while learning the implicit kinematic structures entirely from data. Beyond standard IK generation, IKDiffuser handles partially specified goals via a masked marginalization mechanism that conditions only on a subset of end-effector constraints. Furthermore, it supports adding task objectives at inference through objective-guided sampling, enabling capabilities such as warm-start initialization and manipulability maximization without retraining. Extensive evaluations across seven diverse robotic platforms demonstrate that IKDiffuser significantly outperforms state-of-the-art baselines in accuracy, solution diversity, and collision avoidance. Moreover, when used to initialize optimization-based solvers, IKDiffuser significantly boosts success rates on challenging redundant systems with high Degrees of Freedom (DoF), such as the 29-DoF Unitree G1 humanoid, from 21.01% to 96.96% while reducing computation time to the millisecond range.
comment: under review
♻ ☆ Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
This paper addresses the Kidnapped Robot Problem (KRP), a core localization challenge of relocalizing a robot in a known map without prior pose estimate when localization loss or at SLAM initialization. For this purpose, a passive 2-D global relocalization framework is proposed. It estimates the global pose efficiently and reliably from a single LiDAR scan and an occupancy grid map while the robot remains stationary, thereby enhancing the long-term autonomy of mobile robots. The proposed framework casts global relocalization as a non-convex problem and solves it via the multi-hypothesis scheme with batched multi-stage inference and early termination, balancing completeness and efficiency. The Rapidly-exploring Random Tree (RRT), under traversability constraints, asymptotically covers the reachable space to generate sparse, uniformly distributed feasible positional hypotheses, fundamentally reducing the sampling space. The hypotheses are preliminarily ordered by the proposed Scan Mean Absolute Difference (SMAD), a coarse beam-error level metric that facilitates the early termination by prioritizing high-likelihood candidates. The SMAD computation is optimized for limited scan measurements. The Translation-Affinity Scan-to-Map Alignment Metric (TAM) is proposed for reliable orientation selection at hypothesized positions and accurate final global pose evaluation to mitigate degradation in conventional likelihood-field metrics under translational uncertainty induced by sparse hypotheses, as well as non-panoramic LiDAR scan and environmental changes. Real-world experiments on a resource-constrained mobile robot with non-panoramic LiDAR scans show that the proposed framework achieves competitive performance in success rate, robustness under measurement uncertainty, and computational efficiency.
comment: 10 pages, 8 figures. This work has been submitted to the IEEE for possible publication
♻ ☆ Autonomous Robotic Bone Micro-Milling System with Automatic Calibration and 3D Surface Fitting
Automating bone micro-milling using a robotic system presents challenges due to the uncertainties in both the external and internal features of bone tissue. For example, during mouse cranial window creation, a circular path with a radius of 2 to 4 mm needs to be milled on the mouse skull using a microdrill. The uneven surface and non-uniform thickness of the mouse skull make it difficult to fully automate this process, requiring the system to possess advanced perceptual and adaptive capabilities. In this study, we address this challenge by integrating a Microscopic Stereo Camera System (MSCS) into the robotic bone micro-milling system and proposing a novel online pre-measurement pipeline for the target surface. Starting from uncalibrated cameras, the pipeline enables automatic calibration and 3D surface fitting through a convolutional neural network (CNN)-based keypoint detection. Combined with the existing feedback-based system, we develop the world's first autonomous robotic bone micro-milling system capable of rapidly, in real-time perceiving and adapting to surface unevenness and non-uniform thickness, thereby enabling an end-to-end autonomous cranial window creation workflow without human assistance. Validation experiments on euthanized mice demonstrate that the improved system achieves a success rate of 85.7 % and an average milling time of 2.1 minutes, showing not only significant performance improvements over the previous system but also exceptional accuracy, speed, and stability compared to human operators.
comment: 8 pages, 8 figures, accepted by RA-L. Please refer to the DOI to access the accepted version
♻ ☆ Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving?
The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (El) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article introduces a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning (DRL) for real-time policy optimization. We starts by introducing the foundational principles of EI driving and LMMs. Moreover, we examine the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. A case study is conducted experimentally to validate the performance superiority of our framework in completing lane-change planning task. Finally, several future research directions to empower EI driving are identified to guide subsequent work.
♻ ☆ Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even with a correct textual plan, the generated actions can still miss the intended outcomes in the plan, especially in out-of-distribution (OOD) scenarios. We formalize this phenomenon as a lack of embodied CoT faithfulness, and introduce a training-free, runtime policy steering method for reasoning-action alignment. Given a reasoning VLA's intermediate textual plan, our framework samples multiple candidate action sequences from the same model, predicts their outcomes via simulation, and uses a pre-trained Vision-Language Model (VLM) to select the sequence whose outcome best aligns with the VLA's own textual plan. Only executing action sequences that align with the textual reasoning turns our base VLA's natural action diversity from a source of error into a strength, boosting robustness to semantic and visual OOD perturbations and enabling novel behavior composition without costly re-training. We also contribute a reasoning-annotated extension of LIBERO-100, environment variations tailored for OOD evaluation, and demonstrate up to 15% performance gain over prior work on behavior composition tasks and scales with compute and data diversity. Project Website at: https://yilin-wu98.github.io/steering-reasoning-vla/
♻ ☆ Virtual-force Based Visual Servo for Multiple Peg-in-Hole Assembly with Tightly Coupled Multi-Manipulator
Multiple Peg-in-Hole (MPiH) assembly is one of the fundamental tasks in robotic assembly. In the MPiH tasks for large-size parts, it is challenging for a single manipulator to simultaneously align multiple distant pegs and holes, necessitating tightly coupled multi-manipulator systems. For such MPiH tasks using tightly coupled multiple manipulators, we propose a collaborative visual servo control framework that uses only the monocular in-hand cameras of each manipulator to reduce positioning errors. Initially, we train a state classification neural network and a positioning neural network. The former divides the states of the peg and hole in the image into three categories: obscured, separated, and overlapped, while the latter determines the position of the peg and hole in the image. Based on these findings, we propose a method to integrate the visual features of multiple manipulators using virtual forces, which can naturally combine with the cooperative controller of the multi-manipulator system. To generalize our approach to holes of different appearances, we varied the appearance of the holes during the dataset generation process. The results confirm that by considering the appearance of the holes, classification accuracy and positioning precision can be improved. Finally, the results show that our method achieves 100\% success rate in dual-manipulator dual peg-in-hole tasks with a clearance of 0.2 mm, while robust to camera calibration errors.
comment: 8 pages, 11 figures, this paper has been published by IEEE Robotics and Automation Letters
♻ ☆ AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation
Free space ground segmentation is essential to navigate autonomous robots, recognize drivable zones, and traverse efficiently. Fine-grained features remain challenging for existing segmentation models, particularly for robots in indoor and structured environments. These difficulties arise from ineffective multi-scale processing, suboptimal boundary refinement, and limited feature representation. To address this, we propose Attention-Guided Upsampling with Residual Boundary-Assistive Refinement (AURASeg), a ground-plane semantic segmentation framework designed to improve border precision while preserving strong region accuracy. Built on a ResNet-50 backbone, AURASeg introduces (i) a Residual Border Refinement Module (RBRM) that enhances edge delineation through boundary-assistive feature refinement, and (ii) Attention Progressive Upsampling Decoder (APUD) blocks that progressively fuse multi-level features during decoding. Additionally, we integrate a (iii) lightweight ASPPLite module to capture multi-scale context with minimal overhead. Extensive experiments on CARL-D, the Ground Mobile Robot Perception (GMRP) dataset, and a custom Gazebo indoor dataset show that AURASeg consistently outperforms strong baselines, with notable gains in boundary metrics. Finally, we demonstrate real-time deployment on a Kobuki TurtleBot, validating practical usability. The code is available at https://github.com/Narendhiranv04/AURASeg
comment: 6 pages, 4 figures, 4 tables
Robotics 42
☆ Motion Attribution for Video Generation
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.
comment: See the project website at https://research.nvidia.com/labs/sil/projects/MOTIVE/
☆ Older Adults' Preferences for Feedback Cadence from an Exercise Coach Robot
People can respond to feedback and guidance in different ways, and it is important for robots to personalize their interactions and utilize verbal and nonverbal communication cues. We aim to understand how older adults respond to different cadences of verbal and nonverbal feedback of a robot exercise coach. We conducted an online study of older adults, where participants evaluated videos of the robot giving feedback at different cadences for each modality. The results indicate that changing the cadence of one modality affects the perception of both it and the other modality. We can use the results from this study to better design the frequency of the robot coach's feedback during an exercise session with this population.
comment: Nonarchival submission to RO-MAN 2024 - poster session
☆ Real-Time Localization Framework for Autonomous Basketball Robots
Localization is a fundamental capability for autonomous robots, enabling them to operate effectively in dynamic environments. In Robocon 2025, accurate and reliable localization is crucial for improving shooting precision, avoiding collisions with other robots, and navigating the competition field efficiently. In this paper, we propose a hybrid localization algorithm that integrates classical techniques with learning based methods that rely solely on visual data from the court's floor to achieve self-localization on the basketball field.
comment: 8 pages, 12 figures, Project code: https://github.com/NarenTheNumpkin/Basketball-robot-localization
☆ A Hybrid Model-based and Data-based Approach Developed for a Prosthetic Hand Wrist
The incorporation of advanced control algorithms into prosthetic hands significantly enhances their ability to replicate the intricate motions of a human hand. This work introduces a model-based controller that combines an Artificial Neural Network (ANN) approach with a Sliding Mode Controller (SMC) designed for a tendon-driven soft continuum wrist integrated into a prosthetic hand known as "PRISMA HAND II". Our research focuses on developing a controller that provides a fast dynamic response with reduced computational effort during wrist motions. The proposed controller consists of an ANN for computing bending angles together with an SMC to regulate tendon forces. Kinematic and dynamic models of the wrist are formulated using the Piece-wise Constant Curvature (PCC) hypothesis. The performance of the proposed controller is compared with other control strategies developed for the same wrist. Simulation studies and experimental validations of the fabricated wrist using the controller are included in the paper.
☆ VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, most existing VLA models rely on reactive mappings directly from observations to actions, lacking the explicit reasoning capabilities and persistent memory required for complex, long-horizon navigation tasks. To address these challenges, we propose VLingNav, a VLA model for embodied navigation grounded in linguistic-driven cognition. First, inspired by the dual-process theory of human cognition, we introduce an adaptive chain-of-thought mechanism, which dynamically triggers explicit reasoning only when necessary, enabling the agent to fluidly switch between fast, intuitive execution and slow, deliberate planning. Second, to handle long-horizon spatial dependencies, we develop a visual-assisted linguistic memory module that constructs a persistent, cross-modal semantic memory, enabling the agent to recall past observations to prevent repetitive exploration and infer movement trends for dynamic environments. For the training recipe, we construct Nav-AdaCoT-2.9M, the largest embodied navigation dataset with reasoning annotations to date, enriched with adaptive CoT annotations that induce a reasoning paradigm capable of adjusting both when to think and what to think about. Moreover, we incorporate an online expert-guided reinforcement learning stage, enabling the model to surpass pure imitation learning and to acquire more robust, self-explored navigation behaviors. Extensive experiments demonstrate that VLingNav achieves state-of-the-art performance across a wide range of embodied navigation benchmarks. Notably, VLingNav transfers to real-world robotic platforms in a zero-shot manner, executing various navigation tasks and demonstrating strong cross-domain and cross-task generalization.
comment: Project page: https://wsakobe.github.io/VLingNav-web/
☆ QP-Based Control of an Underactuated Aerial Manipulator under Constraints
This paper presents a constraint-aware control framework for underactuated aerial manipulators, enabling accurate end-effector trajectory tracking while explicitly accounting for safety and feasibility constraints. The control problem is formulated as a quadratic program that computes dynamically consistent generalized accelerations subject to underactuation, actuator bounds, and system constraints. To enhance robustness against disturbances, modeling uncertainties, and steady-state errors, a passivity-based integral action is incorporated at the torque level without compromising feasibility. The effectiveness of the proposed approach is demonstrated through high-fidelity physics-based simulations, which include parameter perturbations, viscous joint friction, and realistic sensing and state-estimation effects. This demonstrates accurate tracking, smooth control inputs, and reliable constraint satisfaction under realistic operating conditions.
☆ Keyframe-based Dense Mapping with the Graph of View-Dependent Local Maps ICRA 2020
In this article, we propose a new keyframe-based mapping system. The proposed method updates local Normal Distribution Transform maps (NDT) using data from an RGB-D sensor. The cells of the NDT are stored in 2D view-dependent structures to better utilize the properties and uncertainty model of RGB-D cameras. This method naturally represents an object closer to the camera origin with higher precision. The local maps are stored in the pose graph which allows correcting global map after loop closure detection. We also propose a procedure that allows merging and filtering local maps to obtain a global map of the environment. Finally, we compare our method with Octomap and NDT-OM and provide example applications of the proposed mapping method.
comment: Accepted in ICRA 2020
☆ Simplifying ROS2 controllers with a modular architecture for robot-agnostic reference generation
This paper introduces a novel modular architecture for ROS2 that decouples the logic required to acquire, validate, and interpolate references from the control laws that track them. The design includes a dedicated component, named Reference Generator, that receives references, in the form of either single points or trajectories, from external nodes (e.g., planners), and writes single-point references at the controller's sampling period via the existing ros2_control chaining mechanism to downstream controllers. This separation removes duplicated reference-handling code from controllers and improves reusability across robot platforms. We implement two reference generators: one for handling joint-space references and one for Cartesian references, along with a set of new controllers (PD with gravity compensation, Cartesian pose, and admittance controllers) and validate the approach on simulated and real Universal Robots and Franka Emika manipulators. Results show that (i) references are tracked reliably in all tested scenarios, (ii) reference generators reduce duplicated reference-handling code across chained controllers to favor the construction and reuse of complex controller pipelines, and (iii) controller implementations remain focused only on control laws.
comment: 5 pages, 7 figures
☆ AUV Trajectory Learning for Underwater Acoustic Energy Transfer and Age Minimization
Internet of underwater things (IoUT) is increasingly gathering attention with the aim of monitoring sea life and deep ocean environment, underwater surveillance as well as maintenance of underwater installments. However, conventional IoUT devices, reliant on battery power, face limitations in lifespan and pose environmental hazards upon disposal. This paper introduces a sustainable approach for simultaneous information uplink from the IoUT devices and acoustic energy transfer (AET) to the devices via an autonomous underwater vehicle (AUV), potentially enabling them to operate indefinitely. To tackle the time-sensitivity, we adopt age of information (AoI), and Jain's fairness index. We develop two deep-reinforcement learning (DRL) algorithms, offering a high-complexity, high-performance frequency division duplex (FDD) solution and a low-complexity, medium-performance time division duplex (TDD) approach. The results elucidate that the proposed FDD and TDD solutions significantly reduce the average AoI and boost the harvested energy as well as data collection fairness compared to baseline approaches.
☆ AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding
Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but often rely on end-to-end sensorimotor models with limited generalization and interpretability. By contrast, methods targeting generalized locomotion typically exhibit limited agility and struggle with visual occlusions. We introduce AME-2, a unified reinforcement learning (RL) framework for agile and generalized locomotion that incorporates a novel attention-based map encoder in the control policy. This encoder extracts local and global mapping features and uses attention mechanisms to focus on salient regions, producing an interpretable and generalized embedding for RL-based control. We further propose a learning-based mapping pipeline that provides fast, uncertainty-aware terrain representations robust to noise and occlusions, serving as policy inputs. It uses neural networks to convert depth observations into local elevations with uncertainties, and fuses them with odometry. The pipeline also integrates with parallel simulation so that we can train controllers with online mapping, aiding sim-to-real transfer. We validate AME-2 with the proposed mapping pipeline on a quadruped and a biped robot, and the resulting controllers demonstrate strong agility and generalization to unseen terrains in simulation and in real-world experiments.
comment: under review
☆ Real2Sim based on Active Perception with automatically VLM-generated Behavior Trees
Constructing an accurate simulation model of real-world environments requires reliable estimation of physical parameters such as mass, geometry, friction, and contact surfaces. Traditional real-to-simulation (Real2Sim) pipelines rely on manual measurements or fixed, pre-programmed exploration routines, which limit their adaptability to varying tasks and user intents. This paper presents a Real2Sim framework that autonomously generates and executes Behavior Trees for task-specific physical interactions to acquire only the parameters required for a given simulation objective, without relying on pre-defined task templates or expert-designed exploration routines. Given a high-level user request, an incomplete simulation description, and an RGB observation of the scene, a vision-language model performs multi-modal reasoning to identify relevant objects, infer required physical parameters, and generate a structured Behavior Tree composed of elementary robotic actions. The resulting behavior is executed on a torque-controlled Franka Emika Panda, enabling compliant, contact-rich interactions for parameter estimation. The acquired measurements are used to automatically construct a physics-aware simulation. Experimental results on the real manipulator demonstrate estimation of object mass, surface height, and friction-related quantities across multiple scenarios, including occluded objects and incomplete prior models. The proposed approach enables interpretable, intent-driven, and autonomously Real2Sim pipelines, bridging high-level reasoning with physically-grounded robotic interaction.
☆ Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving?
The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (El) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article introduces a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning (DRL) for real-time policy optimization. We starts by introducing the foundational principles of EI driving and LMMs. Moreover, we examine the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. A case study is conducted experimentally to validate the performance superiority of our framework in completing lane-change planning task. Finally, several future research directions to empower EI driving are identified to guide subsequent work.
☆ Teaching Robots Like Dogs: Learning Agile Navigation from Luring, Gesture, and Speech
In this work, we aim to enable legged robots to learn how to interpret human social cues and produce appropriate behaviors through physical human guidance. However, learning through physical engagement can place a heavy burden on users when the process requires large amounts of human-provided data. To address this, we propose a human-in-the-loop framework that enables robots to acquire navigational behaviors in a data-efficient manner and to be controlled via multimodal natural human inputs, specifically gestural and verbal commands. We reconstruct interaction scenes using a physics-based simulation and aggregate data to mitigate distributional shifts arising from limited demonstration data. Our progressive goal cueing strategy adaptively feeds appropriate commands and navigation goals during training, leading to more accurate navigation and stronger alignment between human input and robot behavior. We evaluate our framework across six real-world agile navigation scenarios, including jumping over or avoiding obstacles. Our experimental results show that our proposed method succeeds in almost all trials across these scenarios, achieving a 97.15% task success rate with less than 1 hour of demonstration data in total.
comment: 10 pages, 7 figures
☆ Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2
The demand for real-time visual understanding and interaction in complex scenarios is increasingly critical for unmanned aerial vehicles. However, a significant challenge arises from the contradiction between the high computational cost of large Vision language models and the limited computing resources available on UAV edge devices. To address this challenge, this paper proposes a lightweight multimodal task platform based on BLIP-2, integrated with YOLO-World and YOLOv8-Seg models. This integration extends the multi-task capabilities of BLIP-2 for UAV applications with minimal adaptation and without requiring task-specific fine-tuning on drone data. Firstly, the deep integration of BLIP-2 with YOLO models enables it to leverage the precise perceptual results of YOLO for fundamental tasks like object detection and instance segmentation, thereby facilitating deeper visual-attention understanding and reasoning. Secondly, a content-aware key frame sampling mechanism based on K-Means clustering is designed, which incorporates intelligent frame selection and temporal feature concatenation. This equips the lightweight BLIP-2 architecture with the capability to handle video-level interactive tasks effectively. Thirdly, a unified prompt optimization scheme for multi-task adaptation is implemented. This scheme strategically injects structured event logs from the YOLO models as contextual information into BLIP-2's input. Combined with output constraints designed to filter out technical details, this approach effectively guides the model to generate accurate and contextually relevant outputs for various tasks.
comment: The Tenth International Conference on Data Mining and Big Data (DMBD'2025)
☆ Large Language Models to Enhance Multi-task Drone Operations in Simulated Environments
Benefiting from the rapid advancements in large language models (LLMs), human-drone interaction has reached unprecedented opportunities. In this paper, we propose a method that integrates a fine-tuned CodeT5 model with the Unreal Engine-based AirSim drone simulator to efficiently execute multi-task operations using natural language commands. This approach enables users to interact with simulated drones through prompts or command descriptions, allowing them to easily access and control the drone's status, significantly lowering the operational threshold. In the AirSim simulator, we can flexibly construct visually realistic dynamic environments to simulate drone applications in complex scenarios. By combining a large dataset of (natural language, program code) command-execution pairs generated by ChatGPT with developer-written drone code as training data, we fine-tune the CodeT5 to achieve automated translation from natural language to executable code for drone tasks. Experimental results demonstrate that the proposed method exhibits superior task execution efficiency and command understanding capabilities in simulated environments. In the future, we plan to extend the model functionality in a modular manner, enhancing its adaptability to complex scenarios and driving the application of drone technologies in real-world environments.
comment: 1st International Conference on Drones and Unmanned Systems (DAUS' 2025)
☆ Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition
This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterized by partial observability, communication constraints, and dynamic interactions. Each agent's policy is trained with the Multi-Agent Proximal Policy Optimization algorithm and employs a Graph Attention Network encoder that integrates simulated range-sensing data with communication embeddings exchanged among neighboring agents, enabling context-aware decision-making from both local sensing and relational information. In particular, this work introduces a unified framework that integrates graph-based communication and trajectory-aware safety through safety filters. The architecture is supported by a structured reward formulation designed to encourage effective target discovery and acquisition, collision avoidance, and de-correlation between the agents' communication vectors by promoting informational orthogonality. The effectiveness of the proposed reward function is demonstrated through a comprehensive ablation study. Moreover, simulation results demonstrate safe and stable task execution, confirming the framework's effectiveness.
comment: 7 pages, 4 figures, submitted to the IFAC World Congress 2026
☆ ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action prediction, giving rise to the promising vision-language-action (VLA) paradigm. However, most existing approaches overlook the importance of active perception: they typically rely on static, wrist-mounted cameras that provide an end-effector-centric viewpoint. As a result, these models are unable to adaptively select optimal viewpoints or resolutions during task execution, which significantly limits their performance in long-horizon tasks and fine-grained manipulation scenarios. To address these limitations, we propose ActiveVLA, a novel vision-language-action framework that empowers robots with active perception capabilities for high-precision, fine-grained manipulation. ActiveVLA adopts a coarse-to-fine paradigm, dividing the process into two stages: (1) Critical region localization. ActiveVLA projects 3D inputs onto multi-view 2D projections, identifies critical 3D regions, and supports dynamic spatial awareness. (2) Active perception optimization. Drawing on the localized critical regions, ActiveVLA uses an active view selection strategy to choose optimal viewpoints. These viewpoints aim to maximize amodal relevance and diversity while minimizing occlusions. Additionally, ActiveVLA applies a 3D zoom-in to improve resolution in key areas. Together, these steps enable finer-grained active perception for precise manipulation. Extensive experiments demonstrate that ActiveVLA achieves precise 3D manipulation and outperforms state-of-the-art baselines on three simulation benchmarks. Moreover, ActiveVLA transfers seamlessly to real-world scenarios, enabling robots to learn high-precision tasks in complex environments.
☆ Spiking Neural-Invariant Kalman Fusion for Accurate Localization Using Low-Cost IMUs
Low-cost inertial measurement units (IMUs) are widely utilized in mobile robot localization due to their affordability and ease of integration. However, their complex, nonlinear, and time-varying noise characteristics often lead to significant degradation in localization accuracy when applied directly for dead reckoning. To overcome this limitation, we propose a novel brain-inspired state estimation framework that combines a spiking neural network (SNN) with an invariant extended Kalman filter (InEKF). The SNN is designed to extract motion-related features from long sequences of IMU data affected by substantial random noise and is trained via a surrogate gradient descent algorithm to enable dynamic adaptation of the covariance noise parameter within the InEKF. By fusing the SNN output with raw IMU measurements, the proposed method enhances the robustness and accuracy of pose estimation. Extensive experiments conducted on the KITTI dataset and real-world data collected using a mobile robot equipped with a low-cost IMU demonstrate that the proposed approach outperforms state-of-the-art methods in localization accuracy and exhibits strong robustness to sensor noise, highlighting its potential for real-world mobile robot applications.
☆ FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models
Dexterous grasp synthesis remains a central challenge: the high dimensionality and kinematic diversity of multi-fingered hands prevent direct transfer of algorithms developed for parallel-jaw grippers. Existing approaches typically depend on large, hardware-specific grasp datasets collected in simulation or through costly real-world trials, hindering scalability as new dexterous hand designs emerge. To this end, we propose a data-efficient framework, which is designed to bypass robot grasp data collection by exploiting the rich, object-centric semantic priors latent in pretrained generative diffusion models. Temporally aligned and fine-grained grasp affordances are extracted from raw human video demonstrations and fused with 3D scene geometry from depth images to infer semantically grounded contact targets. A kinematics-aware retargeting module then maps these affordance representations to diverse dexterous hands without per-hand retraining. The resulting system produces stable, functionally appropriate multi-contact grasps that remain reliably successful across common objects and tools, while exhibiting strong generalization across previously unseen object instances within a category, pose variations, and multiple hand embodiments. This work (i) introduces a semantic affordance extraction pipeline leveraging vision-language generative priors for dexterous grasping, (ii) demonstrates cross-hand generalization without constructing hardware-specific grasp datasets, and (iii) establishes that a single depth modality suffices for high-performance grasp synthesis when coupled with foundation-model semantics. Our results highlight a path toward scalable, hardware-agnostic dexterous manipulation driven by human demonstrations and pretrained generative models.
☆ A brain-inspired information fusion method for enhancing robot GPS outages navigation
Low-cost inertial navigation systems (INS) are prone to sensor biases and measurement noise, which lead to rapid degradation of navigation accuracy during global positioning system (GPS) outages. To address this challenge and improve positioning continuity in GPS-denied environments, this paper proposes a brain-inspired GPS/INS fusion network (BGFN) based on spiking neural networks (SNNs). The BGFN architecture integrates a spiking Transformer with a spiking encoder to simultaneously extract spatial features from inertial measurement unit (IMU) signals and capture their temporal dynamics. By modeling the relationship between vehicle attitude, specific force, angular rate, and GPS-derived position increments, the network leverages both current and historical IMU data to estimate vehicle motion. The effectiveness of the proposed method is evaluated through real-world field tests and experiments on public datasets. Compared to conventional deep learning approaches, the results demonstrate that BGFN achieves higher accuracy and enhanced reliability in navigation performance, particularly under prolonged GPS outages.
☆ Robust Subpixel Localization of Diagonal Markers in Large-Scale Navigation via Multi-Layer Screening and Adaptive Matching
This paper proposes a robust, high-precision positioning methodology to address localization failures arising from complex background interference in large-scale flight navigation and the computational inefficiency inherent in conventional sliding window matching techniques. The proposed methodology employs a three-tiered framework incorporating multi-layer corner screening and adaptive template matching. Firstly, dimensionality is reduced through illumination equalization and structural information extraction. A coarse-to-fine candidate selection strategy minimizes sliding window computational costs, enabling rapid estimation of the marker's position. Finally, adaptive templates are generated for candidate points, achieving subpixel precision through improved template matching with correlation coefficient extremum fitting. Experimental results demonstrate the method's effectiveness in extracting and localizing diagonal markers in complex, large-scale environments, making it ideal for field-of-view measurement in navigation tasks.
comment: This paper has been accepted by Applied Optics
☆ A Pin-Array Structure for Gripping and Shape Recognition of Convex and Concave Terrain Profiles
This paper presents a gripper capable of grasping and recognizing terrain shapes for mobile robots in extreme environments. Multi-limbed climbing robots with grippers are effective on rough terrains, such as cliffs and cave walls. However, such robots may fall over by misgrasping the surface or getting stuck owing to the loss of graspable points in unknown natural environments. To overcome these issues, we need a gripper capable of adaptive grasping to irregular terrains, not only for grasping but also for measuring the shape of the terrain surface accurately. We developed a gripper that can grasp both convex and concave terrains and simultaneously measure the terrain shape by introducing a pin-array structure. We demonstrated the mechanism of the gripper and evaluated its grasping and terrain recognition performance using a prototype. Moreover, the proposed pin-array design works well for 3D terrain mapping as well as adaptive grasping for irregular terrains.
comment: Author's version of a manuscript accepted at the 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO). (c) IEEE
☆ Efficient Incremental SLAM via Information-Guided and Selective Optimization
We present an efficient incremental SLAM back-end that achieves the accuracy of full batch optimization while substantially reducing computational cost. The proposed approach combines two complementary ideas: information-guided gating (IGG) and selective partial optimization (SPO). IGG employs an information-theoretic criterion based on the log-determinant of the information matrix to quantify the contribution of new measurements, triggering global optimization only when a significant information gain is observed. This avoids unnecessary relinearization and factorization when incoming data provide little additional information. SPO executes multi-iteration Gauss-Newton (GN) updates but restricts each iteration to the subset of variables most affected by the new measurements, dynamically refining this active set until convergence. Together, these mechanisms retain all measurements to preserve global consistency while focusing computation on parts of the graph where it yields the greatest benefit. We provide theoretical analysis showing that the proposed approach maintains the convergence guarantees of full GN. Extensive experiments on benchmark SLAM datasets show that our approach consistently matches the estimation accuracy of batch solvers, while achieving significant computational savings compared to conventional incremental approaches. The results indicate that the proposed approach offers a principled balance between accuracy and efficiency, making it a robust and scalable solution for real-time operation in dynamic data-rich environments.
☆ Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation
Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, precise scene understanding and sample-efficient learning from human demonstrations remain critical challenges, severely hindering the applicability and generalizability of existing frameworks. This paper presents a novel RGMP-S, Recurrent Geometric-prior Multimodal Policy with Spiking features, facilitating both high-level skill reasoning and data-efficient motion synthesis. To ground high-level reasoning in physical reality, we leverage lightweight 2D geometric inductive biases to enable precise 3D scene understanding within the vision-language model. Specifically, we construct a Long-horizon Geometric Prior Skill Selector that effectively aligns the semantic instructions with spatial constraints, ultimately achieving robust generalization in unseen environments. For the data efficiency issue in robotic action generation, we introduce a Recursive Adaptive Spiking Network. We parameterize robot-object interactions via recursive spiking for spatiotemporal consistency, fully distilling long-horizon dynamic features while mitigating the overfitting issue in sparse demonstration scenarios. Extensive experiments are conducted across the Maniskill simulation benchmark and three heterogeneous real-world robotic systems, encompassing a custom-developed humanoid, a desktop manipulator, and a commercial robotic platform. Empirical results substantiate the superiority of our method over state-of-the-art baselines and validate the efficacy of the proposed modules in diverse generalization scenarios. To facilitate reproducibility, the source code and video demonstrations are publicly available at https://github.com/xtli12/RGMP-S.git.
☆ Fairness risk and its privacy-enabled solution in AI-driven robotic applications
Complex decision-making by autonomous machines and algorithms could underpin the foundations of future society. Generative AI is emerging as a powerful engine for such transitions. However, we show that Generative AI-driven developments pose a critical pitfall: fairness concerns. In robotic applications, although intuitions about fairness are common, a precise and implementable definition that captures user utility and inherent data randomness is missing. Here we provide a utility-aware fairness metric for robotic decision making and analyze fairness jointly with user-data privacy, deriving conditions under which privacy budgets govern fairness metrics. This yields a unified framework that formalizes and quantifies fairness and its interplay with privacy, which is tested in a robot navigation task. In view of the fact that under legal requirements, most robotic systems will enforce user privacy, the approach shows surprisingly that such privacy budgets can be jointly used to meet fairness targets. Addressing fairness concerns in the creative combined consideration of privacy is a step towards ethical use of AI and strengthens trust in autonomous robots deployed in everyday environments.
♻ ☆ An Adaptive Neuro-Controller Developed for a Prosthetic Hand Wrist
The significance of employing a controller in prosthetic hands cannot be overstated, as it plays a crucial role in enhancing the functionality and usability of these systems. This paper introduces an adaptive neuro-controller specifically developed for a tendon-driven soft continuum wrist of a prosthetic hand. Kinematic and dynamic modeling of the wrist is carried out using the Timoshenko beam theory. A Neural Network (NN) based strategy is adopted to predict the required motor currents to manipulate the wrist tendons from the errors in the deflection of the wrist section. The Timoshenko beam theory is used to compute the required tendon tension from the input motor current. A comparison of the adaptive neuro-controller with other similar controllers is conducted to analyze the performance of the proposed approach. Simulation studies and experimental validations of the fabricated wrist are included to demonstrate the effectiveness of the controller.
♻ ☆ Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis
Contact-rich manipulation remains a major challenge in robotics. Optical tactile sensors like GelSight Mini offer a low-cost solution for contact sensing by capturing soft-body deformations of the silicone gel. However, accurately inferring shear and normal force distributions from these gel deformations has yet to be fully addressed. In this work, we propose a machine learning approach using a U-net architecture to predict force distributions directly from the sensor's raw images. Our model, trained on force distributions inferred from \ac{fea}, demonstrates promising accuracy in predicting normal and shear force distributions for the commercially available GelSight Mini sensor. It also shows potential for generalization across indenters, sensors of the same type, and for enabling real-time application. The codebase, dataset and models are open-sourced and available at https://feats-ai.github.io .
♻ ☆ Robotic Tele-Operation for Upper Aerodigestive Tract Microsurgery: System Design and Validation
Upper aerodigestive tract (UADT) treatments frequently employ transoral laser microsurgery (TLM) for procedures such as the removal of tumors or polyps. In TLM, a laser beam is used to cut target tissue, while forceps are employed to grasp, manipulate, and stabilize tissue within the UADT. Although TLM systems may rely on different technologies and interfaces, forceps manipulation is still predominantly performed manually, introducing limitations in ergonomics, precision, and controllability. This paper proposes a novel robotic system for tissue manipulation in UADT procedures, based on a novel end-effector designed for forceps control. The system is integrated within a teleoperation framework that employs a robotic manipulator with a programmed remote center of motion (RCM), enabling precise and constrained instrument motion while improving surgeon ergonomics. The proposed approach is validated through two experimental studies and a dedicated usability evaluation, demonstrating its effectiveness and suitability for UADT surgical applications.
comment: I would like to withdraw the paper because I would like to change some of the results in it which will take some time. For this reason, I prefer to remove it and do a new resubmission once I've finished my work
♻ ☆ Using Mobile AR for Rapid Feasibility Analysis for Deployment of Robots: A Usability Study with Non-Expert Users
Automating a production line with robotic arms is a complex, demanding task that requires not only substantial resources but also a deep understanding of the automated processes and available technologies and tools. Expert integrators must consider factors such as placement, payload, and robot reach requirements to determine the feasibility of automation. Ideally, such considerations are based on a detailed digital simulation developed before any hardware is deployed. However, this process is often time-consuming and challenging. To simplify these processes, we introduce a much simpler method for the feasibility analysis of robotic arms' reachability, designed for non-experts. We implement this method through a mobile, sensing-based prototype tool. The two-step experimental evaluation included the expert user study results, which helped us identify the difficulty levels of various deployment scenarios and refine the initial prototype. The results of the subsequent quantitative study with 22 non-expert participants utilizing both scenarios indicate that users could complete both simple and complex feasibility analyses in under ten minutes, exhibiting similar cognitive loads and high engagement. Overall, the results suggest that the tool was well-received and rated as highly usable, thereby showing a new path for changing the ease of feasibility analysis for automation.
comment: Accepted in IEEE RA-L
♻ ☆ RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization
We introduce RGS-SLAM, a robust Gaussian-splatting SLAM framework that replaces the residual-driven densification stage of GS-SLAM with a training-free correspondence-to-Gaussian initialization. Instead of progressively adding Gaussians as residuals reveal missing geometry, RGS-SLAM performs a one-shot triangulation of dense multi-view correspondences derived from DINOv3 descriptors refined through a confidence-aware inlier classifier, generating a well-distributed and structure-aware Gaussian seed prior to optimization. This initialization stabilizes early mapping and accelerates convergence by roughly 20\%, yielding higher rendering fidelity in texture-rich and cluttered scenes while remaining fully compatible with existing GS-SLAM pipelines. Evaluated on the TUM RGB-D and Replica datasets, RGS-SLAM achieves competitive or superior localization and reconstruction accuracy compared with state-of-the-art Gaussian and point-based SLAM systems, sustaining real-time mapping performance at up to 925 FPS. Project page:https://breeze1124.github.io/rgs-slam-project-page/
comment: 10 pages, 9 figures
♻ ☆ Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots
Reduced-order models are central to motion planning and control of quadruped robots, yet existing templates are often hand-crafted for a specific locomotion modality. This motivates the need for automatic methods that extract task-specific, interpretable low-dimensional dynamics directly from data. We propose a methodology that combines a linear autoencoder with symbolic regression to derive such models. The linear autoencoder provides a consistent latent embedding for configurations, velocities, accelerations, and inputs, enabling the sparse identification of nonlinear dynamics (SINDy) to operate in a compact, physics-aligned space. A multi-phase, hybrid-aware training scheme ensures coherent latent coordinates across contact transitions. We focus our validation on quadruped jumping-a representative, challenging, yet contained scenario in which a principled template model is especially valuable. The resulting symbolic dynamics outperform the state-of-the-art handcrafted actuated spring-loaded inverted pendulum (aSLIP) baseline in simulation and hardware across multiple robots and jumping modalities.
comment: 8 pages
♻ ☆ FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis
Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly challenging. In this paper, we present a synthetic garment dataset that can be used for robotic garment folding. We begin by constructing geometric garment templates based on keypoints and applying generative models to generate realistic texture patterns. Leveraging these keypoint annotations, we generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning. To improve robustness, we propose KG-DAgger, which uses a keypoint-based strategy to generate demonstration data for recovering from failures. KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25\%. After training with 15K trajectories (about 2M image-action pairs), the model achieves a 75\% success rate in the real world. Experiments in both simulation and real-world settings validate the effectiveness of our proposed framework.
♻ ☆ DexH2R: Task-oriented Dexterous Manipulation from Human to Robots
Dexterous manipulation is a critical aspect of human capability, enabling interaction with a wide variety of objects. Recent advancements in learning from human demonstrations and teleoperation have enabled progress for robots in such ability. However, these approaches either require complex data collection such as costly human effort for eye-robot contact, or suffer from poor generalization when faced with novel scenarios. To solve both challenges, we propose a framework, DexH2R, that combines human hand motion retargeting with a task-oriented residual action policy, improving task performance by bridging the embodiment gap between human and robotic dexterous hands. Specifically, DexH2R learns the residual policy directly from retargeted primitive actions and task-oriented rewards, eliminating the need for labor-intensive teleoperation systems. Moreover, we incorporate test-time guidance for novel scenarios by taking in desired trajectories of human hands and objects, allowing the dexterous hand to acquire new skills with high generalizability. Extensive experiments in both simulation and real-world environments demonstrate the effectiveness of our work, outperforming prior state-of-the-arts by 40% across various settings.
♻ ☆ Learning Contextually-Adaptive Rewards via Calibrated Features
A key challenge in reward learning from human input is that desired agent behavior often changes based on context. For example, a robot must adapt to avoid a stove once it becomes hot. We observe that while high-level preferences (e.g., prioritizing safety over efficiency) often remain constant, context alters the $\textit{saliency}$--or importance--of reward features. For instance, stove heat changes the relevance of the robot's proximity, not the underlying preference for safety. Moreover, these contextual effects recur across tasks, motivating the need for transferable representations to encode them. Existing multi-task and meta-learning methods simultaneously learn representations and task preferences, at best $\textit{implicitly}$ capturing contextual effects and requiring substantial data to separate them from task-specific preferences. Instead, we propose $\textit{explicitly}$ modeling and learning context-dependent feature saliency separately from context-invariant preferences. We introduce $\textit{calibrated features}$--modular representations that capture contextual effects on feature saliency--and present specialized paired comparison queries that isolate saliency from preference for efficient learning. Simulated experiments show our method improves sample efficiency, requiring 10x fewer preference queries than baselines to achieve equivalent reward accuracy, with up to 15% better performance in low-data regimes (5-10 queries). An in-person user study (N=12) demonstrates that participants can effectively teach their personal contextual preferences with our method, enabling adaptable and personalized reward learning.
comment: Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI '26), March 16 - 19, 2026, Edinburgh, Scotland, UK
♻ ☆ MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving
As one of the automotive sensors that have emerged in recent years, 4D millimeter-wave radar has a higher resolution than conventional 3D radar and provides precise elevation measurements. But its point clouds are still sparse and noisy, making it challenging to meet the requirements of autonomous driving. Camera, as another commonly used sensor, can capture rich semantic information. As a result, the fusion of 4D radar and camera can provide an affordable and robust perception solution for autonomous driving systems. However, previous radar-camera fusion methods have not yet been thoroughly investigated, resulting in a large performance gap compared to LiDAR-based methods. Specifically, they ignore the feature-blurring problem and do not deeply interact with image semantic information. To this end, we present a simple but effective multi-stage sampling fusion (MSSF) network based on 4D radar and camera. On the one hand, we design a fusion block that can deeply interact point cloud features with image features, and can be applied to commonly used single-modal backbones in a plug-and-play manner. The fusion block encompasses two types, namely, simple feature fusion (SFF) and multiscale deformable feature fusion (MSDFF). The SFF is easy to implement, while the MSDFF has stronger fusion abilities. On the other hand, we propose a semantic-guided head to perform foreground-background segmentation on voxels with voxel feature re-weighting, further alleviating the problem of feature blurring. Extensive experiments on the View-of-Delft (VoD) and TJ4DRadset datasets demonstrate the effectiveness of our MSSF. Notably, compared to state-of-the-art methods, MSSF achieves a 7.0% and 4.0% improvement in 3D mean average precision on the VoD and TJ4DRadSet datasets, respectively. It even surpasses classical LiDAR-based methods on the VoD dataset.
comment: T-TITS accepted, code avaliable
♻ ☆ Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission
To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. LiDAR sensors capture 3D in real time, but produce sparce point clouds. Therefore, this paper presents a high-speed LiDAR point cloud densification method to generate dense 3D scene with minimal latency, addressing the need for on-the-fly depth completion while maintaining real-time performance. Our approach combines multiple LiDAR inputs with high-resolution color images and applies a joint bilateral filtering strategy implemented through a convolutional neural network architecture. Experiments demonstrate that the proposed method produces dense depth maps at full HD resolution in real time (30 fps), which is over 15x faster than a recent training-based depth completion approach. The resulting dense point clouds exhibit accurate geometry without multiview inconsistencies or ghosting artifacts.
♻ ☆ Variable Elimination in Hybrid Factor Graphs for Discrete-Continuous Inference & Estimation
Many hybrid problems in robotics involve both continuous and discrete components, and modeling them together for estimation tasks has been a long standing and difficult problem. Hybrid Factor Graphs give us a mathematical framework to model these types of problems, however existing approaches for solving them are based on approximations. In this work, we propose an efficient Hybrid Factor Graph framework alongwith a variable elimination algorithm to produce a hybrid Bayes network, which can then be used for exact Maximum A Posteriori estimation and marginalization over both sets of variables. Our approach first develops a novel hybrid Gaussian factor which can connect to both discrete and continuous variables, and a hybrid conditional which can represent multiple continuous hypotheses conditioned on the discrete variables. Using these representations, we derive the process of hybrid variable elimination under the Conditional Linear Gaussian scheme, giving us exact posteriors as hybrid Bayes network. To bound the number of discrete hypotheses, we use a tree-structured representation of the factors coupled with a simple pruning and probabilistic assignment scheme, which allows for tractable inference. We demonstrate the applicability of our framework on a SLAM dataset with ambiguous measurements, where discrete choices for the most likely measurement have to be made. Our demonstrated results showcase the accuracy, generality, and simplicity of our hybrid factor graph framework.
♻ ☆ On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular, they are primarily trained via supervised fine-tuning or training-time reinforcement learning, requiring explicit fine-tuning phases, human interventions, or controlled data collection. Consequently, existing methods remain unsuitable for challenging simulated- or physical-world deployments, where robots must respond autonomously and flexibly to evolving environments. To address this limitation, we introduce a Test-Time Reinforcement Learning for VLAs (TT-VLA), a framework that enables on-the-fly policy adaptation during inference. TT-VLA formulates a dense reward mechanism that leverages step-by-step task-progress signals to refine action policies during test time while preserving the SFT/RL-trained priors, making it an effective supplement to current VLA models. Empirical results show that our approach enhances overall adaptability, stability, and task success in dynamic, previously unseen scenarios under simulated and real-world settings. We believe TT-VLA offers a principled step toward self-improving, deployment-ready VLAs.
♻ ☆ Cross-Domain Imitation Learning via Optimal Transport ICLR 2022
Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajectories and stationary distributions between the expert and imitation agents is challenging because they live on different systems that may not even have the same dimensionality. We propose Gromov-Wasserstein Imitation Learning (GWIL), a method for cross-domain imitation that uses the Gromov-Wasserstein distance to align and compare states between the different spaces of the agents. Our theory formally characterizes the scenarios where GWIL preserves optimality, revealing its possibilities and limitations. We demonstrate the effectiveness of GWIL in non-trivial continuous control domains ranging from simple rigid transformation of the expert domain to arbitrary transformation of the state-action space.
comment: ICLR 2022
♻ ☆ Ensemble-Based Event Camera Place Recognition Under Varying Illumination
Compared to conventional cameras, event cameras provide a high dynamic range and low latency, offering greater robustness to rapid motion and challenging lighting conditions. Although the potential of event cameras for visual place recognition (VPR) has been established, developing robust VPR frameworks under severe illumination changes remains an open research problem. In this paper, we introduce an ensemble-based approach to event camera place recognition that combines sequence-matched results from multiple event-to-frame reconstructions, VPR feature extractors, and temporal resolutions. Unlike previous event-based ensemble methods, which only utilise temporal resolution, our broader fusion strategy delivers significantly improved robustness under varied lighting conditions (e.g., afternoon, sunset, night), achieving a 57% relative improvement in Recall@1 across day-night transitions. We evaluate our approach on two long-term driving datasets (with 8 km per traverse) without metric subsampling, thereby preserving natural variations in speed and stop duration that influence event density. We also conduct a comprehensive analysis of key design choices, including binning strategies, polarity handling, reconstruction methods, and feature extractors, to identify the most critical components for robust performance. Additionally, we propose a modification to the standard sequence matching framework that enhances performance at longer sequence lengths. To facilitate future research, we will release our codebase and benchmarking framework.
♻ ☆ Human-in-the-Loop Segmentation of Multi-species Coral Imagery CVPR 2024
Marine surveys by robotic underwater and surface vehicles result in substantial quantities of coral reef imagery, however labeling these images is expensive and time-consuming for domain experts. Point label propagation is a technique that uses existing images labeled with sparse points to create augmented ground truth data, which can be used to train a semantic segmentation model. In this work, we show that recent advances in large foundation models facilitate the creation of augmented ground truth masks using only features extracted by the denoised version of the DINOv2 foundation model and K-Nearest Neighbors (KNN), without any pre-training. For images with extremely sparse labels, we use human-in-the-loop principles to enhance annotation efficiency: if there are 5 point labels per image, our method outperforms the prior state-of-the-art by 19.7% for mIoU. When human-in-the-loop labeling is not available, using the denoised DINOv2 features with a KNN still improves on the prior state-of-the-art by 5.8% for mIoU (5 grid points). On the semantic segmentation task, we outperform the prior state-of-the-art by 13.5% for mIoU when only 5 point labels are used for point label propagation. Additionally, we perform a comprehensive study into the number and placement of point labels, and make several recommendations for improving the efficiency of labeling images with points.
comment: IEEE Journal of Oceanic Engineering accepted preprint of extended paper, 36 pages, 14 figures. Original conference paper (v2) accepted at the CVPR 2024 3rd Workshop on Learning with Limited Labelled Data for Image and Video Understanding (L3D-IVU)
♻ ☆ Look as You Leap: Planning Simultaneous Motion and Perception for High-DOF Robots
Most common tasks for robots in dynamic spaces require that the environment is regularly and actively perceived, with many of them explicitly requiring objects or persons to be within view, i.e., for monitoring or safety. However, solving motion and perception tasks simultaneously is challenging, as these objectives often impose conflicting requirements. Furthermore, while robots must react quickly to changes in the environment, directly evaluating the quality of perception (e.g., object detection confidence) is often expensive or infeasible at runtime. This problem is especially important in human-centered environments, such as homes and hospitals, where effective perception is essential for safe and reliable operation. In this work, we address the challenge of solving motion planning problems for high-degree-of-freedom (DoF) robots from a start to a goal configuration with continuous perception constraints under both static and dynamic environments. We propose a GPU-parallelized perception-score-guided probabilistic roadmap planner with a neural surrogate model (PS-PRM). Unlike existing active perception-, visibility-aware or learning-based planners, our work integrates perception tasks and constraints directly into the motion planning formulation. Our method uses a neural surrogate model to approximate perception scores, incorporates them into the roadmap, and leverages GPU parallelism to enable efficient online replanning in dynamic settings. We demonstrate that our planner, evaluated on high-DoF robots, outperforms baseline methods in both static and dynamic environments in both simulation and real-robot experiments.
comment: 20 pages, 13 figures, under review
Robotics 47
☆ Video Generation Models in Robotics -- Applications, Research Challenges, Future Directions
Video generation models have emerged as high-fidelity models of the physical world, capable of synthesizing high-quality videos capturing fine-grained interactions between agents and their environments conditioned on multi-modal user inputs. Their impressive capabilities address many of the long-standing challenges faced by physics-based simulators, driving broad adoption in many problem domains, e.g., robotics. For example, video models enable photorealistic, physically consistent deformable-body simulation without making prohibitive simplifying assumptions, which is a major bottleneck in physics-based simulation. Moreover, video models can serve as foundation world models that capture the dynamics of the world in a fine-grained and expressive way. They thus overcome the limited expressiveness of language-only abstractions in describing intricate physical interactions. In this survey, we provide a review of video models and their applications as embodied world models in robotics, encompassing cost-effective data generation and action prediction in imitation learning, dynamics and rewards modeling in reinforcement learning, visual planning, and policy evaluation. Further, we highlight important challenges hindering the trustworthy integration of video models in robotics, which include poor instruction following, hallucinations such as violations of physics, and unsafe content generation, in addition to fundamental limitations such as significant data curation, training, and inference costs. We present potential future directions to address these open research challenges to motivate research and ultimately facilitate broader applications, especially in safety-critical settings.
☆ Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
Post-training algorithms based on deep reinforcement learning can push the limits of robotic models for specific objectives, such as generalizability, accuracy, and robustness. However, Intervention-requiring Failures (IR Failures) (e.g., a robot spilling water or breaking fragile glass) during real-world exploration happen inevitably, hindering the practical deployment of such a paradigm. To tackle this, we introduce Failure-Aware Offline-to-Online Reinforcement Learning (FARL), a new paradigm minimizing failures during real-world reinforcement learning. We create FailureBench, a benchmark that incorporates common failure scenarios requiring human intervention, and propose an algorithm that integrates a world-model-based safety critic and a recovery policy trained offline to prevent failures during online exploration. Extensive simulation and real-world experiments demonstrate the effectiveness of FARL in significantly reducing IR Failures while improving performance and generalization during online reinforcement learning post-training. FARL reduces IR Failures by 73.1% while elevating performance by 11.3% on average during real-world RL post-training. Videos and code are available at https://failure-aware-rl.github.io.
comment: Project page: https://failure-aware-rl.github.io
☆ Data-driven control of hydraulic impact hammers under strict operational and control constraints
This paper presents a data-driven methodology for the control of static hydraulic impact hammers, also known as rock breakers, which are commonly used in the mining industry. The task addressed in this work is that of controlling the rock-breaker so its end-effector reaches arbitrary target poses, which is required in normal operation to place the hammer on top of rocks that need to be fractured. The proposed approach considers several constraints, such as unobserved state variables due to limited sensing and the strict requirement of using a discrete control interface at the joint level. First, the proposed methodology addresses the problem of system identification to obtain an approximate dynamic model of the hydraulic arm. This is done via supervised learning, using only teleoperation data. The learned dynamic model is then exploited to obtain a controller capable of reaching target end-effector poses. For policy synthesis, both reinforcement learning (RL) and model predictive control (MPC) algorithms are utilized and contrasted. As a case study, we consider the automation of a Bobcat E10 mini-excavator arm with a hydraulic impact hammer attached as end-effector. Using this machine, both the system identification and policy synthesis stages are studied in simulation and in the real world. The best RL-based policy consistently reaches target end-effector poses with position errors below 12 cm and pitch angle errors below 0.08 rad in the real world. Considering that the impact hammer has a 4 cm diameter chisel, this level of precision is sufficient for breaking rocks. Notably, this is accomplished by relying only on approximately 68 min of teleoperation data to train and 8 min to evaluate the dynamic model, and without performing any adjustments for a successful policy Sim2Real transfer. A demonstration of policy execution in the real world can be found in https://youtu.be/e-7tDhZ4ZgA.
comment: 21 pages, 14 figures
☆ Affordable Data Collection System for UAVs Taxi Vibration Testing
Structural vibration testing plays a key role in aerospace engineering for evaluating dynamic behaviour, ensuring reliability and verifying structural integrity. These tests rely on accurate and robust data acquisition systems (DAQ) to capture high-quality acceleration data. However, commercial DAQs that provide the required performance and features are often expensive and complex, limiting their accessibility for small-scale research and experimental applications. This work presents the design and experimental validation of an affordable and in-house-developed acceleration DAQ, tested on a small fixed-wing UAV through several Taxi Vibration Test (TVT) runs and ambient vibration measurements. The proposed system integrates several OrangePi 3 LTS single-board computers with multiple LSM6DS3TR-C MEMS inertial measurement units operating simultaneously via an Inter-Integrated Circuit (I2C) communication interface, managed under a Python-based master/slave architecture. Data is acquired at a stable sampling rate of approximately 208 Hz and post-processed using Welch's method to estimate their Power Spectral Density (PSD). Results confirm the system ability to provide consistent multi-sensor acceleration data and repeatable PSD profiles under the same test conditions; thus, demonstrating its reliability. With a total hardware cost below 600 EUR (approximately 690 USD), the developed DAQ offers a compact, scalable and cost-effective alternative for aerospace vibration analysis and structural testing.
☆ THETA: Triangulated Hand-State Estimation for Teleoperation and Automation in Robotic Hand Control
The teleoperation of robotic hands is limited by the high costs of depth cameras and sensor gloves, commonly used to estimate hand relative joint positions (XYZ). We present a novel, cost-effective approach using three webcams for triangulation-based tracking to approximate relative joint angles (theta) of human fingers. We also introduce a modified DexHand, a low-cost robotic hand from TheRobotStudio, to demonstrate THETA's real-time application. Data collection involved 40 distinct hand gestures using three 640x480p webcams arranged at 120-degree intervals, generating over 48,000 RGB images. Joint angles were manually determined by measuring midpoints of the MCP, PIP, and DIP finger joints. Captured RGB frames were processed using a DeepLabV3 segmentation model with a ResNet-50 backbone for multi-scale hand segmentation. The segmented images were then HSV-filtered and fed into THETA's architecture, consisting of a MobileNetV2-based CNN classifier optimized for hierarchical spatial feature extraction and a 9-channel input tensor encoding multi-perspective hand representations. The classification model maps segmented hand views into discrete joint angles, achieving 97.18% accuracy, 98.72% recall, F1 Score of 0.9274, and a precision of 0.8906. In real-time inference, THETA captures simultaneous frames, segments hand regions, filters them, and compiles a 9-channel tensor for classification. Joint-angle predictions are relayed via serial to an Arduino, enabling the DexHand to replicate hand movements. Future research will increase dataset diversity, integrate wrist tracking, and apply computer vision techniques such as OpenAI-Vision. THETA potentially ensures cost-effective, user-friendly teleoperation for medical, linguistic, and manufacturing applications.
comment: The 11th International Conference on Engineering and Emerging Technologies (ICEET) 2025
☆ Predefined-time One-Shot Cooperative Estimation, Guidance, and Control for Simultaneous Target Interception
This work develops a unified nonlinear estimation-guidance-control framework for cooperative simultaneous interception of a stationary target under a heterogeneous sensing topology, where sensing capabilities are non-uniform across interceptors. Specifically, only a subset of agents is instrumented with onboard seekers (informed/seeker-equipped agents), whereas the rest of them (seeker-less agents) acquire the information about the target indirectly via the informed agents and execute a distributed cooperative guidance for simultaneous target interception. To address the resulting partial observability, a predefined-time distributed observer is leveraged, guaranteeing convergence of the target state estimates for seeker-less agents through information exchange with seeker-equipped neighbors over a directed communication graph. Thereafter, an improved time-to-go estimate accounting for wide launch envelopes is utilized to design the distributed cooperative guidance commands. This estimate is coupled with a predefined-time consensus protocol, ensuring consensus in the agents' time-to-go values. The temporal upper bounds within which both observer error and time-to-go consensus error converge to zero can be prescribed as design parameters. Furthermore, the cooperative guidance commands are realized by means of an autopilot, wherein the interceptor is steered by canard actuation. The corresponding fin deflection commands are generated using a predefined-time convergent sliding mode control law. This enables the autopilot to precisely track the commanded lateral acceleration within a design-specified time, while maintaining non-singularity of the overall design. Theoretical guarantees are supported by numerical simulations across diverse engagement geometries, verifying the estimation accuracy, the cooperative interception performance, and the autopilot response using the proposed scheme.
☆ FMAC: a Fair Fiducial Marker Accuracy Comparison Software
This paper presents a method for carrying fair comparisons of the accuracy of pose estimation using fiducial markers. These comparisons rely on large sets of high-fidelity synthetic images enabling deep exploration of the 6 degrees of freedom. A low-discrepancy sampling of the space allows to check the correlations between each degree of freedom and the pose errors by plotting the 36 pairs of combinations. The images are rendered using a physically based ray tracing code that has been specifically developed to use the standard calibration coefficients of any camera directly. The software reproduces image distortions, defocus and diffraction blur. Furthermore, sub-pixel sampling is applied to sharp edges to enhance the fidelity of the rendered image. After introducing the rendering algorithm and its experimental validation, the paper proposes a method for evaluating the pose accuracy. This method is applied to well-known markers, revealing their strengths and weaknesses for pose estimation. The code is open source and available on GitHub.
☆ Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids
Achieving robust humanoid hiking in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception. However, integrating exteroception remains a significant challenge: mapping-based methods suffer from state estimation drift; for instance, LiDAR-based methods do not handle torso jitter well. Existing end-to-end approaches often struggle with scalability and training complexity; specifically, some previous works using virtual obstacles are implemented case-by-case. In this work, we present \textit{Hiking in the Wild}, a scalable, end-to-end parkour perceptive framework designed for robust humanoid hiking. To ensure safety and training stability, we introduce two key mechanisms: a foothold safety mechanism combining scalable \textit{Terrain Edge Detection} with \textit{Foot Volume Points} to prevent catastrophic slippage on edges, and a \textit{Flat Patch Sampling} strategy that mitigates reward hacking by generating feasible navigation targets. Our approach utilizes a single-stage reinforcement learning scheme, mapping raw depth inputs and proprioception directly to joint actions, without relying on external state estimation. Extensive field experiments on a full-size humanoid demonstrate that our policy enables robust traversal of complex terrains at speeds up to 2.5 m/s. The training and deployment code is open-sourced to facilitate reproducible research and deployment on real robots with minimal hardware modifications.
comment: Project Page: https://project-instinct.github.io/hiking-in-the-wild
☆ Deep Whole-body Parkour
Current approaches to humanoid control generally fall into two paradigms: perceptive locomotion, which handles terrain well but is limited to pedal gaits, and general motion tracking, which reproduces complex skills but ignores environmental capabilities. This work unites these paradigms to achieve perceptive general motion control. We present a framework where exteroceptive sensing is integrated into whole-body motion tracking, permitting a humanoid to perform highly dynamic, non-locomotion tasks on uneven terrain. By training a single policy to perform multiple distinct motions across varied terrestrial features, we demonstrate the non-trivial benefit of integrating perception into the control loop. Our results show that this framework enables robust, highly dynamic multi-contact motions, such as vaulting and dive-rolling, on unstructured terrain, significantly expanding the robot's traversability beyond simple walking or running. https://project-instinct.github.io/deep-whole-body-parkour
☆ Aggregating swarms through morphology handling design contingencies: from the sweet spot to a rich expressivity
Morphological computing, the use of the physical design of a robot to ease the realization of a given task has been proven to be a relevant concept in the context of swarm robotics. Here we demonstrate both experimentally and numerically, that the success of such a strategy may heavily rely on the type of policy adopted by the robots, as well as on the details of the physical design. To do so, we consider a swarm of robots, composed of Kilobots embedded in an exoskeleton, the design of which controls the propensity of the robots to align or anti-align with the direction of the external force they experience. We find experimentally that the contrast that was observed between the two morphologies in the success rate of a simple phototactic task, where the robots were programmed to stop when entering a light region, becomes dramatic, if the robots are not allowed to stop, and can only slow down. Building on a faithful physical model of the self-aligning dynamics of the robots, we perform numerical simulations and demonstrate on one hand that a precise tuning of the self-aligning strength around a sweet spot is required to achieve an efficient phototactic behavior, on the other hand that exploring a range of self-alignment strength allows for a rich expressivity of collective behaviors.
comment: 8 pages, 3 figures
☆ Stable In-hand Manipulation for a Lightweight Four-motor Prosthetic Hand
Electric prosthetic hands should be lightweight to decrease the burden on the user, shaped like human hands for cosmetic purposes, and designed with motors enclosed inside to protect them from damage and dirt. Additionally, in-hand manipulation is necessary to perform daily activities such as transitioning between different postures, particularly through rotational movements, such as reorienting a pen into a writing posture after picking it up from a desk. We previously developed PLEXUS hand (Precision-Lateral dEXteroUS manipulation hand), a lightweight (311 g) prosthetic hand driven by four motors. This prosthetic performed reorientation between precision and lateral grasps with various objects. However, its controller required predefined object widths and was limited to handling lightweight objects (of weight up to 34 g). This study addresses these limitations by employing motor current feedback. Combined with the hand's previously optimized single-axis thumb, this approach achieves more stable manipulation by estimating the object's width and adjusting the index finger position to maintain stable object holding during the reorientation. Experimental validation using primitive objects of various widths (5-30 mm) and shapes (cylinders and prisms) resulted in a 100% success rate with lightweight objects and maintained a high success rate (>=80) even with heavy aluminum prisms (of weight up to 289 g). By contrast, the performance without index finger coordination dropped to just 40% on the heaviest 289 g prism. The hand also successfully executed several daily tasks, including closing bottle caps and orienting a pen for writing.
☆ FlyCo: Foundation Model-Empowered Drones for Autonomous 3D Structure Scanning in Open-World Environments
Autonomous 3D scanning of open-world target structures via drones remains challenging despite broad applications. Existing paradigms rely on restrictive assumptions or effortful human priors, limiting practicality, efficiency, and adaptability. Recent foundation models (FMs) offer great potential to bridge this gap. This paper investigates a critical research problem: What system architecture can effectively integrate FM knowledge for this task? We answer it with FlyCo, a principled FM-empowered perception-prediction-planning loop enabling fully autonomous, prompt-driven 3D target scanning in diverse unknown open-world environments. FlyCo directly translates low-effort human prompts (text, visual annotations) into precise adaptive scanning flights via three coordinated stages: (1) perception fuses streaming sensor data with vision-language FMs for robust target grounding and tracking; (2) prediction distills FM knowledge and combines multi-modal cues to infer the partially observed target's complete geometry; (3) planning leverages predictive foresight to generate efficient and safe paths with comprehensive target coverage. Building on this, we further design key components to boost open-world target grounding efficiency and robustness, enhance prediction quality in terms of shape accuracy, zero-shot generalization, and temporal stability, and balance long-horizon flight efficiency with real-time computability and online collision avoidance. Extensive challenging real-world and simulation experiments show FlyCo delivers precise scene understanding, high efficiency, and real-time safety, outperforming existing paradigms with lower human effort and verifying the proposed architecture's practicality. Comprehensive ablations validate each component's contribution. FlyCo also serves as a flexible, extensible blueprint, readily leveraging future FM and robotics advances. Code will be released.
comment: 34 pages, 24 figures, 9 tables. Video: https://www.youtube.com/playlist?list=PLqjZjnqsCyl40rw3y15Yzc7Mdo-z1y2j8
☆ NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics
Autonomous nano-drones, powered by vision-based tiny machine learning (TinyML) models, are a novel technology gaining momentum thanks to their broad applicability and pushing scientific advancement on resource-limited embedded systems. Their small form factor, i.e., a few 10s grams, severely limits their onboard computational resources to sub-\SI{100}{\milli\watt} microcontroller units (MCUs). The Bitcraze Crazyflie nano-drone is the \textit{de facto} standard, offering a rich set of programmable MCUs for low-level control, multi-core processing, and radio transmission. However, roboticists very often underutilize these onboard precious resources due to the absence of a simple yet efficient software layer capable of time-optimal pipelining of multi-buffer image acquisition, multi-core computation, intra-MCUs data exchange, and Wi-Fi streaming, leading to sub-optimal control performances. Our \textit{NanoCockpit} framework aims to fill this gap, increasing the throughput and minimizing the system's latency, while simplifying the developer experience through coroutine-based multi-tasking. In-field experiments on three real-world TinyML nanorobotics applications show our framework achieves ideal end-to-end latency, i.e. zero overhead due to serialized tasks, delivering quantifiable improvements in closed-loop control performance ($-$30\% mean position error, mission success rate increased from 40\% to 100\%).
comment: Source code available on GitHub at https://github.com/idsia-robotics/crazyflie-nanocockpit
☆ WaveMan: mmWave-Based Room-Scale Human Interaction Perception for Humanoid Robots
Reliable humanoid-robot interaction (HRI) in household environments is constrained by two fundamental requirements, namely robustness to unconstrained user positions and preservation of user privacy. Millimeter-wave (mmWave) sensing inherently supports privacy-preserving interaction, making it a promising modality for room-scale HRI. However, existing mmWave-based interaction-sensing systems exhibit poor spatial generalization at unseen distances or viewpoints. To address this challenge, we introduce WaveMan, a spatially adaptive room-scale perception system that restores reliable human interaction sensing across arbitrary user positions. WaveMan integrates viewpoint alignment and spectrogram enhancement for spatial consistency, with dual-channel attention for robust feature extraction. Experiments across five participants show that, under fixed-position evaluation, WaveMan achieves the same cross-position accuracy as the baseline with five times fewer training positions. In random free-position testing, accuracy increases from 33.00% to 94.33%, enabled by the proposed method. These results demonstrate the feasibility of reliable, privacy-preserving interaction for household humanoid robots across unconstrained user positions.
☆ LOONG: Online Time-Optimal Autonomous Flight for MAVs in Cluttered Environments
Autonomous flight of micro air vehicles (MAVs) in unknown, cluttered environments remains challenging for time-critical missions due to conservative maneuvering strategies. This article presents an integrated planning and control framework for high-speed, time-optimal autonomous flight of MAVs in cluttered environments. In each replanning cycle (100 Hz), a time-optimal trajectory under polynomial presentation is generated as a reference, with the time-allocation process accelerated by imitation learning. Subsequently, a time-optimal model predictive contouring control (MPCC) incorporates safe flight corridor (SFC) constraints at variable horizon steps to enable aggressive yet safe maneuvering, while fully exploiting the MAV's dynamics. We validate the proposed framework extensively on a custom-built LiDAR-based MAV platform. Simulation results demonstrate superior aggressiveness compared to the state of the art, while real-world experiments achieve a peak speed of 18 m/s in a cluttered environment and succeed in 10 consecutive trials from diverse start points. The video is available at the following link: https://youtu.be/vexXXhv99oQ.
☆ Optimizing the Design of a Simple Three-Sphere Magnetic Microswimmer
When swimming at low Reynolds numbers, inertial effects are negligible and reciprocal movements cannot induce net motion. Instead, symmetry breaking is necessary to achieve net propulsion. Directed swimming can be supported by magnetic fields, which simultaneously provide a versatile means of remote actuation. Thus, we analyze the motion of a straight microswimmer composed of three magnetizable beads connected by two elastic links. The swimming mechanism is based on oriented external magnetic fields that oscillate in magnitude. Through induced reversible hysteretic collapse of the two segments of the swimmer, the two pairs of beads jump into contact and separate nonreciprocally. Due to higher-order hydrodynamic interactions, net displacement results after each cycle. Different microswimmers can be tuned to different driving amplitudes and frequencies, allowing for simultaneous independent control by just one external magnetic field. The swimmer geometry and magnetic field shape are optimized for maximum swimming speed using an evolutionary optimization strategy. Thanks to the simple working principle, an experimental realization of such a microrobot seems feasible and may open new approaches for microinvasive medical interventions such as targeted drug delivery.
comment: 10 pages, 7 figures
☆ Large-Scale Autonomous Gas Monitoring for Volcanic Environments: A Legged Robot on Mount Etna
Volcanic gas emissions are key precursors of eruptive activity. Yet, obtaining accurate near-surface measurements remains hazardous and logistically challenging, motivating the need for autonomous solutions. Limited mobility in rough volcanic terrain has prevented wheeled systems from performing reliable in situ gas measurements, reducing their usefulness as sensing platforms. We present a legged robotic system for autonomous volcanic gas analysis, utilizing the quadruped ANYmal, equipped with a quadrupole mass spectrometer system. Our modular autonomy stack integrates a mission planning interface, global planner, localization framework, and terrain-aware local navigation. We evaluated the system on Mount Etna across three autonomous missions in varied terrain, achieving successful gas-source detections with autonomy rates of 93-100%. In addition, we conducted a teleoperated mission in which the robot measured natural fumaroles, detecting sulfur dioxide and carbon dioxide. We discuss lessons learned from the gas-analysis and autonomy perspectives, emphasizing the need for adaptive sensing strategies, tighter integration of global and local planning, and improved hardware design.
comment: 12 pages, 7 figures, submitted to IEEE Robotics & Automation Magazine (RAM)
☆ OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Image
6D object pose estimation plays a crucial role in scene understanding for applications such as robotics and augmented reality. To support the needs of ever-changing object sets in such context, modern zero-shot object pose estimators were developed to not require object-specific training but only rely on CAD models. Such models are hard to obtain once deployed, and a continuously changing and growing set of objects makes it harder to reliably identify the instance model of interest. To address this challenge, we introduce an Open-Set CAD Retrieval from a Language Prompt and a Single Image (OSCAR), a novel training-free method that retrieves a matching object model from an unlabeled 3D object database. During onboarding, OSCAR generates multi-view renderings of database models and annotates them with descriptive captions using an image captioning model. At inference, GroundedSAM detects the queried object in the input image, and multi-modal embeddings are computed for both the Region-of-Interest and the database captions. OSCAR employs a two-stage retrieval: text-based filtering using CLIP identifies candidate models, followed by image-based refinement using DINOv2 to select the most visually similar object. In our experiments we demonstrate that OSCAR outperforms all state-of-the-art methods on the cross-domain 3D model retrieval benchmark MI3DOR. Furthermore, we demonstrate OSCAR's direct applicability in automating object model sourcing for 6D object pose estimation. We propose using the most similar object model for pose estimation if the exact instance is not available and show that OSCAR achieves an average precision of 90.48\% during object retrieval on the YCB-V object dataset. Moreover, we demonstrate that the most similar object model can be utilized for pose estimation using Megapose achieving better results than a reconstruction-based approach.
☆ Heterogeneous Multi-Expert Reinforcement Learning for Long-Horizon Multi-Goal Tasks in Autonomous Forklifts
Autonomous mobile manipulation in unstructured warehouses requires a balance between efficient large-scale navigation and high-precision object interaction. Traditional end-to-end learning approaches often struggle to handle the conflicting demands of these distinct phases. Navigation relies on robust decision-making over large spaces, while manipulation needs high sensitivity to fine local details. Forcing a single network to learn these different objectives simultaneously often causes optimization interference, where improving one task degrades the other. To address these limitations, we propose a Heterogeneous Multi-Expert Reinforcement Learning (HMER) framework tailored for autonomous forklifts. HMER decomposes long-horizon tasks into specialized sub-policies controlled by a Semantic Task Planner. This structure separates macro-level navigation from micro-level manipulation, allowing each expert to focus on its specific action space without interference. The planner coordinates the sequential execution of these experts, bridging the gap between task planning and continuous control. Furthermore, to solve the problem of sparse exploration, we introduce a Hybrid Imitation-Reinforcement Training Strategy. This method uses expert demonstrations to initialize the policy and Reinforcement Learning for fine-tuning. Experiments in Gazebo simulations show that HMER significantly outperforms sequential and end-to-end baselines. Our method achieves a task success rate of 94.2\% (compared to 62.5\% for baselines), reduces operation time by 21.4\%, and maintains placement error within 1.5 cm, validating its efficacy for precise material handling.
comment: 9 pages
☆ AdaMorph: Unified Motion Retargeting via Embodiment-Aware Adaptive Transformers
Retargeting human motion to heterogeneous robots is a fundamental challenge in robotics, primarily due to the severe kinematic and dynamic discrepancies between varying embodiments. Existing solutions typically resort to training embodiment-specific models, which scales poorly and fails to exploit shared motion semantics. To address this, we present AdaMorph, a unified neural retargeting framework that enables a single model to adapt human motion to diverse robot morphologies. Our approach treats retargeting as a conditional generation task. We map human motion into a morphology-agnostic latent intent space and utilize a dual-purpose prompting mechanism to condition the generation. Instead of simple input concatenation, we leverage Adaptive Layer Normalization (AdaLN) to dynamically modulate the decoder's feature space based on embodiment constraints. Furthermore, we enforce physical plausibility through a curriculum-based training objective that ensures orientation and trajectory consistency via integration. Experimental results on 12 distinct humanoid robots demonstrate that AdaMorph effectively unifies control across heterogeneous topologies, exhibiting strong zero-shot generalization to unseen complex motions while preserving the dynamic essence of the source behaviors.
☆ Robust maximum hands-off optimal control: existence, maximum principle, and $L^{0}$-$L^1$ equivalence
This work advances the maximum hands-off sparse control framework by developing a robust counterpart for constrained linear systems with parametric uncertainties. The resulting optimal control problem minimizes an $L^{0}$ objective subject to an uncountable, compact family of constraints, and is therefore a nonconvex, nonsmooth robust optimization problem. To address this, we replace the $L^{0}$ objective with its convex $L^{1}$ surrogate and, using a nonsmooth variant of the robust Pontryagin maximum principle, show that the $L^{0}$ and $L^{1}$ formulations have identical sets of optimal solutions -- we call this the robust hands-off principle. Building on this equivalence, we propose an algorithmic framework -- drawing on numerically viable techniques from the semi-infinite robust optimization literature -- to solve the resulting problems. An illustrative example is provided to demonstrate the effectiveness of the approach.
comment: Revised version of a journal submission; comments are welcome
☆ HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization
We present HERE, an active 3D scene reconstruction framework based on neural radiance fields, enabling high-fidelity implicit mapping. Our approach centers around an active learning strategy for camera trajectory generation, driven by accurate identification of unseen regions, which supports efficient data acquisition and precise scene reconstruction. The key to our approach is epistemic uncertainty quantification based on evidential deep learning, which directly captures data insufficiency and exhibits a strong correlation with reconstruction errors. This allows our framework to more reliably identify unexplored or poorly reconstructed regions compared to existing methods, leading to more informed and targeted exploration. Additionally, we design a hierarchical exploration strategy that leverages learned epistemic uncertainty, where local planning extracts target viewpoints from high-uncertainty voxels based on visibility for trajectory generation, and global planning uses uncertainty to guide large-scale coverage for efficient and comprehensive reconstruction. The effectiveness of the proposed method in active 3D reconstruction is demonstrated by achieving higher reconstruction completeness compared to previous approaches on photorealistic simulated scenes across varying scales, while a hardware demonstration further validates its real-world applicability.
comment: Accepted to IEEE RA-L. The first two authors contributed equally
☆ PROTEA: Securing Robot Task Planning and Execution
Robots need task planning methods to generate action sequences for complex tasks. Recent work on adversarial attacks has revealed significant vulnerabilities in existing robot task planners, especially those built on foundation models. In this paper, we aim to address these security challenges by introducing PROTEA, an LLM-as-a-Judge defense mechanism, to evaluate the security of task plans. PROTEA is developed to address the dimensionality and history challenges in plan safety assessment. We used different LLMs to implement multiple versions of PROTEA for comparison purposes. For systemic evaluations, we created a dataset containing both benign and malicious task plans, where the harmful behaviors were injected at varying levels of stealthiness. Our results provide actionable insights for robotic system practitioners seeking to enhance robustness and security of their task planning systems. Details, dataset and demos are provided: https://protea-secure.github.io/PROTEA/
☆ TranSC: Hardware-Aware Design of Transcendental Functions Using Stochastic Logic
The hardware-friendly implementation of transcendental functions remains a longstanding challenge in design automation. These functions, which cannot be expressed as finite combinations of algebraic operations, pose significant complexity in digital circuit design. This study introduces a novel approach, TranSC, that utilizes stochastic computing (SC) for lightweight yet accurate implementation of transcendental functions. Building on established SC techniques, our method explores alternative random sources-specifically, quasi-random Van der Corput low-discrepancy (LD) sequences-instead of conventional pseudo-randomness. This shift enhances both the accuracy and efficiency of SC-based computations. We validate our approach through extensive experiments on various function types, including trigonometric, hyperbolic, and activation functions. The proposed design approach significantly reduces MSE by up to 98% compared to the state-of-the-art solutions while reducing hardware area, power consumption, and energy usage by 33%, 72%, and 64%, respectively.
comment: 12 pages
☆ The embodied brain: Bridging the brain, body, and behavior with neuromechanical digital twins
Animal behavior reflects interactions between the nervous system, body, and environment. Therefore, biomechanics and environmental context must be considered to dissect algorithms for behavioral control. This is enabled by leveraging neuromechanical digital twins: computational models that embed artificial neural controllers within realistic body models in simulated environments. Here we review advances in the creation and use of neuromechanical digital twins while also highlighting emerging opportunities for the future. First, we illustrate how neuromechanical models allow researchers to infer hidden biophysical variables that may be difficult to measure experimentally. Additionally, by perturbing these models, one can generate new experimentally testable hypotheses. Next, we explore how neuromechanical twins have been used to foster a deeper exchange between neuroscience, robotics, and machine learning. Finally, we show how neuromechanical twins can advance healthcare. We envision that coupling studies on animals with active probing of their neuromechanical twins will greatly accelerate neuroscientific discovery.
comment: 17 pages, 4 figures (including 1 graphical abstract), 1 table
☆ μDopplerTag: CNN-Based Drone Recognition via Cooperative Micro-Doppler Tagging
The rapid deployment of drones poses significant challenges for airspace management, security, and surveillance. Current detection and classification technologies, including cameras, LiDAR, and conventional radar systems, often struggle to reliably identify and differentiate drones, especially those of similar models, under diverse environmental conditions and at extended ranges. Moreover, low radar cross sections and clutter further complicate accurate drone identification. To address these limitations, we propose a novel drone classification method based on artificial micro-Doppler signatures encoded by resonant electromagnetic stickers attached to drone blades. These tags generate distinctive, configuration-specific radar returns, enabling robust identification. We develop a tailored convolutional neural network (CNN) capable of processing raw radar signals, achieving high classification accuracy. Extensive experiments were conducted both in anechoic chambers with 43 tag configurations and outdoors under realistic flight trajectories and noise conditions. Dimensionality reduction techniques, including Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP), provided insight into code separability and robustness. Our results demonstrate reliable drone classification performance at signal-to-noise ratios as low as 7 dB, indicating the feasibility of long-range detection with advanced surveillance radar systems. Preliminary range estimations indicate potential operational distances of several kilometers, suitable for critical applications such as airport airspace monitoring. The integration of electromagnetic tagging with machine learning enables scalable and efficient drone identification, paving the way for enhanced aerial traffic management and security in increasingly congested airspaces.
☆ Fiducial Exoskeletons: Image-Centric Robot State Estimation
We introduce Fiducial Exoskeletons, an image-based reformulation of 3D robot state estimation that replaces cumbersome procedures and motor-centric pipelines with single-image inference. Traditional approaches - especially robot-camera extrinsic estimation - often rely on high-precision actuators and require time-consuming routines such as hand-eye calibration. In contrast, modern learning-based robot control is increasingly trained and deployed from RGB observations on lower-cost hardware. Our key insight is twofold. First, we cast robot state estimation as 6D pose estimation of each link from a single RGB image: the robot-camera base transform is obtained directly as the estimated base-link pose, and the joint state is recovered via a lightweight global optimization that enforces kinematic consistency with the observed link poses (optionally warm-started with encoder readings). Second, we make per-link 6D pose estimation robust and simple - even without learning - by introducing the fiducial exoskeleton: a lightweight 3D-printed mount with a fiducial marker on each link and known marker-link geometry. This design yields robust camera-robot extrinsics, per-link SE(3) poses, and joint-angle state from a single image, enabling robust state estimation even on unplugged robots. Demonstrated on a low-cost robot arm, fiducial exoskeletons substantially simplify setup while improving calibration, state accuracy, and downstream 3D control performance. We release code and printable hardware designs to enable further algorithm-hardware co-design.
☆ Contact-aware Path Planning for Autonomous Neuroendovascular Navigation IROS
We propose a deterministic and time-efficient contact-aware path planner for neurovascular navigation. The algorithm leverages information from pre- and intra-operative images of the vessels to navigate pre-bent passive tools, by intelligently predicting and exploiting interactions with the anatomy. A kinematic model is derived and employed by the sampling-based planner for tree expansion that utilizes simplified motion primitives. This approach enables fast computation of the feasible path, with negligible loss in accuracy, as demonstrated in diverse and representative anatomies of the vessels. In these anatomical demonstrators, the algorithm shows a 100% convergence rate within 22.8s in the worst case, with sub-millimeter tracking errors (less than 0.64 mm), and is found effective on anatomical phantoms representative of around 94% of patients.
comment: 8 pages, 7 figures, IROS(R-AL)
♻ ☆ ManiFeel: Benchmarking and Understanding Visuotactile Manipulation Policy Learning
Supervised visuomotor policies have shown strong performance in robotic manipulation but often struggle in tasks with limited visual inputs, such as operations in confined spaces and dimly lit environments, or tasks requiring precise perception of object properties and environmental interactions. In such cases, tactile feedback becomes essential for manipulation. While the rapid progress of supervised visuomotor policies has benefited greatly from high-quality, reproducible simulation benchmarks in visual imitation, the visuotactile domain still lacks a similarly comprehensive and reliable benchmark for large-scale and rigorous evaluation. To address this, we introduce ManiFeel, a reproducible and scalable simulation benchmark designed to systematically study supervised visuotactile policy learning. ManiFeel offers a diverse suite of contact-rich and visually challenging manipulation tasks, a modular evaluation pipeline spanning sensing modalities, tactile representations, and policy architectures, as well as real-world validation. Through extensive experiments, ManiFeel demonstrates how tactile sensing enhances policy performance across diverse manipulation scenarios, ranging from precise contact-driven operations to visually constrained settings. In addition, the results reveal task-dependent strengths of different tactile modalities and identify key design principles and open challenges for robust visuotactile policy learning. Real-world evaluations further confirm that ManiFeel provides a reliable and meaningful foundation for benchmarking and future visuotactile policy development. To foster reproducibility and future research, we will release our codebase, datasets, training logs, and pretrained checkpoints, aiming to accelerate progress toward generalizable visuotactile policy learning and manipulation.
♻ ☆ SegDAC: Improving Visual Reinforcement Learning by Extracting Dynamic Object-Centric Representations from Pretrained Vision Models
Visual reinforcement learning (RL) is challenging due to the need to extract useful representations from high-dimensional inputs while learning effective control from sparse and noisy rewards. Although large perception models exist, integrating them effectively into RL for visual generalization and improved sample efficiency remains difficult. We propose SegDAC, a Segmentation-Driven Actor-Critic method. SegDAC uses Segment Anything (SAM) for object-centric decomposition and YOLO-World to ground the image segmentation process via text inputs. It includes a novel transformer-based architecture that supports a dynamic number of segments at each time step and effectively learns which segments to focus on using online RL, without using human labels. By evaluating SegDAC over a challenging visual generalization benchmark using Maniskill3, which covers diverse manipulation tasks under strong visual perturbations, we demonstrate that SegDAC achieves significantly better visual generalization, doubling prior performance on the hardest setting and matching or surpassing prior methods in sample efficiency across all evaluated tasks. Project Page: https://segdac.github.io/
♻ ☆ Surface-Based Manipulation with Modular Foldable Robots
Intelligence lies not only in the brain (decision-making processes) but in the body (physical morphology). The morphology of robots can significantly influence how they interact with the physical world, crucial for manipulating objects in real-life scenarios. Conventional robotic manipulation strategies mainly rely on finger-shaped end effectors. However, achieving stable grasps on fragile, deformable, irregularly shaped, or slippery objects is challenging due to difficulty in establishing stable forces or geometric constraints. Here, we present surface-based manipulation strategies that diverge from classical grasping approaches, using flat surfaces as minimalist end-effectors. By adjusting surfaces' position and orientation, objects can be translated, rotated, and flipped across the surface using closed-loop control strategies. Since this method does not rely on stable grasping, it can adapt to objects of various shapes, sizes, and stiffness levels and can even manipulate the shape of deformable objects. Our results provide a new perspective for solving complex manipulation problems.
comment: This manuscript has been published in npj Robotics. Supplementary video: https://www.youtube.com/watch?v=2TPTBqp84BY
♻ ☆ Multi-User Personalisation in Human-Robot Interaction: Resolving Preference Conflicts Using Gradual Argumentation
While personalisation in Human-Robot Interaction (HRI) has advanced significantly, most existing approaches focus on single-user adaptation, overlooking scenarios involving multiple stakeholders with potentially conflicting preferences. To address this, we propose the Multi-User Preferences Quantitative Bipolar Argumentation Framework (MUP-QBAF), a novel multi-user personalisation framework based on Quantitative Bipolar Argumentation Frameworks (QBAFs) that explicitly models and resolves multi-user preference conflicts. Unlike prior work in Argumentation Frameworks, which typically assumes static inputs, our approach is tailored to robotics: it incorporates both users' arguments and the robot's dynamic observations of the environment, allowing the system to adapt over time and respond to changing contexts. Preferences, both positive and negative, are represented as arguments whose strength is recalculated iteratively based on new information. The framework's properties and capabilities are presented and validated through a realistic case study, where an assistive robot mediates between the conflicting preferences of a caregiver and a care recipient during a frailty assessment task. This evaluation further includes a sensitivity analysis of argument base scores, demonstrating how preference outcomes can be shaped by user input and contextual observations. By offering a transparent, structured, and context-sensitive approach to resolving competing user preferences, this work advances the field of multi-user HRI. It provides a principled alternative to data-driven methods, enabling robots to navigate conflicts in real-world environments.
comment: Preprint submitted to a journal
♻ ☆ Proprioception Enhances Vision Language Model in Generating Captions and Subtask Segmentations for Robot Task
From the perspective of future developments in robotics, it is crucial to verify whether foundation models trained exclusively on offline data, such as images and language, can understand the robot motion. In particular, since Vision Language Models (VLMs) do not include low-level motion information from robots in their training datasets, video understanding including trajectory information remains a significant challenge. In this study, we assess two capabilities of VLMs through a video captioning task with low-level robot motion information: (1) automatic captioning of robot tasks and (2) segmentation of a series of tasks. Both capabilities are expected to enhance the efficiency of robot imitation learning by linking language and motion and serve as a measure of the foundation model's performance. The proposed method generates multiple "scene" captions using image captions and trajectory data from robot tasks. The full task caption is then generated by summarizing these individual captions. Additionally, the method performs subtask segmentation by comparing the similarity between text embeddings of image captions. In both captioning tasks, the proposed method aims to improve performance by providing the robot's motion data - joint and end-effector states - as input to the VLM. Simulator experiments were conducted to validate the effectiveness of the proposed method.
♻ ☆ From Human Bias to Robot Choice: How Occupational Contexts and Racial Priming Shape Robot Selection
As artificial agents increasingly integrate into professional environments, fundamental questions have emerged about how societal biases influence human-robot selection decisions. We conducted two comprehensive experiments (N = 1,038) examining how occupational contexts and stereotype activation shape robotic agent choices across construction, healthcare, educational, and athletic domains. Participants made selections from artificial agents that varied systematically in skin tone and anthropomorphic characteristics. Our study revealed distinct context-dependent patterns. Healthcare and educational scenarios demonstrated strong favoritism toward lighter-skinned artificial agents, while construction and athletic contexts showed greater acceptance of darker-toned alternatives. Participant race was associated with systematic differences in selection patterns across professional domains. The second experiment demonstrated that exposure to human professionals from specific racial backgrounds systematically shifted later robotic agent preferences in stereotype-consistent directions. These findings show that occupational biases and color-based discrimination transfer directly from human-human to human-robot evaluation contexts. The results highlight mechanisms through which robotic deployment may unintentionally perpetuate existing social inequalities.
comment: HRI '26
♻ ☆ Modern Middlewares for Automated Vehicles: A Tutorial
This paper offers a tutorial on current middlewares in automated vehicles. Our aim is to provide the reader with an overview of current middlewares and to identify open challenges in this field. We start by explaining the fundamentals of software architecture in distributed systems and the distinguishing requirements of Automated Vehicles. We then distinguish between communication middlewares and architecture platforms and highlight their key principles and differences. Next, we present five state-of-the-art middlewares as well as their capabilities and functions. We explore how these middlewares could be applied in the design of future vehicle software and their role in the automotive domain. Finally, we compare the five middlewares presented and discuss open research challenges.
comment: This work has been submitted and accepted to the IEEE for possible publication
♻ ☆ LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation models. To address this limitation, we propose LOST-3DSG, a lightweight open-vocabulary 3D scene graph designed to track dynamic objects in real-world environments. Our method adopts a semantic approach to entity tracking based on word2vec and sentence embeddings, enabling an open-vocabulary representation while avoiding the necessity of storing dense CLIP visual features. As a result, LOST-3DSG achieves superior performance compared to approaches that rely on high-dimensional visual embeddings. We evaluate our method through qualitative and quantitative experiments conducted in a real 3D environment using a TIAGo robot. The results demonstrate the effectiveness and efficiency of LOST-3DSG in dynamic object tracking. Code and supplementary material are publicly available on the project website at https://lab-rococo-sapienza.github.io/lost-3dsg/.
♻ ☆ Autonomous Driving in Unstructured Environments: How Far Have We Come?
Research on autonomous driving in unstructured outdoor environments is less advanced than in structured urban settings due to challenges like environmental diversities and scene complexity. These environments-such as rural areas and rugged terrains-pose unique obstacles that are not common in structured urban areas. Despite these difficulties, autonomous driving in unstructured outdoor environments is crucial for applications in agriculture, mining, and military operations. Our survey reviews over 250 papers for autonomous driving in unstructured outdoor environments, covering offline mapping, pose estimation, environmental perception, path planning, end-to-end autonomous driving, datasets, and relevant challenges. We also discuss emerging trends and future research directions. This review aims to consolidate knowledge and encourage further research for autonomous driving in unstructured environments. To support ongoing work, we maintain an active repository with up-to-date literature and open-source projects at: https://github.com/chaytonmin/Survey-Autonomous-Driving-in-Unstructured-Environments.
comment: Accepted by Journal of Field Robotics (JFR) 2025; Survey paper; 59 pages
♻ ☆ AgriLiRa4D: A Multi-Sensor UAV Dataset for Robust SLAM in Challenging Agricultural Fields
Multi-sensor Simultaneous Localization and Mapping (SLAM) is essential for Unmanned Aerial Vehicles (UAVs) performing agricultural tasks such as spraying, surveying, and inspection. However, real-world, multi-modal agricultural UAV datasets that enable research on robust operation remain scarce. To address this gap, we present AgriLiRa4D, a multi-modal UAV dataset designed for challenging outdoor agricultural environments. AgriLiRa4D spans three representative farmland types-flat, hilly, and terraced-and includes both boundary and coverage operation modes, resulting in six flight sequence groups. The dataset provides high-accuracy ground-truth trajectories from a Fiber Optic Inertial Navigation System with Real-Time Kinematic capability (FINS_RTK), along with synchronized measurements from a 3D LiDAR, a 4D Radar, and an Inertial Measurement Unit (IMU), accompanied by complete intrinsic and extrinsic calibrations. Leveraging its comprehensive sensor suite and diverse real-world scenarios, AgriLiRa4D supports diverse SLAM and localization studies and enables rigorous robustness evaluation against low-texture crops, repetitive patterns, dynamic vegetation, and other challenges of real agricultural environments. To further demonstrate its utility, we benchmark four state-of-the-art multi-sensor SLAM algorithms across different sensor combinations, highlighting the difficulty of the proposed sequences and the necessity of multi-modal approaches for reliable UAV localization. By filling a critical gap in agricultural SLAM datasets, AgriLiRa4D provides a valuable benchmark for the research community and contributes to advancing autonomous navigation technologies for agricultural UAVs. The dataset can be downloaded from: https://zhan994.github.io/AgriLiRa4D.
♻ ☆ Aerial Robots Persistent Monitoring and Target Detection: Deployment and Assessment in the Field
In this article, we present a distributed algorithm for multi-robot persistent monitoring and target detection. In particular, we propose a novel solution that effectively integrates the Time-inverted Kuramoto model, three-dimensional Lissajous curves, and Model Predictive Control. We focus on the implementation of this algorithm on aerial robots, addressing the practical challenges involved in deploying our approach under real-world conditions. Our method ensures an effective and robust solution that maintains operational efficiency even in the presence of what we define as type I and type II failures. Type I failures refer to short-time disruptions, such as tracking errors and communication delays, while type II failures account for long-time disruptions, including malicious attacks, severe communication failures, and battery depletion. Our approach guarantees persistent monitoring and target detection despite these challenges. Furthermore, we validate our method with extensive field experiments involving up to eleven aerial robots, demonstrating the effectiveness, resilience, and scalability of our solution.
♻ ☆ A Vision-Language-Action Model with Visual Prompt for OFF-Road Autonomous Driving
Efficient trajectory planning in off-road terrains presents a formidable challenge for autonomous vehicles, often necessitating complex multi-step pipelines. However, traditional approaches exhibit limited adaptability in dynamic environments. To address these limitations, this paper proposes OFF-EMMA, a novel end-to-end multimodal framework designed to overcome the deficiencies of insufficient spatial perception and unstable reasoning in visual-language-action (VLA) models for off-road autonomous driving scenarios. The framework explicitly annotates input images through the design of a visual prompt block and introduces a chain-of-thought with self-consistency (COT-SC) reasoning strategy to enhance the accuracy and robustness of trajectory planning. The visual prompt block utilizes semantic segmentation masks as visual prompts, enhancing the spatial understanding ability of pre-trained visual-language models for complex terrains. The COT- SC strategy effectively mitigates the error impact of outliers on planning performance through a multi-path reasoning mechanism. Experimental results on the RELLIS-3D off-road dataset demonstrate that OFF-EMMA significantly outperforms existing methods, reducing the average L2 error of the Qwen backbone model by 13.3% and decreasing the failure rate from 16.52% to 6.56%.
♻ ☆ Navigation Around Unknown Space Objects Using Visible-Thermal Image Fusion SC
As the popularity of on-orbit operations grows, so does the need for precise navigation around unknown resident space objects (RSOs) such as other spacecraft, orbital debris, and asteroids. The use of Simultaneous Localization and Mapping (SLAM) algorithms is often studied as a method to map out the surface of an RSO and find the inspector's relative pose using a lidar or conventional camera. However, conventional cameras struggle during eclipse or shadowed periods, and lidar, though robust to lighting conditions, tends to be heavier, bulkier, and more power-intensive. Thermal-infrared cameras can track the target RSO throughout difficult illumination conditions without these limitations. While useful, thermal-infrared imagery lacks the resolution and feature-richness of visible cameras. In this work, images of a target satellite in low Earth orbit are photo-realistically simulated in both visible and thermal-infrared bands. Pixel-level fusion methods are used to create visible/thermal-infrared composites that leverage the best aspects of each camera. Navigation errors from a monocular SLAM algorithm are compared between visible, thermal-infrared, and fused imagery in various lighting and trajectories. Fused imagery yields substantially improved navigation performance over visible-only and thermal-only methods.
comment: 18 pages, 11 figures. To be published in proceedings of AIAA SCITECH 2026 Forum
♻ ☆ Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions NeurIPS 2025
Establishing stability certificates for closed-loop systems under reinforcement learning (RL) policies is essential to move beyond empirical performance and offer guarantees of system behavior. Classical Lyapunov methods require a strict stepwise decrease in the Lyapunov function but such certificates are difficult to construct for learned policies. The RL value function is a natural candidate but it is not well understood how it can be adapted for this purpose. To gain intuition, we first study the linear quadratic regulator (LQR) problem and make two key observations. First, a Lyapunov function can be obtained from the value function of an LQR policy by augmenting it with a residual term related to the system dynamics and stage cost. Second, the classical Lyapunov decrease requirement can be relaxed to a generalized Lyapunov condition requiring only decrease on average over multiple time steps. Using this intuition, we consider the nonlinear setting and formulate an approach to learn generalized Lyapunov functions by augmenting RL value functions with neural network residual terms. Our approach successfully certifies the stability of RL policies trained on Gymnasium and DeepMind Control benchmarks. We also extend our method to jointly train neural controllers and stability certificates using a multi-step Lyapunov loss, resulting in larger certified inner approximations of the region of attraction compared to the classical Lyapunov approach. Overall, our formulation enables stability certification for a broad class of systems with learned policies by making certificates easier to construct, thereby bridging classical control theory and modern learning-based methods.
comment: NeurIPS 2025
♻ ☆ Explicit World Models for Reliable Human-Robot Collaboration AAAI-26
This paper addresses the topic of robustness under sensing noise, ambiguous instructions, and human-robot interaction. We take a radically different tack to the issue of reliable embodied AI: instead of focusing on formal verification methods aimed at achieving model predictability and robustness, we emphasise the dynamic, ambiguous and subjective nature of human-robot interactions that requires embodied AI systems to perceive, interpret, and respond to human intentions in a manner that is consistent, comprehensible and aligned with human expectations. We argue that when embodied agents operate in human environments that are inherently social, multimodal, and fluid, reliability is contextually determined and only has meaning in relation to the goals and expectations of humans involved in the interaction. This calls for a fundamentally different approach to achieving reliable embodied AI that is centred on building and updating an accessible "explicit world model" representing the common ground between human and AI, that is used to align robot behaviours with human expectations.
comment: Accepted to AAAI-26 Bridge Program B10: Making Embodied AI Reliable with Testing and Formal Verification
♻ ☆ Modeling and Control for UAV with Off-center Slung Load
Unmanned aerial vehicle (UAV) with slung load system is a classic air transportation system. In practical applications, the suspension point of the slung load does not always align with the center of mass (CoM) of the UAV due to mission requirements or mechanical interference. This offset creates coupling in the system's nonlinear dynamics which leads to a complicated motion control problem. In existing research, modeling of the system are performed about the UAV's CoM. In this work we use the point of suspension instead. Based on the new model, a cascade control strategy is developed. In the middle-loop controller, the acceleration of the suspension point is used to regulate the swing angle of the slung load without the need for considering the coupling between the slung load and the UAV. An inner-loop controller is designed to track the UAV's attitude without the need of simplification on the coupling effects. We prove local exponential stability of the closed-loop using Lyapunov approach. Finally, simulations and experiments are conducted to validate the proposed control system.
♻ ☆ UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles
Safe large-scale coordination of multiple cooperative connected autonomous vehicles (CAVs) hinges on communication that is both efficient and interpretable. Existing approaches either rely on transmitting high-bandwidth raw sensor data streams or neglect perception and planning uncertainties inherent in shared data, resulting in systems that are neither scalable nor safe. To address these limitations, we propose Uncertainty-Guided Natural Language Cooperative Autonomous Planning (UNCAP), a vision-language model-based planning approach that enables CAVs to communicate via lightweight natural language messages while explicitly accounting for perception uncertainty in decision-making. UNCAP features a two-stage communication protocol: (i) an ego CAV first identifies the subset of vehicles most relevant for information exchange, and (ii) the selected CAVs then transmit messages that quantitatively express their perception uncertainty. By selectively fusing messages that maximize mutual information, this strategy allows the ego vehicle to integrate only the most relevant signals into its decision-making, improving both the scalability and reliability of cooperative planning. Experiments across diverse driving scenarios show a 63% reduction in communication bandwidth with a 31% increase in driving safety score, a 61% reduction in decision uncertainty, and a four-fold increase in collision distance margin during near-miss events. Project website: https://uncap-project.github.io/
♻ ☆ CLAMP: Crowdsourcing a LArge-scale in-the-wild haptic dataset with an open-source device for Multimodal robot Perception
Robust robot manipulation in unstructured environments often requires understanding object properties that extend beyond geometry, such as material or compliance-properties that can be challenging to infer using vision alone. Multimodal haptic sensing provides a promising avenue for inferring such properties, yet progress has been constrained by the lack of large, diverse, and realistic haptic datasets. In this work, we introduce the CLAMP device, a low-cost (<\$200) sensorized reacher-grabber designed to collect large-scale, in-the-wild multimodal haptic data from non-expert users in everyday settings. We deployed 16 CLAMP devices to 41 participants, resulting in the CLAMP dataset, the largest open-source multimodal haptic dataset to date, comprising 12.3 million datapoints across 5357 household objects. Using this dataset, we train a haptic encoder that can infer material and compliance object properties from multimodal haptic data. We leverage this encoder to create the CLAMP model, a visuo-haptic perception model for material recognition that generalizes to novel objects and three robot embodiments with minimal finetuning. We also demonstrate the effectiveness of our model in three real-world robot manipulation tasks: sorting recyclable and non-recyclable waste, retrieving objects from a cluttered bag, and distinguishing overripe from ripe bananas. Our results show that large-scale, in-the-wild haptic data collection can unlock new capabilities for generalizable robot manipulation. Website: https://emprise.cs.cornell.edu/clamp/
♻ ☆ SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation AAAI 2026
Robotic manipulation requires precise spatial understanding to interact with objects in the real world. Point-based methods suffer from sparse sampling, leading to the loss of fine-grained semantics. Image-based methods typically feed RGB and depth into 2D backbones pre-trained on 3D auxiliary tasks, but their entangled semantics and geometry are sensitive to inherent depth noise in real-world that disrupts semantic understanding. Moreover, these methods focus on high-level geometry while overlooking low-level spatial cues essential for precise interaction. We propose SpatialActor, a disentangled framework for robust robotic manipulation that explicitly decouples semantics and geometry. The Semantic-guided Geometric Module adaptively fuses two complementary geometry from noisy depth and semantic-guided expert priors. Also, a Spatial Transformer leverages low-level spatial cues for accurate 2D-3D mapping and enables interaction among spatial features. We evaluate SpatialActor on multiple simulation and real-world scenarios across 50+ tasks. It achieves state-of-the-art performance with 87.4% on RLBench and improves by 13.9% to 19.4% under varying noisy conditions, showing strong robustness. Moreover, it significantly enhances few-shot generalization to new tasks and maintains robustness under various spatial perturbations. Project Page: https://shihao1895.github.io/SpatialActor
comment: AAAI 2026 Oral | Project Page: https://shihao1895.github.io/SpatialActor
Robotics 23
☆ PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify task-relevant interaction cues or track progress within a subtask, leading to critical execution errors such as repeated actions, missed steps, and premature termination. To address these challenges, we introduce PALM, a VLA framework that structures policy learning around interaction-centric affordance reasoning and subtask progress cues. PALM distills complementary affordance representations that capture object relevance, contact geometry, spatial placements, and motion dynamics, and serve as task-relevant anchors for visuomotor control. To further stabilize long-horizon execution, PALM predicts continuous within-subtask progress, enabling seamless subtask transitions. Across extensive simulation and real-world experiments, PALM consistently outperforms baselines, achieving a 91.8% success rate on LIBERO-LONG, a 12.5% improvement in average length on CALVIN ABC->D, and a 2x improvement over real-world baselines across three long-horizon generalization settings.
☆ RSLCPP -- Deterministic Simulations Using ROS 2
Simulation is crucial in real-world robotics, offering safe, scalable, and efficient environments for developing applications, ranging from humanoid robots to autonomous vehicles and drones. While the Robot Operating System (ROS) has been widely adopted as the backbone of these robotic applications in both academia and industry, its asynchronous, multiprocess design complicates reproducibility, especially across varying hardware platforms. Deterministic callback execution cannot be guaranteed when computation times and communication delays vary. This lack of reproducibility complicates scientific benchmarking and continuous integration, where consistent results are essential. To address this, we present a methodology to create deterministic simulations using ROS 2 nodes. Our ROS Simulation Library for C++ (RSLCPP) implements this approach, enabling existing nodes to be combined into a simulation routine that yields reproducible results without requiring any code changes. We demonstrate that our approach yields identical results across various CPUs and architectures when testing both a synthetic benchmark and a real-world robotics system. RSLCPP is open-sourced at https://github.com/TUMFTM/rslcpp.
comment: Submitted to 'IEEE Robotics and Automation Practice' for possible publication
☆ A Sliding Mode Controller Based on Timoshenko Beam Theory Developed for a Tendon-Driven Robotic Wrist
Development of dexterous robotic joints is essential for advancing manipulation capabilities in robotic systems. This paper presents the design and implementation of a tendon-driven robotic wrist joint together with an efficient Sliding Mode Controller (SMC) for precise motion control. The wrist mechanism is modeled using a Timoshenko-based approach to accurately capture its kinematic and dynamic properties, which serve as the foundation for tendon force calculations within the controller. The proposed SMC is designed to deliver fast dynamic response and computational efficiency, enabling accurate trajectory tracking under varying operating conditions. The effectiveness of the controller is validated through comparative analyses with existing controllers for similar wrist mechanisms. The proposed SMC demonstrates superior performance in both simulation and experimental studies. The Root Mean Square Error (RMSE) in simulation is approximately 1.67e-2 radians, while experimental validation yields an error of 0.2 radians. Additionally, the controller achieves a settling time of less than 3 seconds and a steady-state error below 1e-1 radians, consistently observed across both simulation and experimental evaluations. Comparative analyses confirm that the developed SMC surpasses alternative control strategies in motion accuracy, rapid convergence, and steady-state precision. This work establishes a foundation for future exploration of tendon-driven wrist mechanisms and control strategies in robotic applications.
☆ ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .
comment: Project Page: https://li-yuetao.github.io/ObjSplat-page/
☆ Benchmarking Autonomy in Scientific Experiments: A Hierarchical Taxonomy for Autonomous Large-Scale Facilities
The transition from automated data collection to fully autonomous discovery requires a shared vocabulary to benchmark progress. While the automotive industry relies on the SAE J3016 standard, current taxonomies for autonomous science presuppose an owner-operator model that is incompatible with the operational rigidities of Large-Scale User Facilities. Here, we propose the Benchmarking Autonomy in Scientific Experiments (BASE) Scale, a 6-level taxonomy (Levels 0-5) specifically adapted for these unique constraints. Unlike owner-operator models, User Facilities require zero-shot deployment where agents must operate immediately without extensive training periods. We define the specific technical requirements for each tier, identifying the Inference Barrier (Level 3) as the critical latency threshold where decisions shift from scalar feedback to semantic digital twins. Fundamentally, this level extends the decision manifold from spatial exploration to temporal gating, enabling the agent to synchronise acquisition with the onset of transient physical events. By establishing these operational definitions, the BASE Scale provides facility directors, funding bodies, and beamline scientists with a standardised metric to assess risk, define liability, and quantify the intelligence of experimental workflows.
comment: 12 pages, 2 figures, 2 tables
☆ Observability-Enhanced Target Motion Estimation via Bearing-Box: Theory and MAV Applications
Monocular vision-based target motion estimation is a fundamental challenge in numerous applications. This work introduces a novel bearing-box approach that fully leverages modern 3D detection measurements that are widely available nowadays but have not been well explored for motion estimation so far. Unlike existing methods that rely on restrictive assumptions such as isotropic target shape and lateral motion, our bearing-box estimator can estimate both the target's motion and its physical size without these assumptions by exploiting the information buried in a 3D bounding box. When applied to multi-rotor micro aerial vehicles (MAVs), the estimator yields an interesting advantage: it further removes the need for higher-order motion assumptions by exploiting the unique coupling between MAV's acceleration and thrust. This is particularly significant, as higher-order motion assumptions are widely believed to be necessary in state-of-the-art bearing-based estimators. We support our claims with rigorous observability analyses and extensive experimental validation, demonstrating the estimator's superior performance in real-world scenarios.
comment: This paper is accepted by IEEE Transactions on Robotics (20 pages, 11 figures)
☆ Semilinear single-track vehicle models with distributed tyre friction dynamics
This paper introduces a novel family of single-track vehicle models that incorporate a distributed representation of transient tyre dynamics, whilst simultaneously accounting for nonlinear effects induced by friction. The core of the proposed framework is represented by the distributed Friction with Bristle Dynamics (FrBD) model, which unifies and extends classical formulations such as Dahl and LuGre by describing the rolling contact process as a spatially distributed system governed by semilinear partial differential equations (PDEs). This model is systematically integrated into a single-track vehicle framework, where the resulting semilinear ODE-PDE interconnection captures the interaction between lateral vehicle motion and tyre deformation. Two main variants are considered: one with rigid tyre carcass and another with flexible carcass, each admitting a compact state-space representation. Local and global well-posedness properties for the coupled system are established rigorously, highlighting the dissipative and physically consistent properties of the distributed FrBD model. A linearisation procedure is also presented, enabling spectral analysis and transfer function derivation, and potentially facilitating the synthesis of controllers and observers. Numerical simulations demonstrate the model's capability to capture micro-shimmy oscillations and transient lateral responses to advanced steering manoeuvres. The proposed formulation advances the state-of-the-art in vehicle dynamics modelling by providing a physically grounded, mathematically rigorous, and computationally tractable approach to incorporating transient tyre behaviour in lateral vehicle dynamics, when accounting for the effect of limited friction.
comment: 37 pages, 12 figures. Accepted by Nonlinear Dynamics
☆ SPINE Gripper: A Twisted Underactuated Mechanism-based Passive Mode-Transition Gripper
This paper presents a single-actuator passive gripper that achieves both stable grasping and continuous bidirectional in-hand rotation through mechanically encoded power transmission logic. Unlike conventional multifunctional grippers that require multiple actuators, sensors, or control-based switching, the proposed gripper transitions between grasping and rotation solely according to the magnitude of the applied input torque. The key enabler of this behavior is a Twisted Underactuated Mechanism (TUM), which generates non-coplanar motions, namely axial contraction and rotation, from a single rotational input while producing identical contraction regardless of rotation direction. A friction generator mechanically defines torque thresholds that govern passive mode switching, enabling stable grasp establishment before autonomously transitioning to in-hand rotation without sensing or active control. Analytical models describing the kinematics, elastic force generation, and torque transmission of the TUM are derived and experimentally validated. The fabricated gripper is evaluated through quantitative experiments on grasp success, friction-based grasp force regulation, and bidirectional rotation performance. System-level demonstrations, including bolt manipulation, object reorientation, and manipulator-integrated tasks driven solely by wrist torque, confirm reliable grasp to rotate transitions in both rotational directions. These results demonstrate that non-coplanar multifunctional manipulation can be realized through mechanical design alone, establishing mechanically encoded power transmission logic as a robust alternative to actuator and control intensive gripper architectures.
comment: 11 pages, 10 figures. Preprint version of a manuscript submitted to IEEE Transactions on Mechatronics
☆ SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation.
comment: 11 pages, 4 figures, 6 tables
☆ On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular, they are primarily trained via supervised fine-tuning or training-time reinforcement learning, requiring explicit fine-tuning phases, human interventions, or controlled data collection. Consequently, existing methods remain unsuitable for challenging simulated- or physical-world deployments, where robots must respond autonomously and flexibly to evolving environments. To address this limitation, we introduce a Test-Time Reinforcement Learning for VLAs (TT-VLA), a framework that enables on-the-fly policy adaptation during inference. TT-VLA formulates a dense reward mechanism that leverages step-by-step task-progress signals to refine action policies during test time while preserving the SFT/RL-trained priors, making it an effective supplement to current VLA models. Empirical results show that our approach enhances overall adaptability, stability, and task success in dynamic, previously unseen scenarios under simulated and real-world settings. We believe TT-VLA offers a principled step toward self-improving, deployment-ready VLAs.
☆ Robust Evacuation for Multi-Drone Failure in Drone Light Shows AAAI-26
Drone light shows have emerged as a popular form of entertainment in recent years. However, several high-profile incidents involving large-scale drone failures -- where multiple drones simultaneously fall from the sky -- have raised safety and reliability concerns. To ensure robustness, we propose a drone parking algorithm designed specifically for multiple drone failures in drone light shows, aimed at mitigating the risk of cascading collisions by drone evacuation and enabling rapid recovery from failures by leveraging strategically placed hidden drones. Our algorithm integrates a Social LSTM model with attention mechanisms to predict the trajectories of failing drones and compute near-optimal evacuation paths that minimize the likelihood of surviving drones being hit by fallen drones. In the recovery node, our system deploys hidden drones (operating with their LED lights turned off) to replace failed drones so that the drone light show can continue. Our experiments showed that our approach can greatly increase the robustness of a multi-drone system by leveraging deep learning to predict the trajectories of fallen drones.
comment: Accepted to AAAI-26 Bridge Program B10: Making Embodied AI Reliable with Testing and Formal Verification
☆ Residual Cross-Modal Fusion Networks for Audio-Visual Navigation
Audio-visual embodied navigation aims to enable an agent to autonomously localize and reach a sound source in unseen 3D environments by leveraging auditory cues. The key challenge of this task lies in effectively modeling the interaction between heterogeneous features during multimodal fusion, so as to avoid single-modality dominance or information degradation, particularly in cross-domain scenarios. To address this, we propose a Cross-Modal Residual Fusion Network, which introduces bidirectional residual interactions between audio and visual streams to achieve complementary modeling and fine-grained alignment, while maintaining the independence of their representations. Unlike conventional methods that rely on simple concatenation or attention gating, CRFN explicitly models cross-modal interactions via residual connections and incorporates stabilization techniques to improve convergence and robustness. Experiments on the Replica and Matterport3D datasets demonstrate that CRFN significantly outperforms state-of-the-art fusion baselines and achieves stronger cross-domain generalization. Notably, our experiments also reveal that agents exhibit differentiated modality dependence across different datasets. The discovery of this phenomenon provides a new perspective for understanding the cross-modal collaboration mechanism of embodied agents.
comment: Main paper (10 pages). Accepted for publication by the 14th international conference on Computational Visual Media (CVM 2026)
♻ ☆ Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers
Spacecraft rendezvous enables on-orbit servicing, debris removal, and crewed docking, forming the foundation for a scalable space economy. Designing such missions requires rapid exploration of the tradespace between control cost and flight time across multiple candidate targets. However, multi-objective optimization in this setting is challenging, as the underlying constraints are often nonconvex, and mission designers must balance accuracy (e.g., solving the full problem) with efficiency (e.g., convex relaxations), slowing iteration and limiting design agility. To address these challenges, this paper proposes an AI-powered framework that enables agile and generalized rendezvous mission design. Given the orbital information of the target spacecraft, boundary conditions of the servicer, and a range of flight times, a transformer model generates a set of near-Pareto optimal trajectories across varying flight times in a single parallelized inference step, thereby enabling rapid mission trade studies. The model is further extended to accommodate variable flight times and perturbed orbital dynamics, supporting realistic multi-objective trade-offs. Validation on chance-constrained rendezvous problems in Earth orbits with passive safety constraints demonstrates that the model generalizes across both flight times and dynamics, consistently providing high-quality initial guesses that converge to superior solutions in fewer iterations. Moreover, the framework efficiently approximates the Pareto front, achieving runtimes comparable to convex relaxation by exploiting parallelized inference. Together, these results position the proposed framework as a practical surrogate for nonconvex trajectory generation and mark an important step toward AI-driven trajectory design for accelerating preliminary mission planning in real-world rendezvous applications.
comment: 14 pages, 7 figures
♻ ☆ AURA-CVC: Autonomous Ultrasound-guided Robotic Assistance for Central Venous Catheterization
Purpose: Central venous catheterization (CVC) is a critical medical procedure for vascular access, hemodynamic monitoring, and life-saving interventions. Its success remains challenging due to the need for continuous ultrasound-guided visualization of a target vessel and approaching needle, which is further complicated by anatomical variability and operator dependency. Errors in needle placement can lead to life-threatening complications. While robotic systems offer a potential solution, achieving full autonomy remains challenging. In this work, we propose an end-to-end robotic-ultrasound-guided CVC pipeline, from scan initialization to needle insertion. Methods: We introduce a deep-learning model to identify clinically relevant anatomical landmarks from a depth image of the patient's neck, obtained using RGB-D camera, to autonomously define the scanning region and paths. Then, a robot motion planning framework is proposed to scan, segment, reconstruct, and localize vessels (veins and arteries), followed by the identification of the optimal insertion zone. Finally, a needle guidance module plans the insertion under ultrasound guidance with operator's feedback. This pipeline was validated on a high-fidelity commercial phantom across 10 simulated clinical scenarios. Results: The proposed pipeline achieved 10 out of 10 successful needle placements on the first attempt. Vessels were reconstructed with a mean error of 2.15 \textit{mm}, and autonomous needle insertion was performed with an error less than or close to 1 \textit{mm}. Conclusion: To our knowledge, this is the first robotic CVC system demonstrated on a high-fidelity phantom with integrated planning, scanning, and insertion. Experimental results show its potential for clinical translation.
comment: Accepted in International Journal of Computer Assisted Radiology and Surgery (IJCARS) 2026
♻ ☆ SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles ICRA 2024
This paper introduces the first publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, collected over 4 years and consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in ASVs by providing a multi-modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset by training and testing current deep learning-based open-source perception algorithms that have shown success in the autonomous ground vehicle domain. With the training and testing results, we discuss open challenges for existing datasets and methods, identifying future research directions. We expect that our dataset will contribute to the development of future marine autonomy pipelines and marine (field) robotics. This dataset is open source and found at https://seepersea.github.io/.
comment: Topic: Special Issue on ICRA 2024 Workshop on Field Robotics
♻ ☆ MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis
Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems.
comment: IEEE Transactions on Automation Science and Engineering
♻ ☆ Scaffolding Dexterous Manipulation with Vision-Language Models
Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensional control. While reinforcement learning (RL) can alleviate the data bottleneck by generating experience in simulation, it typically relies on carefully designed, task-specific reward functions, which hinder scalability and generalization. Thus, contemporary works in dexterous manipulation have often bootstrapped from reference trajectories. These trajectories specify target hand poses that guide the exploration of RL policies and object poses that enable dense, task-agnostic rewards. However, sourcing suitable trajectories - particularly for dexterous hands - remains a significant challenge. Yet, the precise details in explicit reference trajectories are often unnecessary, as RL ultimately refines the motion. Our key insight is that modern vision-language models (VLMs) already encode the commonsense spatial and semantic knowledge needed to specify tasks and guide exploration effectively. Given a task description (e.g., "open the cabinet") and a visual scene, our method uses an off-the-shelf VLM to first identify task-relevant keypoints (e.g., handles, buttons) and then synthesize 3D trajectories for hand motion and object motion. Subsequently, we train a low-level residual RL policy in simulation to track these coarse trajectories or "scaffolds" with high fidelity. Across a number of simulated tasks involving articulated objects and semantic understanding, we demonstrate that our method is able to learn robust dexterous manipulation policies. Moreover, we showcase that our method transfers to real-world robotic hands without any human demonstrations or handcrafted rewards.
♻ ☆ RoboPanoptes: The All-seeing Robot with Whole-body Dexterity
We present RoboPanoptes, a capable yet practical robot system that achieves whole-body dexterity through whole-body vision. Its whole-body dexterity allows the robot to utilize its entire body surface for manipulation, such as leveraging multiple contact points or navigating constrained spaces. Meanwhile, whole-body vision uses a camera system distributed over the robot's surface to provide comprehensive, multi-perspective visual feedback of its own and the environment's state. At its core, RoboPanoptes uses a whole-body visuomotor policy that learns complex manipulation skills directly from human demonstrations, efficiently aggregating information from the distributed cameras while maintaining resilience to sensor failures. Together, these design aspects unlock new capabilities and tasks, allowing RoboPanoptes to unbox in narrow spaces, sweep multiple or oversized objects, and succeed in multi-step stowing in cluttered environments, outperforming baselines in adaptability and efficiency. Results are best viewed on https://robopanoptes.github.io.
comment: Project website: https://robopanoptes.github.io
♻ ☆ Integrating Symbolic RL Planning into a BDI-based Autonomous UAV Framework: System Integration and SIL Validation
Modern autonomous drone missions increasingly require software frameworks capable of seamlessly integrating structured symbolic planning with adaptive reinforcement learning (RL). Although traditional rule-based architectures offer robust structured reasoning for drone autonomy, their capabilities fall short in dynamically complex operational environments that require adaptive symbolic planning. Symbolic RL (SRL), using the Planning Domain Definition Language (PDDL), explicitly integrates domain-specific knowledge and operational constraints, significantly improving the reliability and safety of unmanned aerial vehicle (UAV) decision making. In this study, we propose the AMAD-SRL framework, an extended and refined version of the Autonomous Mission Agents for Drones (AMAD) cognitive multi-agent architecture, enhanced with symbolic reinforcement learning for dynamic mission planning and execution. We validated our framework in a Software-in-the-Loop (SIL) environment structured identically to an intended Hardware-In-the-Loop Simulation (HILS) platform, ensuring seamless transition to real hardware. Experimental results demonstrate stable integration and interoperability of modules, successful transitions between BDI-driven and symbolic RL-driven planning phases, and consistent mission performance. Specifically, we evaluate a target acquisition scenario in which the UAV plans a surveillance path followed by a dynamic reentry path to secure the target while avoiding threat zones. In this SIL evaluation, mission efficiency improved by approximately 75% over a coverage-based baseline, measured by travel distance reduction. This study establishes a robust foundation for handling complex UAV missions and discusses directions for further enhancement and validation.
comment: This submission has been withdrawn by the authors due to institutional and contractual requirements related to security and export-control review
♻ ☆ DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Models
This paper proposes DiffPF, a differentiable particle filter that leverages diffusion models for state estimation in dynamic systems. Unlike conventional differentiable particle filters, which require importance weighting and typically rely on predefined or low-capacity proposal distributions. DiffPF learns a flexible posterior sampler by conditioning a diffusion model on predicted particles and the current observation. This enables accurate, equally-weighted sampling from complex, high-dimensional, and multimodal filtering distributions. We evaluate DiffPF across a range of scenarios, including both unimodal and highly multimodal distributions, and test it on simulated as well as real-world tasks, where it consistently outperforms existing filtering baselines. In particular, DiffPF achieves an 82.8% improvement in estimation accuracy on a highly multimodal global localization benchmark, and a 26% improvement on the real-world KITTI visual odometry benchmark, compared to state-of-the-art differentiable filters. To the best of our knowledge, DiffPF is the first method to integrate conditional diffusion models into particle filtering, enabling high-quality posterior sampling that produces more informative particles and significantly improves state estimation.
♻ ☆ E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mapping
Semantic mapping aims to construct a 3D semantic representation of the environment, providing essential knowledge for robots operating in complex outdoor settings. While Bayesian Kernel Inference (BKI) addresses discontinuities of map inference from sparse sensor data, existing semantic mapping methods suffer from various sources of uncertainties in challenging outdoor environments. To address these issues, we propose an uncertainty-aware semantic mapping framework that handles multiple sources of uncertainties, which significantly degrade mapping performance. Our method estimates uncertainties in semantic predictions using Evidential Deep Learning and incorporates them into BKI for robust semantic inference. It further aggregates noisy observations into coherent Gaussian representations to mitigate the impact of unreliable points, while employing geometry-aligned kernels that adapt to complex scene structures. These Gaussian primitives effectively fuse local geometric and semantic information, enabling robust, uncertainty-aware mapping in complex outdoor scenarios. Comprehensive evaluation across diverse off-road and urban outdoor environments demonstrates consistent improvements in mapping quality, uncertainty calibration, representational flexibility, and robustness, while maintaining real-time efficiency. Our project website: https://e2-bki.github.io
comment: Accepted to IEEE RA-L. Our project website can be found at https://kjyoung.github.io/Homepage/#/Projects/E2-BKI
♻ ☆ Out-of-Distribution Semantic Occupancy Prediction
3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution (OoD) objects and long-tail distributions, which increases the risk of undetected anomalies and misinterpretations, posing safety hazards. To address these challenges, we introduce Out-of-Distribution Semantic Occupancy Prediction, targeting OoD detection in 3D voxel space. To fill dataset gaps, we propose a Realistic Anomaly Augmentation that injects synthetic anomalies while preserving realistic spatial and occlusion patterns, enabling the creation of two datasets: VAA-KITTI and VAA-KITTI-360. Then, a novel framework that integrates OoD detection into 3D semantic occupancy prediction, OccOoD, is proposed, which uses Cross-Space Semantic Refinement (CSSR) to refine semantic predictions from complementary voxel and BEV representations, improving OoD detection. Experimental results demonstrate that OccOoD achieves state-of-the-art OoD detection with an AuROC of 65.50% and an AuPRCr of 31.83 within a 1.2m region, while maintaining competitive semantic occupancy prediction performance and generalization in real-world urban driving scenes. The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD.
comment: The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD
♻ ☆ MimicKit: A Reinforcement Learning Framework for Motion Imitation and Control
MimicKit is an open-source framework for training motion controllers using motion imitation and reinforcement learning. The codebase provides implementations of commonly-used motion-imitation techniques and RL algorithms. This framework is intended to support research and applications in computer graphics and robotics by providing a unified training framework, along with standardized environment, agent, and data structures. The codebase is designed to be modular and easily configurable, enabling convenient modification and extension to new characters and tasks. The open-source codebase is available at: https://github.com/xbpeng/MimicKit.
Robotics 16
☆ Follow the Signs: Using Textual Cues and LLMs to Guide Efficient Robot Navigation
Autonomous navigation in unfamiliar environments often relies on geometric mapping and planning strategies that overlook rich semantic cues such as signs, room numbers, and textual labels. We propose a novel semantic navigation framework that leverages large language models (LLMs) to infer patterns from partial observations and predict regions where the goal is most likely located. Our method combines local perceptual inputs with frontier-based exploration and periodic LLM queries, which extract symbolic patterns (e.g., room numbering schemes and building layout structures) and update a confidence grid used to guide exploration. This enables robots to move efficiently toward goal locations labeled with textual identifiers (e.g., "room 8") even before direct observation. We demonstrate that this approach enables more efficient navigation in sparse, partially observable grid environments by exploiting symbolic patterns. Experiments across environments modeled after real floor plans show that our approach consistently achieves near-optimal paths and outperforms baselines by over 25% in Success weighted by Path Length.
☆ Robotic Tele-Operation for Upper Aerodigestive Tract Microsurgery: System Design and Validation
Upper aerodigestive tract (UADT) treatments frequently employ transoral laser microsurgery (TLM) for procedures such as the removal of tumors or polyps. In TLM, a laser beam is used to cut target tissue, while forceps are employed to grasp, manipulate, and stabilize tissue within the UADT. Although TLM systems may rely on different technologies and interfaces, forceps manipulation is still predominantly performed manually, introducing limitations in ergonomics, precision, and controllability. This paper proposes a novel robotic system for tissue manipulation in UADT procedures, based on a novel end-effector designed for forceps control. The system is integrated within a teleoperation framework that employs a robotic manipulator with a programmed remote center of motion (RCM), enabling precise and constrained instrument motion while improving surgeon ergonomics. The proposed approach is validated through two experimental studies and a dedicated usability evaluation, demonstrating its effectiveness and suitability for UADT surgical applications.
☆ Object-Centric World Models Meet Monte Carlo Tree Search
In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects. These objects, which can be manipulated and interact with each other, serve as the foundation for our model's understanding of the environment. We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics. Our results highlight that a structured world model operating on object-centric representations can be successfully integrated into a model-based RL algorithm utilizing Monte Carlo Tree Search as a planning module.
☆ UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds
Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define 68%, 90%, and 95% prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-hour indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of 5.9% over a 70 m travel distance and an average Absolute Trajectory Error (ATE) of 1.36 m, while maintaining calibrated prediction bounds.
☆ Model Reconciliation through Explainability and Collaborative Recovery in Assistive Robotics
Whenever humans and robots work together, it is essential that unexpected robot behavior can be explained to the user. Especially in applications such as shared control the user and the robot must share the same model of the objects in the world, and the actions that can be performed on these objects. In this paper, we achieve this with a so-called model reconciliation framework. We leverage a Large Language Model to predict and explain the difference between the robot's and the human's mental models, without the need of a formal mental model of the user. Furthermore, our framework aims to solve the model divergence after the explanation by allowing the human to correct the robot. We provide an implementation in an assistive robotics domain, where we conduct a set of experiments with a real wheelchair-based mobile manipulator and its digital twin.
☆ Visible Light Communication using Led-Based AR Markers for Robot Localization
A method of information transmission using visual markers has been widely studied. In this approach, information or identifiers (IDs) are encoded in the black-and-white pattern of each marker. By analyzing the geometric properties of the marker frame - such as its size, distortion, and coordinates - the relative position and orientation between the camera and the marker can be estimated. Furthermore, by associating the positional information of each marker with its corresponding ID, the position of the camera that takes the image picture can be calculated. In the field of mobile robotics, such markers are commonly utilized for robot localization. As mobile robots become more widely used in everyday environments, such visual markers are expected to be utilized across various contexts. In environments where robots collaborate with humans - such as in cell-based manufacturing systems in factories or in domestic settings with partner robots - it is desirable for such markers to be designed in a manner that appears natural and unobtrusive to humans. In this paper, we propose a method for implementing an ArUco marker in the form of illumination. In the proposed method, LEDs are arranged in accordance with the grid pattern of the marker, and the blinking frequency of each LED is determined based on the corresponding black or white cell. As a result, the illumination appears uniformly bright to the human eye, while the camera can capture variations in the blinking frequency. From these differences, the black-and-white pattern can be reconstructed, enabling the identification of the marker's tag information. We develop a prototype system, and conduct experiments which are conducted to evaluate its performance in terms of recognition accuracy under varying distances and viewing angles with respect to the ArUco marker.
☆ Precision Meets Art: Autonomous Multi-UAV System for Large Scale Mural Drawing
The integration of autonomous unmanned aerial vehicles (UAVs) into large-scale artistic projects has emerged as a new application in robotics. This paper presents the design, deployment, and testing of a novel multi-drone system for automated mural painting in outdoor settings. This technology makes use of new software that coordinates multiple drones simultaneously, utilizing state-machine algorithms for task execution. Key advancements are the complex positioning system that combines 2D localization using a single motion tracking camera with onboard LiDAR for precise positioning, and a novel flight control algorithm, which works differently along the trajectory and normally to it, ensuring smoothness and high precision of the drawings at the same time. A 100 square meters mural was created using the developed multi-drone system, validating the system's efficacy. Compared to single-drone approaches, our multi-UAV solution significantly improves scalability and operational speed while maintaining high stability even in harsh weather conditions. The findings highlight the potential of autonomous robotic swarms in creative applications, paving the way for further advancements in large-scale robotic art.
comment: 6 pages, 9 figures
☆ CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method
Food cutting is a highly practical yet underexplored application at the intersection of vision and robotic manipulation. The task remains challenging because interactions between the knife and deformable materials are highly nonlinear and often entail large deformations, frequent contact, and topological change, which in turn hinder stable and safe large-scale data collection. To address these challenges, we propose a unified framework that couples a vision-language-action (VLA) dataset with a physically realistic cutting simulator built on the material point method (MPM). Our simulator adopts MLS-MPM as its computational core, reducing numerical dissipation and energy drift while preserving rotational and shear responses even under topology-changing cuts. During cutting, forces and stress distributions are estimated from impulse exchanges between particles and the grid, enabling stable tracking of transient contact forces and energy transfer. We also provide a benchmark dataset that integrates diverse cutting trajectories, multi-view visual observations, and fine-grained language instructions, together with force--torque and tool--pose labels to provide physically consistent training signals. These components realize a learning--evaluation loop that respects the core physics of cutting and establishes a safe, reproducible, and scalable foundation for advancing VLA models in deformable object manipulation.
comment: 16 pages; 15 figures; 5 tables
☆ WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes
Point Cloud-based Place Recognition (PCPR) demonstrates considerable potential in applications such as autonomous driving, robot localization and navigation, and map update. In practical applications, point clouds used for place recognition are often acquired from different platforms and LiDARs across varying scene. However, existing PCPR datasets lack diversity in scenes, platforms, and sensors, which limits the effective development of related research. To address this gap, we establish WHU-PCPR, a cross-platform heterogeneous point cloud dataset designed for place recognition. The dataset differentiates itself from existing datasets through its distinctive characteristics: 1) cross-platform heterogeneous point clouds: collected from survey-grade vehicle-mounted Mobile Laser Scanning (MLS) systems and low-cost Portable helmet-mounted Laser Scanning (PLS) systems, each equipped with distinct mechanical and solid-state LiDAR sensors. 2) Complex localization scenes: encompassing real-time and long-term changes in both urban and campus road scenes. 3) Large-scale spatial coverage: featuring 82.3 km of trajectory over a 60-month period and an unrepeated route of approximately 30 km. Based on WHU-PCPR, we conduct extensive evaluation and in-depth analysis of several representative PCPR methods, and provide a concise discussion of key challenges and future research directions. The dataset and benchmark code are available at https://github.com/zouxianghong/WHU-PCPR.
☆ Semantic Enrichment of CAD-Based Industrial Environments via Scene Graphs for Simulation and Reasoning
Utilizing functional elements in an industrial environment, such as displays and interactive valves, provide effective possibilities for robot training. When preparing simulations for robots or applications that involve high-level scene understanding, the simulation environment must be equally detailed. Although CAD files for such environments deliver an exact description of the geometry and visuals, they usually lack semantic, relational and functional information, thus limiting the simulation and training possibilities. A 3D scene graph can organize semantic, spatial and functional information by enriching the environment through a Large Vision-Language Model (LVLM). In this paper we present an offline approach to creating detailed 3D scene graphs from CAD environments. This will serve as a foundation to include the relations of functional and actionable elements, which then can be used for dynamic simulation and reasoning. Key results of this research include both quantitative results of the generated semantic labels as well as qualitative results of the scene graph, especially in hindsight of pipe structures and identified functional relations. All code, results and the environment will be made available at https://cad-scenegraph.github.io
comment: Accepted to IEEE SSRR 2025
♻ ☆ Adaptive Science Operations in Deep Space Missions Using Offline Belief State Planning SP
Deep space missions face extreme communication delays and environmental uncertainty that prevent real-time ground operations. To support autonomous science operations in communication-constrained environments, we present a partially observable Markov decision process (POMDP) framework that adaptively sequences spacecraft science instruments. We integrate a Bayesian network into the POMDP observation space to manage the high-dimensional and uncertain measurements typical of astrobiology missions. This network compactly encodes dependencies among measurements and improves the interpretability and computational tractability of science data. Instrument operation policies are computed offline, allowing resource-aware plans to be generated and thoroughly validated prior to launch. We use the Enceladus Orbilander's proposed Life Detection Suite (LDS) as a case study, demonstrating how Bayesian network structure and reward shaping influence system performance. We compare our method against the mission's baseline Concept of Operations (ConOps), evaluating both misclassification rates and performance in off-nominal sample accumulation scenarios. Our approach reduces sample identification errors by nearly 40%
comment: 7 pages, 4 tables, 5 figures, accepted in IEEE ISPARO 2025 (V2 - grammatical edits, also mispelled conference year)
♻ ☆ First Experimental Demonstration of Natural Hovering Extremum Seeking: A New Paradigm in Flapping Flight Physics
In this letter, we report the first experimental demonstration of the recently emerged new paradigm in flapping flight physics called (Natural Hovering Extremum Seeking (NH-ES)) [doi.org/10.1103/4dm4-kc4g], which theorized that hovering flight physics observed in nature by flapping insects and hummingbirds can be generated via a model-free, real-time, computationally basic, sensory-based feedback mechanism that only needs the built-in natural oscillations of the flapping wing as its propulsive input. We run experiments, including moth-like, light source-seeking, on a flapping-wing body in a total model-free setting that is agnostic to morphological parameters and body/aerodynamic models, and show that the flapping body gains altitude and stabilizes hovering about the light source autonomously needing only sensor measurements of light intensity.
♻ ☆ Cross-Platform Learnable Fuzzy Gain-Scheduled Proportional-Integral-Derivative Controller Tuning via Physics-Constrained Meta-Learning and Reinforcement Learning Adaptation
Motivation and gap: PID-family controllers remain a pragmatic choice for many robotic systems due to their simplicity and interpretability, but tuning stable, high-performing gains is time-consuming and typically non-transferable across robot morphologies, payloads, and deployment conditions. Fuzzy gain scheduling can provide interpretable online adjustment, yet its per-joint scaling and consequent parameters are platform-dependent and difficult to tune systematically. Proposed approach: We propose a hierarchical framework for cross-platform tuning of a learnable fuzzy gain-scheduled PID (LF-PID). The controller uses shared fuzzy membership partitions to preserve common error semantics, while learning per-joint scaling and Takagi-Sugeno consequent parameters that schedule PID gains online. Combined with physics-constrained virtual robot synthesis, meta-learning provides cross-platform initialization from robot physical features, and a lightweight reinforcement learning (RL) stage performs deployment-specific refinement under dynamics mismatch. Starting from three base simulated platforms, we generate 232 physically valid training variants via bounded perturbations of mass (+/-10%), inertia (+/-15%), and friction (+/-20%). Results and insight: We evaluate cross-platform generalization on two distinct systems (a 9-DOF serial manipulator and a 12-DOF quadruped) under multiple disturbance scenarios. The RL adaptation stage improves tracking performance on top of the meta-initialized controller, with up to 80.4% error reduction in challenging high-load joints (12.36 degrees to 2.42 degrees) and 19.2% improvement under parameter uncertainty. We further identify an optimization ceiling effect: online refinement yields substantial gains when the meta-initialized baseline exhibits localized deficiencies, but provides limited improvement when baseline quality is already uniformly strong.
comment: 24 pages,15 tables, 6 figures
♻ ☆ VibES: Induced Vibration for Persistent Event-Based Sensing 3DV
Event cameras are a bio-inspired class of sensors that asynchronously measure per-pixel intensity changes. Under fixed illumination conditions in static or low-motion scenes, rigidly mounted event cameras are unable to generate any events and become unsuitable for most computer vision tasks. To address this limitation, recent work has investigated motion-induced event stimulation, which often requires complex hardware or additional optical components. In contrast, we introduce a lightweight approach to sustain persistent event generation by employing a simple rotating unbalanced mass to induce periodic vibrational motion. This is combined with a motion-compensation pipeline that removes the injected motion and yields clean, motion-corrected events for downstream perception tasks. We develop a hardware prototype to demonstrate our approach and evaluate it on real-world datasets. Our method reliably recovers motion parameters and improves both image reconstruction and edge detection compared to event-based sensing without motion induction.
comment: Accepted to the IEEE International Conference on 3D Vision (3DV), Vancouver, BC, Canada, Mar 20-23, 2026
♻ ☆ What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
In this paper, we provide a comprehensive overview of existing scene representation methods for robotics, covering traditional representations such as point clouds, voxels, signed distance functions (SDF), and scene graphs, as well as more recent neural representations like Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and the emerging Foundation Models. While current SLAM and localization systems predominantly rely on sparse representations like point clouds and voxels, dense scene representations are expected to play a critical role in downstream tasks such as navigation and obstacle avoidance. Moreover, neural representations such as NeRF, 3DGS, and foundation models are well-suited for integrating high-level semantic features and language-based priors, enabling more comprehensive 3D scene understanding and embodied intelligence. In this paper, we categorized the core modules of robotics into five parts (Perception, Mapping, Localization, Navigation, Manipulation). We start by presenting the standard formulation of different scene representation methods and comparing the advantages and disadvantages of scene representation across different modules. This survey is centered around the question: What is the best 3D scene representation for robotics? We then discuss the future development trends of 3D scene representations, with a particular focus on how the 3D Foundation Model could replace current methods as the unified solution for future robotic applications. The remaining challenges in fully realizing this model are also explored. We aim to offer a valuable resource for both newcomers and experienced researchers to explore the future of 3D scene representations and their application in robotics. We have published an open-source project on GitHub and will continue to add new works and technologies to this project.
♻ ☆ Meta-learning enhanced adaptive robot control strategy for automated PCB assembly
The assembly of printed circuit boards (PCBs) is one of the standard processes in chip production, directly contributing to the quality and performance of the chips. In the automated PCB assembly process, machine vision and coordinate localization methods are commonly employed to guide the positioning of assembly units. However, occlusion or poor lighting conditions can affect the effectiveness of machine vision-based methods. Additionally, the assembly of odd-form components requires highly specialized fixtures for assembly unit positioning, leading to high costs and low flexibility, especially for multi-variety and small-batch production. Drawing on these considerations, a vision-free, model-agnostic meta-method for compensating robotic position errors is proposed, which maximizes the probability of accurate robotic positioning through interactive feedback, thereby reducing the dependency on visual feedback and mitigating the impact of occlusions or lighting variations. The proposed method endows the robot with the capability to learn and adapt to various position errors, inspired by the human instinct for grasping under uncertainties. Furthermore, it is a self-adaptive method that can accelerate the robotic positioning process as more examples are incorporated and learned. Empirical studies show that the proposed method can handle a variety of odd-form components without relying on specialized fixtures, while achieving similar assembly efficiency to highly dedicated automation equipment. As of the writing of this paper, the proposed meta-method has already been implemented in a robotic-based assembly line for odd-form electronic components. Since PCB assembly involves various electronic components with different sizes, shapes, and functions, subsequent studies can focus on assembly sequence and assembly route optimization to further enhance assembly efficiency.
comment: Pattern: CN 118960772 A
Robotics 32
☆ Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.
comment: Code and interactive demos at https://goal-force.github.io/
☆ DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation
Capturing fine-grained hand-object interactions is challenging due to severe self-occlusion from closely spaced fingers and the subtlety of in-hand manipulation motions. Existing optical motion capture systems rely on expensive camera setups and extensive manual post-processing, while low-cost vision-based methods often suffer from reduced accuracy and reliability under occlusion. To address these challenges, we present DexterCap, a low-cost optical capture system for dexterous in-hand manipulation. DexterCap uses dense, character-coded marker patches to achieve robust tracking under severe self-occlusion, together with an automated reconstruction pipeline that requires minimal manual effort. With DexterCap, we introduce DexterHand, a dataset of fine-grained hand-object interactions covering diverse manipulation behaviors and objects, from simple primitives to complex articulated objects such as a Rubik's Cube. We release the dataset and code to support future research on dexterous hand-object interaction.
comment: 12 pages, 12 figures
☆ Intelligent Singularity Avoidance in UR10 Robotic Arm Path Planning Using Hybrid Fuzzy Logic and Reinforcement Learning
This paper presents a comprehensive approach to singularity detection and avoidance in UR10 robotic arm path planning through the integration of fuzzy logic safety systems and reinforcement learning algorithms. The proposed system addresses critical challenges in robotic manipulation where singularities can cause loss of control and potential equipment damage. Our hybrid approach combines real-time singularity detection using manipulability measures, condition number analysis, and fuzzy logic decision-making with a stable reinforcement learning framework for adaptive path planning. Experimental results demonstrate a 90% success rate in reaching target positions while maintaining safe distances from singular configurations. The system integrates PyBullet simulation for training data collection and URSim connectivity for real-world deployment.
comment: Published in TANET 2025 (Paper No. T0404)
☆ SceneFoundry: Generating Interactive Infinite 3D Worlds
The ability to automatically generate large-scale, interactive, and physically realistic 3D environments is crucial for advancing robotic learning and embodied intelligence. However, existing generative approaches often fail to capture the functional complexity of real-world interiors, particularly those containing articulated objects with movable parts essential for manipulation and navigation. This paper presents SceneFoundry, a language-guided diffusion framework that generates apartment-scale 3D worlds with functionally articulated furniture and semantically diverse layouts for robotic training. From natural language prompts, an LLM module controls floor layout generation, while diffusion-based posterior sampling efficiently populates the scene with articulated assets from large-scale 3D repositories. To ensure physical usability, SceneFoundry employs differentiable guidance functions to regulate object quantity, prevent articulation collisions, and maintain sufficient walkable space for robotic navigation. Extensive experiments demonstrate that our framework generates structurally valid, semantically coherent, and functionally interactive environments across diverse scene types and conditions, enabling scalable embodied AI research.
comment: 15 pages
☆ Modular Autonomy with Conversational Interaction: An LLM-driven Framework for Decision Making in Autonomous Driving
Recent advancements in Large Language Models (LLMs) offer new opportunities to create natural language interfaces for Autonomous Driving Systems (ADSs), moving beyond rigid inputs. This paper addresses the challenge of mapping the complexity of human language to the structured action space of modular ADS software. We propose a framework that integrates an LLM-based interaction layer with Autoware, a widely used open-source software. This system enables passengers to issue high-level commands, from querying status information to modifying driving behavior. Our methodology is grounded in three key components: a taxonomization of interaction categories, an application-centric Domain Specific Language (DSL) for command translation, and a safety-preserving validation layer. A two-stage LLM architecture ensures high transparency by providing feedback based on the definitive execution status. Evaluation confirms the system's timing efficiency and translation robustness. Simulation successfully validated command execution across all five interaction categories. This work provides a foundation for extensible, DSL-assisted interaction in modular and safety-conscious autonomy stacks.
comment: Submitted to the IEEE Intelligent Vehicles Symposium (IV 2026), Detroit, MI, United States
☆ InsSo3D: Inertial Navigation System and 3D Sonar SLAM for turbid environment inspection
This paper presents InsSo3D, an accurate and efficient method for large-scale 3D Simultaneous Localisation and Mapping (SLAM) using a 3D Sonar and an Inertial Navigation System (INS). Unlike traditional sonar, which produces 2D images containing range and azimuth information but lacks elevation information, 3D Sonar produces a 3D point cloud, which therefore does not suffer from elevation ambiguity. We introduce a robust and modern SLAM framework adapted to the 3D Sonar data using INS as prior, detecting loop closure and performing pose graph optimisation. We evaluated InsSo3D performance inside a test tank with access to ground truth data and in an outdoor flooded quarry. Comparisons to reference trajectories and maps obtained from an underwater motion tracking system and visual Structure From Motion (SFM) demonstrate that InsSo3D efficiently corrects odometry drift. The average trajectory error is below 21cm during a 50-minute-long mission, producing a map of 10m by 20m with a 9cm average reconstruction error, enabling safe inspection of natural or artificial underwater structures even in murky water conditions.
☆ FlyPose: Towards Robust Human Pose Estimation From Aerial Views WACV
Unmanned Aerial Vehicles (UAVs) are increasingly deployed in close proximity to humans for applications such as parcel delivery, traffic monitoring, disaster response and infrastructure inspections. Ensuring safe and reliable operation in these human-populated environments demands accurate perception of human poses and actions from an aerial viewpoint. This perspective challenges existing methods with low resolution, steep viewing angles and (self-)occlusion, especially if the application demands realtime feasibile models. We train and deploy FlyPose, a lightweight top-down human pose estimation pipeline for aerial imagery. Through multi-dataset training, we achieve an average improvement of 6.8 mAP in person detection across the test-sets of Manipal-UAV, VisDrone, HIT-UAV as well as our custom dataset. For 2D human pose estimation we report an improvement of 16.3 mAP on the challenging UAV-Human dataset. FlyPose runs with an inference latency of ~20 milliseconds including preprocessing on a Jetson Orin AGX Developer Kit and is deployed onboard a quadrotor UAV during flight experiments. We also publish FlyPose-104, a small but challenging aerial human pose estimation dataset, that includes manual annotations from difficult aerial perspectives: https://github.com/farooqhassaan/FlyPose.
comment: 11 pages, 9 figures, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026
☆ Motion Compensation for Real Time Ultrasound Scanning in Robotically Assisted Prostate Biopsy Procedures ICRA 2026
Prostate cancer is one of the most common types of cancer in men. Its diagnosis by biopsy requires a high level of expertise and precision from the surgeon, so the results are highly operator-dependent. The aim of this work is to develop a robotic system for assisted ultrasound (US) examination of the prostate, a prebiopsy step that could reduce the dexterity requirements and enable faster, more accurate and more available prostate biopsy. We developed and validated a laboratory setup with a collaborative robotic arm that can autonomously scan a prostate phantom and attached the phantom to a medical robotic arm that mimics the patient's movements. The scanning robot keeps the relative position of the US probe and the prostate constant, ensuring a consistent and robust approach to reconstructing the prostate. To reconstruct the prostate, each slice is segmented to generate a series of prostate contours converted into a 3D point cloud used for biopsy planning. The average scan time of the prostate was 30 s, and the average 3D reconstruction of the prostate took 3 s. We performed four motion scenarios: the phantom was scanned in a stationary state (S), with horizontal motion (H), with vertical motion (V), and with a combination of the two (C). System validation is performed by registering the prostate point cloud reconstructions acquired during different motions (H, V, C) with those obtained in the stationary state. ICP registration with a threshold of 0.8 mm yields mean 83.2\% fitness and 0.35 mm RMSE for S-H registration, 84.1\% fitness and 0.37 mm RMSE for S-V registration and 79.4\% fitness and 0.37 mm RMSE for S-C registration. Due to the elastic and soft material properties of the prostate phantom, the maximum robot tracking error was 3 mm, which can be sufficient for prostate biopsy according to medical literature. The maximum delay in motion compensation was 0.5 s.
comment: Submitted for ICRA 2026
☆ EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium
Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash or coarse correlated equilibria, implicitly assuming perfectly rational agents. However, human drivers exhibit bounded rationality, making approximately optimal decisions under cognitive and perceptual constraints. We propose EvoQRE, a principled framework for modeling safety-critical traffic interactions as general-sum Markov games solved via Quantal Response Equilibrium (QRE) and evolutionary game dynamics. EvoQRE integrates a pre-trained generative world model with entropy-regularized replicator dynamics, capturing stochastic human behavior while maintaining equilibrium structure. We provide rigorous theoretical results, proving that the proposed dynamics converge to Logit-QRE under a two-timescale stochastic approximation with an explicit convergence rate of O(log k / k^{1/3}) under weak monotonicity assumptions. We further extend QRE to continuous action spaces using mixture-based and energy-based policy representations. Experiments on the Waymo Open Motion Dataset and nuPlan benchmark demonstrate that EvoQRE achieves state-of-the-art realism, improved safety metrics, and controllable generation of diverse safety-critical scenarios through interpretable rationality parameters.
comment: 11 pages, 5 figures
☆ Mobile Robot Localization Using a Novel Whisker-Like Sensor
Whisker-like touch sensors offer unique advantages for short-range perception in environments where visual and long-range sensing are unreliable, such as confined, cluttered, or low-visibility settings. This paper presents a framework for estimating contact points and robot localization in a known planar environment using a single whisker sensor. We develop a family of virtual sensor models. Each model maps robot configurations to sensor observations and enables structured reasoning through the concept of preimages - the set of robot states consistent with a given observation. The notion of virtual sensor models serves as an abstraction to reason about state uncertainty without dependence on physical implementation. By combining sensor observations with a motion model, we estimate the contact point. Iterative estimation then enables reconstruction of obstacle boundaries. Furthermore, intersecting states inferred from current observations with forward-projected states from previous steps allow accurate robot localization without relying on vision or external systems. The framework supports both deterministic and possibilistic formulations and is validated through simulation and physical experiments using a low-cost, 3D printed, Hall-effect-based whisker sensor. Results demonstrate accurate contact estimation and localization with errors under 7 mm, demonstrating the potential of whisker-based sensing as a lightweight, adaptable complement to vision-based navigation.
☆ Learning specifications for reactive synthesis with safety constraints
This paper presents a novel approach to learning from demonstration that enables robots to autonomously execute complex tasks in dynamic environments. We model latent tasks as probabilistic formal languages and introduce a tailored reactive synthesis framework that balances robot costs with user task preferences. Our methodology focuses on safety-constrained learning and inferring formal task specifications as Probabilistic Deterministic Finite Automata (PDFA). We adapt existing evidence-driven state merging algorithms and incorporate safety requirements throughout the learning process to ensure that the learned PDFA always complies with safety constraints. Furthermore, we introduce a multi-objective reactive synthesis algorithm that generates deterministic strategies that are guaranteed to satisfy the PDFA task while optimizing the trade-offs between user preferences and robot costs, resulting in a Pareto front of optimal solutions. Our approach models the interaction as a two-player game between the robot and the environment, accounting for dynamic changes. We present a computationally-tractable value iteration algorithm to generate the Pareto front and the corresponding deterministic strategies. Comprehensive experimental results demonstrate the effectiveness of our algorithms across various robots and tasks, showing that the learned PDFA never includes unsafe behaviors and that synthesized strategies consistently achieve the task while meeting both the robot cost and user-preference requirements.
☆ Safety Not Found (404): Hidden Risks of LLM-Based Robotics Decision Making
One mistake by an AI system in a safety-critical setting can cost lives. As Large Language Models (LLMs) become integral to robotics decision-making, the physical dimension of risk grows; a single wrong instruction can directly endanger human safety. This paper addresses the urgent need to systematically evaluate LLM performance in scenarios where even minor errors are catastrophic. Through a qualitative evaluation of a fire evacuation scenario, we identified critical failure cases in LLM-based decision-making. Based on these, we designed seven tasks for quantitative assessment, categorized into: Complete Information, Incomplete Information, and Safety-Oriented Spatial Reasoning (SOSR). Complete information tasks utilize ASCII maps to minimize interpretation ambiguity and isolate spatial reasoning from visual processing. Incomplete information tasks require models to infer missing context, testing for spatial continuity versus hallucinations. SOSR tasks use natural language to evaluate safe decision-making in life-threatening contexts. We benchmark various LLMs and Vision-Language Models (VLMs) across these tasks. Beyond aggregate performance, we analyze the implications of a 1% failure rate, highlighting how "rare" errors escalate into catastrophic outcomes. Results reveal serious vulnerabilities: several models achieved a 0% success rate in ASCII navigation, while in a simulated fire drill, models instructed robots to move toward hazardous areas instead of emergency exits. Our findings lead to a sobering conclusion: current LLMs are not ready for direct deployment in safety-critical systems. A 99% accuracy rate is dangerously misleading in robotics, as it implies one out of every hundred executions could result in catastrophic harm. We demonstrate that even state-of-the-art models cannot guarantee safety, and absolute reliance on them creates unacceptable risks.
☆ TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point Clouds AAAI 2026
Task-oriented dexterous grasping remains challenging in robotic manipulations of open-world objects under severe partial observation, where significant missing data invalidates generic shape completion. In this paper, to overcome this limitation, we study Task-Oriented Shape Completion, a new task that focuses on completing the potential contact regions rather than the entire shape. We argue that shape completion for grasping should be explicitly guided by the downstream manipulation task. To achieve this, we first generate multiple task-oriented shape completion candidates by leveraging the zero-shot capabilities of object functional understanding from several pre-trained foundation models. A 3D discriminative autoencoder is then proposed to evaluate the plausibility of each generated candidate and optimize the most plausible one from a global perspective. A conditional flow-matching model named FlowGrasp is developed to generate task-oriented dexterous grasps from the optimized shape. Our method achieves state-of-the-art performance in task-oriented dexterous grasping and task-oriented shape completion, improving the Grasp Displacement and the Chamfer Distance over the state-of-the-art by 16.17\% and 55.26%, respectively. In particular, it shows good capabilities in grasping objects with severe missing data. It also demonstrates good generality in handling open-set categories and tasks.
comment: Accepted to AAAI 2026
☆ Assembling Solar Panels by Dual Robot Arms Towards Full Autonomous Lunar Base Construction
Since the successful Apollo program, humanity is once again aiming to return to the Moon for scientific discovery, resource mining, and inhabitation. Upcoming decades focus on building a lunar outpost, with robotic systems playing a crucial role to safely and efficiently establish essential infrastructure such as solar power generating towers. Similar to the construction of the International Space Station (ISS), shipping necessary components via modules and assembling them in situ should be a practical scenario. In this context, this paper focuses on the integration of vision, control, and hardware systems within an autonomous sequence for a dual-arm robot system. We explore a perception and control pipeline specifically designed for assembling solar panel modules, one of the benchmark tasks. Ad hoc hardware was designed and tested in real-world experiments. A mock-up of modular solar panels and active-passive connectors are employed, with the control of this grappling fixture integrated into the proposed pipeline. The successful implementation of our method demonstrates that the two robot manipulators can effectively connect arbitrarily placed panels, highlighting the seamless integration of vision, control, and hardware systems in complex space applications.
comment: This is the authors' version of a paper accepted for publication in IEEE/SICE International Symposium on System Integration (SII), 2025, (c) IEEE
☆ BlazeAIoT: A Modular Multi-Layer Platform for Real-Time Distributed Robotics Across Edge, Fog, and Cloud Infrastructures
The increasing complexity of distributed robotics has driven the need for platforms that seamlessly integrate edge, fog, and cloud computing layers while meeting strict real-time constraints. This paper introduces BlazeAIoT, a modular multi-layer platform designed to unify distributed robotics across heterogeneous infrastructures. BlazeAIoT provides dynamic data transfer, configurable services, and integrated monitoring, while ensuring resilience, security, and programming language flexibility. The architecture leverages Kubernetes-based clusters, broker interoperability (DDS, Kafka, Redis, and ROS2), and adaptive data distribution mechanisms to optimize communication and computation across diverse environments. The proposed solution includes a multi-layer configuration service, dynamic and adaptive data bridging, and hierarchical rate limiting to handle large messages. The platform is validated through robotics scenarios involving navigation and artificial intelligence-driven large-scale message processing, demonstrating robust performance under real-time constraints. Results highlight BlazeAIoT's ability to dynamically allocate services across incomplete topologies, maintain system health, and minimize latency, making it a cost-aware, scalable solution for robotics and broader IoT applications, such as smart cities and smart factories.
comment: 17 pages, 9 figures
☆ Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds
Bipedal humanoid robots must precisely coordinate balance, timing, and contact decisions when locomoting on constrained footholds such as stepping stones, beams, and planks -- even minor errors can lead to catastrophic failure. Classical optimization and control pipelines handle these constraints well but depend on highly accurate mathematical representations of terrain geometry, making them prone to error when perception is noisy or incomplete. Meanwhile, reinforcement learning has shown strong resilience to disturbances and modeling errors, yet end-to-end policies rarely discover the precise foothold placement and step sequencing required for discontinuous terrain. These contrasting limitations motivate approaches that guide learning with physics-based structure rather than relying purely on reward shaping. In this work, we introduce a locomotion framework in which a reduced-order stepping planner supplies dynamically consistent motion targets that steer the RL training process via Control Lyapunov Function (CLF) rewards. This combination of structured footstep planning and data-driven adaptation produces accurate, agile, and hardware-validated stepping-stone locomotion on a humanoid robot, substantially improving reliability compared to conventional model-free reinforcement-learning baselines.
☆ NAS-GS: Noise-Aware Sonar Gaussian Splatting
Underwater sonar imaging plays a crucial role in various applications, including autonomous navigation in murky water, marine archaeology, and environmental monitoring. However, the unique characteristics of sonar images, such as complex noise patterns and the lack of elevation information, pose significant challenges for 3D reconstruction and novel view synthesis. In this paper, we present NAS-GS, a novel Noise-Aware Sonar Gaussian Splatting framework specifically designed to address these challenges. Our approach introduces a Two-Ways Splatting technique that accurately models the dual directions for intensity accumulation and transmittance calculation inherent in sonar imaging, significantly improving rendering speed without sacrificing quality. Moreover, we propose a Gaussian Mixture Model (GMM) based noise model that captures complex sonar noise patterns, including side-lobes, speckle, and multi-path noise. This model enhances the realism of synthesized images while preventing 3D Gaussian overfitting to noise, thereby improving reconstruction accuracy. We demonstrate state-of-the-art performance on both simulated and real-world large-scale offshore sonar scenarios, achieving superior results in novel view synthesis and 3D reconstruction.
♻ ☆ Low-Latency Event-Based Velocimetry for Quadrotor Control in a Narrow Pipe
Autonomous quadrotor flight in confined spaces such as pipes and tunnels presents significant challenges due to unsteady, self-induced aerodynamic disturbances. Very recent advances have enabled flight in such conditions, but they either rely on constant motion through the pipe to mitigate airflow recirculation effects or suffer from limited stability during hovering. In this work, we present the first closed-loop control system for quadrotors for hovering in narrow pipes that leverages real-time flow field measurements. We develop a low-latency, event-based smoke velocimetry method that estimates local airflow at high temporal resolution. This flow information is used by a disturbance estimator based on a recurrent convolutional neural network, which infers force and torque disturbances in real time. The estimated disturbances are integrated into a learning-based controller trained via reinforcement learning. The flow-feedback control proves particularly effective during lateral translation maneuvers in the pipe cross-section. There, the real-time disturbance information enables the controller to effectively counteract transient aerodynamic effects, thereby preventing collisions with the pipe wall. To the best of our knowledge, this work represents the first demonstration of an aerial robot with closed-loop control informed by real-time flow field measurements. This opens new directions for research on flight in aerodynamically complex environments. In addition, our work also sheds light on the characteristic flow structures that emerge during flight in narrow, circular pipes, providing new insights at the intersection of robotics and fluid dynamics.
comment: 19 pages
♻ ☆ Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation
Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities, but training control policies that can directly deploy on real hardware remains difficult due to contact-rich physics and imperfect actuation. We close this gap with a practical sim-to-real reinforcement learning (RL) framework that utilizes dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective sim-to-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling to bridge the actuation gaps with randomization of non-ideal effects such as backlash, torque-speed saturation. Using an asymmetric actor-critic PPO pipeline trained entirely in simulation, our policies deploy directly to a five-finger hand. The resulting policies demonstrated two essential skills: (1) command-based, controllable grasp force tracking, and (2) reorientation of objects in the hand, both of which were robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with effective sensing/actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.
♻ ☆ iTeach: Interactive Teaching for Robot Perception using Mixed Reality
Robots deployed in the wild often encounter objects and scenes that break pre-trained perception models, yet adapting these models typically requires slow offline data collection, labeling, and retraining. We introduce iTeach, a human-in-the-loop system that enables robots to improve perception continuously as they explore new environments. A human sees the robot's predictions from its own viewpoint, corrects failures in real time, and the informed data drives iterative fine-tuning until performance is satisfactory. A mixed reality headset provides the interface, overlaying predictions in the user's view and enabling lightweight annotation via eye gaze and voice. Instead of tedious frame-by-frame labeling, a human guides the robot to scenes of choice and records short videos while interacting with objects. The human labels only the final frame, and a video segmentation model propagates labels across the sequence, converting seconds of input into dense supervision. The refined model is deployed immediately, closing the loop between human feedback and robot learning. We demonstrate iTeach on Unseen Object Instance Segmentation (UOIS), achieving consistent improvements over a pre-trained MSMFormer baseline on both our collected dataset and the SceneReplica benchmark, where it leads to higher grasping success, followed by a real-world demonstration of grasping unseen objects with a Fetch robot. By combining human judgment, efficient annotation, and on-the-fly refinement, iTeach provides a practical path toward perception systems that generalize robustly in diverse real-world conditions. Project page at https://irvlutd.github.io/iTeach
♻ ☆ Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images
Landslide monitoring is essential for understanding geohazards and mitigating associated risks. Existing point cloud-based methods, however, typically rely on either geometric or radiometric information and often yield sparse or non-3D displacement estimates. In this paper, we propose a hierarchical partitioning-based coarse-to-fine approach that integrates 3D point clouds and co-registered RGB images to estimate dense 3D displacement vector fields. Patch-level matches are constructed using both 3D geometry and 2D image features, refined via geometric consistency checks, and followed by rigid transformation estimation per match. Experimental results on two real-world landslide datasets demonstrate that the proposed method produces 3D displacement estimates with high spatial coverage (79% and 97%) and accuracy. Deviations in displacement magnitude with respect to external measurements (total station or GNSS observations) are 0.15 m and 0.25 m on the two datasets, respectively, and only 0.07 m and 0.20 m compared to manually derived references, all below the mean scan resolutions (0.08 m and 0.30 m). Compared with the state-of-the-art method F2S3, the proposed approach improves spatial coverage while maintaining comparable accuracy. The proposed approach offers a practical and adaptable solution for TLS-based landslide monitoring and is extensible to other types of point clouds and monitoring tasks. The example data and source code are publicly available at https://github.com/gseg-ethz/fusion4landslide.
comment: Published in the International Journal of Applied Earth Observation and Geoinformation. 25 pages, 19 figures
♻ ☆ Anomaly detection for generic failure monitoring in robotic assembly, screwing and manipulation
Out-of-distribution states in robot manipulation often lead to unpredictable robot behavior or task failure, limiting success rates and increasing risk of damage. Anomaly detection (AD) can identify deviations from expected patterns in data, which can be used to trigger failsafe behaviors and recovery strategies. Prior work has applied data-driven AD on time series data for specific robotic tasks, however the transferability of an AD approach between different robot control strategies and task types has not been shown. Leveraging time series data, such as force/torque signals, allows to directly capture robot-environment interactions, crucial for manipulation and online failure detection. Their broad availability, high sampling rates, and low dimensionality enable high temporal resolution and efficient processing. As robotic tasks can have widely signal characteristics and requirements, AD methods which can be applied in the same way to a wide range of tasks is needed, ideally with good data efficiency. We examine three industrial tasks, each presenting several anomalies. Test scenarios in robotic cabling, screwing, and sanding are built, and multi-modal time series data is gathered. Several autoencoder-based methods are compared, and we evaluate the generalization across different tasks and control methods (diffusion policy-, position-, and impedance-controlled). This allows us to validate the integration of AD in complex tasks involving tighter tolerances and variation from both the robot and its environment. Additionally, we evaluate data efficiency, detection latency, and task characteristics which support robust detection. The results indicate reliable detection with AUROC above 0.96 in failures in the cabling and screwing task, such as incorrect or misaligned parts. In the polishing task, only severe failures were reliably detected, while more subtle failures remained undetected.
♻ ☆ Non-Prehensile Tool-Object Manipulation by Integrating LLM-Based Planning and Manoeuvrability-Driven Controls
The ability to wield tools was once considered exclusive to human intelligence, but it's now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert a human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot's tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.
♻ ☆ AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation
Free space ground segmentation is essential to navigate autonomous robots, recognize drivable zones, and traverse efficiently. Fine-grained features remain challenging for existing segmentation models, particularly for robots in indoor and structured environments. These difficulties arise from ineffective multi-scale processing, suboptimal boundary refinement, and limited feature representation. To address this, we propose Attention-Guided Upsampling with Residual Boundary-Assistive Refinement (AURASeg), a ground-plane semantic segmentation framework designed to improve border precision while preserving strong region accuracy. Built on a ResNet-50 backbone, AURASeg introduces (i) a Residual Border Refinement Module (RBRM) that enhances edge delineation through boundary-assistive feature refinement, and (ii) Attention Progressive Upsampling Decoder (APUD) blocks that progressively fuse multi-level features during decoding. Additionally, we integrate a (iii) lightweight ASPPLite module to capture multi-scale context with minimal overhead. Extensive experiments on CARL-D, the Ground Mobile Robot Perception (GMRP) dataset, and a custom Gazebo indoor dataset show that AURASeg consistently outperforms strong baselines, with notable gains in boundary metrics. Finally, we demonstrate real-time deployment on a Kobuki TurtleBot, validating practical usability. The code is available at https://github.com/Narendhiranv04/AURASeg
comment: 6 pages, 4 figures, 4 tables
♻ ☆ GR-Dexter Technical Report
Vision-language-action (VLA) models have enabled language-conditioned, long-horizon robot manipulation, but most existing systems are limited to grippers. Scaling VLA policies to bimanual robots with high degree-of-freedom (DoF) dexterous hands remains challenging due to the expanded action space, frequent hand-object occlusions, and the cost of collecting real-robot data. We present GR-Dexter, a holistic hardware-model-data framework for VLA-based generalist manipulation on a bimanual dexterous-hand robot. Our approach combines the design of a compact 21-DoF robotic hand, an intuitive bimanual teleoperation system for real-robot data collection, and a training recipe that leverages teleoperated robot trajectories together with large-scale vision-language and carefully curated cross-embodiment datasets. Across real-world evaluations spanning long-horizon everyday manipulation and generalizable pick-and-place, GR-Dexter achieves strong in-domain performance and improved robustness to unseen objects and unseen instructions. We hope GR-Dexter serves as a practical step toward generalist dexterous-hand robotic manipulation.
♻ ☆ SLAM&Render: A Benchmark for the Intersection Between Neural Rendering, Gaussian Splatting and SLAM
Models and methods originally developed for Novel View Synthesis and Scene Rendering, such as Neural Radiance Fields (NeRF) and Gaussian Splatting, are increasingly being adopted as representations in Simultaneous Localization and Mapping (SLAM). However, existing datasets fail to include the specific challenges of both fields, such as sequential operations and, in many settings, multi-modality in SLAM or generalization across viewpoints and illumination conditions in neural rendering. Additionally, the data are often collected using sensors which are handheld or mounted on drones or mobile robots, which complicates the accurate reproduction of sensor motions. To bridge these gaps, we introduce SLAM&Render, a novel dataset designed to benchmark methods in the intersection between SLAM, Novel View Rendering and Gaussian Splatting. Recorded with a robot manipulator, it uniquely includes 40 sequences with time-synchronized RGB-D images, IMU readings, robot kinematic data, and ground-truth pose streams. By releasing robot kinematic data, the dataset also enables the assessment of recent integrations of SLAM paradigms within robotic applications. The dataset features five setups with consumer and industrial objects under four controlled lighting conditions, each with separate training and test trajectories. All sequences are static with different levels of object rearrangements and occlusions. Our experimental results, obtained with several baselines from the literature, validate SLAM&Render as a relevant benchmark for this emerging research area.
comment: 9 pages, 8 figures, submitted to The International Journal of Robotics Research (IJRR)
♻ ☆ Hierarchical GNN-Based Multi-Agent Learning for Dynamic Queue-Jump Lane and Emergency Vehicle Corridor Formation
Emergency vehicles require rapid passage through congested traffic, yet existing strategies fail to adapt to dynamic conditions. We propose a novel hierarchical graph neural network (GNN)-based multi-agent reinforcement learning framework to coordinate connected vehicles for emergency corridor formation. Our approach uses a high-level planner for global strategy and low-level controllers for trajectory execution, utilizing graph attention networks to scale with variable agent counts. Trained via Multi-Agent Proximal Policy Optimization (MAPPO), the system reduces emergency vehicle travel time by 28.3% compared to baselines and 44.6% compared to uncoordinated traffic in simulations. The design achieves near-zero collision rates (0.3%) while maintaining 81% of background traffic efficiency. Ablation and generalization studies confirm the framework's robustness across diverse scenarios. These results demonstrate the effectiveness of combining GNNs with hierarchical learning for intelligent transportation systems.
comment: 16 Pages, 5 Figures, 9 Tables, submitted to IEEE TITS
♻ ☆ Volume-Consistent Kneading-Based Deformation Manufacturing for Material-Efficient Shaping
Conventional subtractive manufacturing inevitably involves material loss during geometric realization, while additive manufacturing still suffers from limitations in surface quality, process continuity, and productivity when fabricating complex geometries. To address these challenges, this paper proposes a volume-consistent kneading-based forming method for plastic materials, enabling continuous and controllable three-dimensional deformation under mass conservation. An integrated kneading-based manufacturing system is developed, in which geometry-aware kneading command generation, layer-wise kneading execution, and in-process point-cloud scanning are tightly coupled to form a closed-loop workflow of scanning, forming, and feedback compensation. Target geometries are analyzed through layer-wise point-cloud processing and classified into enveloping and non-enveloping types. Accordingly, an Envelope Shaping First strategy and a Similar Gradient Method are adopted to ensure stable material flow and continuous deformation. An RMSE-based compensation scheme is further introduced to correct systematic geometric deviations induced by elastic rebound and material redistribution. Experimental validation on five representative geometries demonstrates high geometric fidelity, with material utilization consistently exceeding 98%. The results indicate that kneading-based forming provides a promising alternative manufacturing paradigm for low-waste, customizable production.
comment: 39 pages, 31 figures
♻ ☆ On Steerability Factors for Growing Vine Robots
Vine robots extend their tubular bodies by everting material from the tip, enabling navigation in complex environments with a minimalist soft body. Despite their promise for field applications, especially in the urban search and rescue domain, performance is constrained by the weight of attached sensors or tools, as well as other design and control choices. This work investigates how tip load, pressure, length, diameter, and fabrication method shape vine robot steerability--the ability to maneuver with controlled curvature--for robots that steer with series pouch motor-style pneumatic actuators. We conduct two groups of experiments: (1) studying tip load, chamber pressure, length, and diameter in a robot supporting itself against gravity, and (2) studying fabrication method and ratio of actuator to chamber pressure in a robot supported on the ground. Results show that steerability decreases with increasing tip load, is best at moderate chamber pressure, increases with length, and is largely unaffected by diameter. Robots with actuators attached on their exterior begin curving at low pressure ratios, but curvature saturates at high pressure ratios; those with actuators integrated into the robot body require higher pressure ratios to begin curving but achieve higher curvature overall. We demonstrate that robots optimized with these principles outperform those with ad hoc parameters in a mobility task that involves maximizing upward and horizontal curvatures.
♻ ☆ PartDexTOG: Generating Dexterous Task-Oriented Grasping via Language-driven Part Analysis
Task-oriented grasping is a crucial yet challenging task in robotic manipulation. Despite the recent progress, few existing methods address task-oriented grasping with dexterous hands. Dexterous hands provide better precision and versatility, enabling robots to perform task-oriented grasping more effectively. In this paper, we argue that part analysis can enhance dexterous grasping by providing detailed information about the object's functionality. We propose PartDexTOG, a method that generates dexterous task-oriented grasps via language-driven part analysis. Taking a 3D object and a manipulation task represented by language as input, the method first generates the category-level and part-level grasp descriptions w.r.t the manipulation task by LLMs. Then, a category-part conditional diffusion model is developed to generate a dexterous grasp for each part, respectively, based on the generated descriptions. To select the most plausible combination of grasp and corresponding part from the generated ones, we propose a measure of geometric consistency between grasp and part. We show that our method greatly benefits from the open-world knowledge reasoning on object parts by LLMs, which naturally facilitates the learning of grasp generation on objects with different geometry and for different manipulation tasks. Our method ranks top on the OakInk-shape dataset over all previous methods, improving the Penetration Volume, the Grasp Displace, and the P-FID over the state-of-the-art by $3.58\%$, $2.87\%$, and $41.43\%$, respectively. Notably, it demonstrates good generality in handling novel categories and tasks.
♻ ☆ Model-free Adaptive Output Feedback Vibration Suppression in a Cantilever Beam
This paper presents a model-free adaptive control approach to suppress vibrations in a cantilevered beam excited by an unknown disturbance. The cantilevered beam under harmonic excitation is modeled using a lumped parameter approach. Based on retrospective cost optimization, a sampled-data adaptive controller is developed to suppress vibrations caused by external disturbances. Both displacement and acceleration measurements are considered for feedback. Since acceleration measurements are more sensitive to spillover, which excites higher frequency modes, a filter is developed to extract key displacement information from the acceleration data and enhance suppression performance. The vibration suppression performance is compared using both displacement and acceleration measurements.
comment: 16 pages, 14 figures, to be presented at Scitech 2026, uploaded new version that corrects some mistakes in the paper
♻ ☆ A Photorealistic Dataset and Vision-Based Algorithm for Anomaly Detection During Proximity Operations in Lunar Orbit
NASA's forthcoming Lunar Gateway space station, which will be uncrewed most of the time, will need to operate with an unprecedented level of autonomy. One key challenge is enabling the Canadarm3, the Gateway's external robotic system, to detect hazards in its environment using its onboard inspection cameras. This task is complicated by the extreme and variable lighting conditions in space. In this paper, we introduce the visual anomaly detection and localization task for the space domain and establish a benchmark based on a synthetic dataset called ALLO (Anomaly Localization in Lunar Orbit). We show that state-of-the-art visual anomaly detection methods often fail in the space domain, motivating the need for new approaches. To address this, we propose MRAD (Model Reference Anomaly Detection), a statistical algorithm that leverages the known pose of the Canadarm3 and a CAD model of the Gateway to generate reference images of the expected scene appearance. Anomalies are then identified as deviations from this model-generated reference. On the ALLO dataset, MRAD surpasses state-of-the-art anomaly detection algorithms, achieving an AP score of 62.9% at the pixel level and an AUROC score of 75.0% at the image level. Given the low tolerance for risk in space operations and the lack of domain-specific data, we emphasize the need for novel, robust, and accurate anomaly detection methods to handle the challenging visual conditions found in lunar orbit and beyond.
comment: In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE International Conference on Robotics and Automation, 1-5 June 2026, Vienna, Austria
Robotics 39
☆ LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
Vision-Language-Action (VLA) models have recently demonstrated strong generalization capabilities in robotic manipulation. Some existing VLA approaches attempt to improve action accuracy by explicitly generating linguistic reasoning traces or future visual observations before action execution. However, explicit reasoning typically incurs non-negligible inference latency, which constrains the temporal resolution required for robotic manipulation. Moreover, such reasoning is confined to the linguistic space, imposing a representational bottleneck that struggles to faithfully capture ineffable physical attributes. To mitigate these limitations, we propose LaST$_0$, a framework that enables efficient reasoning before acting through a Latent Spatio-Temporal Chain-of-Thought (CoT), capturing fine-grained physical and robotic dynamics that are often difficult to verbalize. Specifically, we introduce a token-efficient latent CoT space that models future visual dynamics, 3D structural information, and robot proprioceptive states, and further extends these representations across time to enable temporally consistent implicit reasoning trajectories. Furthermore, LaST$_0$ adopts a dual-system architecture implemented via a Mixture-of-Transformers design, where a reasoning expert conducts low-frequency latent inference and an acting expert generates high-frequency actions conditioned on robotics-oriented latent representations. To facilitate coordination, LaST$_0$ is trained with heterogeneous operation frequencies, enabling adaptive switching between reasoning and action inference rates during deployment. Across ten simulated and six real-world manipulation tasks, LaST$_0$ improves mean success rates by 8% and 13% over prior VLA methods, respectively, while achieving substantially faster inference. Project website: https://sites.google.com/view/last0
☆ Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration
Functional grasping with dexterous robotic hands is a key capability for enabling tool use and complex manipulation, yet progress has been constrained by two persistent bottlenecks: the scarcity of large-scale datasets and the absence of integrated semantic and geometric reasoning in learned models. In this work, we present CorDex, a framework that robustly learns dexterous functional grasps of novel objects from synthetic data generated from just a single human demonstration. At the core of our approach is a correspondence-based data engine that generates diverse, high-quality training data in simulation. Based on the human demonstration, our data engine generates diverse object instances of the same category, transfers the expert grasp to the generated objects through correspondence estimation, and adapts the grasp through optimization. Building on the generated data, we introduce a multimodal prediction network that integrates visual and geometric information. By devising a local-global fusion module and an importance-aware sampling mechanism, we enable robust and computationally efficient prediction of functional dexterous grasps. Through extensive experiments across various object categories, we demonstrate that CorDex generalizes well to unseen object instances and significantly outperforms state-of-the-art baselines.
comment: Project Page: https://cordex-manipulation.github.io/
☆ RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to scale across diverse environments. Recent work uses text-prompt conditioned image diffusion models to augment manipulation data by altering the backgrounds and tabletop objects in the visual observations. However, these approaches often overlook the practical need for multi-view and temporally coherent observations required by state-of-the-art policy models. Further, text prompts alone cannot reliably specify the scene setup. To provide the diffusion model with explicit visual guidance, we introduce visual identity prompting, which supplies exemplar images as conditioning inputs to guide the generation of the desired scene setup. To this end, we also build a scalable pipeline to curate a visual identity pool from large robotics datasets. Using our augmented manipulation data to train downstream vision-language-action and visuomotor policy models yields consistent performance gains in both simulation and real-robot settings.
☆ Driving on Registers
We present DrivoR, a simple and efficient transformer-based architecture for end-to-end autonomous driving. Our approach builds on pretrained Vision Transformers (ViTs) and introduces camera-aware register tokens that compress multi-camera features into a compact scene representation, significantly reducing downstream computation without sacrificing accuracy. These tokens drive two lightweight transformer decoders that generate and then score candidate trajectories. The scoring decoder learns to mimic an oracle and predicts interpretable sub-scores representing aspects such as safety, comfort, and efficiency, enabling behavior-conditioned driving at inference. Despite its minimal design, DrivoR outperforms or matches strong contemporary baselines across NAVSIM-v1, NAVSIM-v2, and the photorealistic closed-loop HUGSIM benchmark. Our results show that a pure-transformer architecture, combined with targeted token compression, is sufficient for accurate, efficient, and adaptive end-to-end driving. Code and checkpoints will be made available via the project page.
☆ Compensation Effect Amplification Control (CEAC): A movement-based approach for coordinated position and velocity control of the elbow of upper-limb prostheses
Despite advances in upper-limb (UL) prosthetic design, achieving intuitive control of intermediate joints - such as the wrist and elbow - remains challenging, particularly for continuous and velocity-modulated movements. We introduce a novel movement-based control paradigm entitled Compensation Effect Amplification Control (CEAC) that leverages users' trunk flexion and extension as input for controlling prosthetic elbow velocity. Considering that the trunk can be both a functional and compensatory joint when performing upper-limb actions, CEAC amplifies the natural coupling between trunk and prosthesis while introducing a controlled delay that allows users to modulate both the position and velocity of the prosthetic joint. We evaluated CEAC in a generic drawing task performed by twelve able-bodied participants using a supernumerary prosthesis with an active elbow. Additionally a multiple-target-reaching task was performed by a subset of ten participants. Results demonstrate task performances comparable to those obtained with natural arm movements, even when gesture velocity or drawing size were varied, while maintaining ergonomic trunk postures. Analysis revealed that CEAC effectively restores joint coordinated action, distributes movement effort between trunk and elbow, enabling intuitive trajectory control without requiring extreme compensatory movements. Overall, CEAC offers a promising control strategy for intermediate joints of UL prostheses, particularly in tasks requiring continuous and precise coordination.
☆ DAVOS: An Autonomous Vehicle Operating System in the Vehicle Computing Era
Vehicle computing represents a fundamental shift in how autonomous vehicles are designed and deployed, transforming them from isolated transportation systems into mobile computing platforms that support both safety-critical, real-time driving and data-centric services. In this setting, vehicles simultaneously support real-time driving pipelines and a growing set of data-driven applications, placing increased responsibility on the vehicle operating system to coordinate computation, data movement, storage, and access. These demands highlight recurring system considerations related to predictable execution, data and execution protection, efficient handling of high-rate sensor data, and long-term system evolvability, commonly summarized as Safety, Security, Efficiency, and Extensibility (SSEE). Existing vehicle operating systems and runtimes address these concerns in isolation, resulting in fragmented software stacks that limit coordination between autonomy workloads and vehicle data services. This paper presents DAVOS, the Delaware Autonomous Vehicle Operating System, a unified vehicle operating system architecture designed for the vehicle computing context. DAVOS provides a cohesive operating system foundation that supports both real-time autonomy and extensible vehicle computing within a single system framework.
☆ The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms IROS 2025
Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.
comment: Official IROS 2025 RoboSense Challenge Report; 51 pages, 37 figures, 5 tables; Competition Website at https://robosense2025.github.io/
☆ When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics
Assistive devices must determine both what a user intends to do and how reliable that prediction is before providing support. We introduce a safety-critical triggering framework based on calibrated probabilities for multimodal next-action prediction in Activities of Daily Living. Raw model confidence often fails to reflect true correctness, posing a safety risk. Post-hoc calibration aligns predicted confidence with empirical reliability and reduces miscalibration by about an order of magnitude without affecting accuracy. The calibrated confidence drives a simple ACT/HOLD rule that acts only when reliability is high and withholds assistance otherwise. This turns the confidence threshold into a quantitative safety parameter for assisted actions and enables verifiable behavior in an assistive control loop.
☆ SKATER: Synthesized Kinematics for Advanced Traversing Efficiency on a Humanoid Robot via Roller Skate Swizzles
Although recent years have seen significant progress of humanoid robots in walking and running, the frequent foot strikes with ground during these locomotion gaits inevitably generate high instantaneous impact forces, which leads to exacerbated joint wear and poor energy utilization. Roller skating, as a sport with substantial biomechanical value, can achieve fast and continuous sliding through rational utilization of body inertia, featuring minimal kinetic energy loss. Therefore, this study proposes a novel humanoid robot with each foot equipped with a row of four passive wheels for roller skating. A deep reinforcement learning control framework is also developed for the swizzle gait with the reward function design based on the intrinsic characteristics of roller skating. The learned policy is first analyzed in simulation and then deployed on the physical robot to demonstrate the smoothness and efficiency of the swizzle gait over traditional bipedal walking gait in terms of Impact Intensity and Cost of Transport during locomotion. A reduction of $75.86\%$ and $63.34\%$ of these two metrics indicate roller skating as a superior locomotion mode for enhanced energy efficiency and joint longevity.
☆ Zero Wrench Control via Wrench Disturbance Observer for Learning-free Peg-in-hole Assembly
This paper proposes a Dynamic Wrench Disturbance Observer (DW-DOB) designed to achieve highly sensitive zero-wrench control in contact-rich manipulation. By embedding task-space inertia into the observer nominal model, DW-DOB cleanly separates intrinsic dynamic reactions from true external wrenches. This preserves sensitivity to small forces and moments while ensuring robust regulation of contact wrenches. A passivity-based analysis further demonstrates that DW-DOB guarantees stable interactions under dynamic conditions, addressing the shortcomings of conventional observers that fail to compensate for inertial effects. Peg-in-hole experiments at industrial tolerances (H7/h6) validate the approach, yielding deeper and more compliant insertions with minimal residual wrenches and outperforming a conventional wrench disturbance observer and a PD baseline. These results highlight DW-DOB as a practical learning-free solution for high-precision zero-wrench control in contact-rich tasks.
☆ SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning
Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task navigation guided by complex, long-horizon language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such multi-task instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a navigation model built on a hierarchical planning framework. Our SeqWalker features: i) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; ii) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the superiority of the proposed SeqWalker.
☆ Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead
Reinforcement Learning (RL) has shown remarkable success in real-world applications, particularly in robotics control. However, RL adoption remains limited due to insufficient safety guarantees. We introduce Nightmare Dreamer, a model-based Safe RL algorithm that addresses safety concerns by leveraging a learned world model to predict potential safety violations and plan actions accordingly. Nightmare Dreamer achieves nearly zero safety violations while maximizing rewards. Nightmare Dreamer outperforms model-free baselines on Safety Gymnasium tasks using only image observations, achieving nearly a 20x improvement in efficiency.
comment: RSS'25: Multi-Objective Optimization and Planning in Robotics Workshop: 5 pages, 8 figures
☆ Optimizing Path Planning using Deep Reinforcement Learning for UGVs in Precision Agriculture
This study focuses on optimizing path planning for unmanned ground vehicles (UGVs) in precision agriculture using deep reinforcement learning (DRL) techniques in continuous action spaces. The research begins with a review of traditional grid-based methods, such as A* and Dijkstra's algorithms, and discusses their limitations in dynamic agricultural environments, highlighting the need for adaptive learning strategies. The study then explores DRL approaches, including Deep Q-Networks (DQN), which demonstrate improved adaptability and performance in two-dimensional simulations. Enhancements such as Double Q-Networks and Dueling Networks are evaluated to further improve decision-making. Building on these results, the focus shifts to continuous action space models, specifically Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3), which are tested in increasingly complex environments. Experiments conducted in a three-dimensional environment using ROS and Gazebo demonstrate the effectiveness of continuous DRL algorithms in navigating dynamic agricultural scenarios. Notably, the pretrained TD3 agent achieves a 95 percent success rate in dynamic environments, demonstrating the robustness of the proposed approach in handling moving obstacles while ensuring safety for both crops and the robot.
☆ Model of Spatial Human-Agent Interaction with Consideration for Others
Communication robots often need to initiate conversations with people in public spaces. At the same time, such robots must not disturb pedestrians. To handle these two requirements, an agent needs to estimate the communication desires of others based on their behavior and then adjust its own communication activities accordingly. In this study, we construct a computational spatial interaction model that considers others. Consideration is expressed as a quantitative parameter: the amount of adjustment of one's internal state to the estimated internal state of the other. To validate the model, we experimented with a human and a virtual robot interacting in a VR environment. The results show that when the participant moves to the target, a virtual robot with a low consideration value inhibits the participant's movement, while a robot with a higher consideration value did not inhibit the participant's movement. When the participant approached the robot, the robot also exhibited approaching behavior, regardless of the consideration value, thus decreasing the participant's movement. These results appear to verify the proposed model's ability to clarify interactions with consideration for others.
☆ UniBiDex: A Unified Teleoperation Framework for Robotic Bimanual Dexterous Manipulation
We present UniBiDex a unified teleoperation framework for robotic bimanual dexterous manipulation that supports both VRbased and leaderfollower input modalities UniBiDex enables realtime contactrich dualarm teleoperation by integrating heterogeneous input devices into a shared control stack with consistent kinematic treatment and safety guarantees The framework employs nullspace control to optimize bimanual configurations ensuring smooth collisionfree and singularityaware motion across tasks We validate UniBiDex on a longhorizon kitchentidying task involving five sequential manipulation subtasks demonstrating higher task success rates smoother trajectories and improved robustness compared to strong baselines By releasing all hardware and software components as opensource we aim to lower the barrier to collecting largescale highquality human demonstration datasets and accelerate progress in robot learning.
☆ Discrete Fourier Transform-based Point Cloud Compression for Efficient SLAM in Featureless Terrain
Simultaneous Localization and Mapping (SLAM) is an essential technology for the efficiency and reliability of unmanned robotic exploration missions. While the onboard computational capability and communication bandwidth are critically limited, the point cloud data handled by SLAM is large in size, attracting attention to data compression methods. To address such a problem, in this paper, we propose a new method for compressing point cloud maps by exploiting the Discrete Fourier Transform (DFT). The proposed technique converts the Digital Elevation Model (DEM) to the frequency-domain 2D image and omits its high-frequency components, focusing on the exploration of gradual terrains such as planets and deserts. Unlike terrains with detailed structures such as artificial environments, high-frequency components contribute little to the representation of gradual terrains. Thus, this method is effective in compressing data size without significant degradation of the point cloud. We evaluated the method in terms of compression rate and accuracy using camera sequences of two terrains with different elevation profiles.
comment: Author's version of a manuscript accepted at the 11th International Conference on Automation, Robotics, and Applications (ICARA). (c) IEEE
☆ Data-Driven Terramechanics Approach Towards a Realistic Real-Time Simulator for Lunar Rovers
High-fidelity simulators for the lunar surface provide a digital environment for extensive testing of rover operations and mission planning. However, current simulators focus on either visual realism or physical accuracy, which limits their capability to replicate lunar conditions comprehensively. This work addresses that gap by combining high visual fidelity with realistic terrain interaction for a realistic representation of rovers on the lunar surface. Because direct simulation of wheel-soil interactions is computationally expensive, a data-driven approach was adopted, using regression models for slip and sinkage from data collected in both full-rover and single-wheel experiments and simulations. The resulting regression-based terramechanics model accurately reproduced steady-state and dynamic slip, as well as sinkage behavior, on flat terrain and slopes up to 20 degrees, with validation against field test results. Additionally, improvements were made to enhance the realism of terrain deformation and wheel trace visualization. This method supports real-time applications that require physically plausible terrain response alongside high visual fidelity.
comment: Author's version of a manuscript accepted at the International Conference on Space Robotics 2025 (iSpaRo 2025). (c) IEEE
☆ Design and Development of Modular Limbs for Reconfigurable Robots on the Moon
In this paper, we present the development of 4-DOF robot limbs, which we call Moonbots, designed to connect in various configurations with each other and wheel modules, enabling adaptation to different environments and tasks. These modular components are intended primarily for robotic systems in space exploration and construction on the Moon in our Moonshot project. Such modular robots add flexibility and versatility for space missions where resources are constrained. Each module is driven by a common actuator characterized by a high torque-to-speed ratio, supporting both precise control and dynamic motion when required. This unified actuator design simplifies development and maintenance across the different module types. The paper describes the hardware implementation, the mechanical design of the modules, and the overall software architecture used to control and coordinate them. Additionally, we evaluate the control performance of the actuator under various load conditions to characterize its suitability for modular robot applications. To demonstrate the adaptability of the system, we introduce nine functional configurations assembled from the same set of modules: 4DOF-limb, 8DOF-limb, vehicle, dragon, minimal, quadruped, cargo, cargo-minimal, and bike. These configurations reflect different locomotion strategies and task-specific behaviors, offering a practical foundation for further research in reconfigurable robotic systems.
comment: Author's version of a manuscript accepted at the International Conference on Space Robotics 2025 (iSpaRo 2025). (c) IEEE
☆ Multiagent Reinforcement Learning with Neighbor Action Estimation
Multiagent reinforcement learning, as a prominent intelligent paradigm, enables collaborative decision-making within complex systems. However, existing approaches often rely on explicit action exchange between agents to evaluate action value functions, which is frequently impractical in real-world engineering environments due to communication constraints, latency, energy consumption, and reliability requirements. From an artificial intelligence perspective, this paper proposes an enhanced multiagent reinforcement learning framework that employs action estimation neural networks to infer agent behaviors. By integrating a lightweight action estimation module, each agent infers neighboring agents' behaviors using only locally observable information, enabling collaborative policy learning without explicit action sharing. This approach is fully compatible with standard TD3 algorithms and scalable to larger multiagent systems. At the engineering application level, this framework has been implemented and validated in dual-arm robotic manipulation tasks: two robotic arms collaboratively lift objects. Experimental results demonstrate that this approach significantly enhances the robustness and deployment feasibility of real-world robotic systems while reducing dependence on information infrastructure. Overall, this research advances the development of decentralized multiagent artificial intelligence systems while enabling AI to operate effectively in dynamic, information-constrained real-world environments.
☆ Fast Continuum Robot Shape and External Load State Estimation on SE(3) ICRA 2026
Previous on-manifold approaches to continuum robot state estimation have typically adopted simplified Cosserat rod models, which cannot directly account for actuation inputs or external loads. We introduce a general framework that incorporates uncertainty models for actuation (e.g., tendon tensions), applied forces and moments, process noise, boundary conditions, and arbitrary backbone measurements. By adding temporal priors across time steps, our method additionally performs joint estimation in both the spatial (arclength) and temporal domains, enabling full \textit{spacetime} state estimation. Discretizing the arclength domain yields a factor graph representation of the continuum robot model, which can be exploited for fast batch sparse nonlinear optimization in the style of SLAM. The framework is general and applies to a broad class of continuum robots; as illustrative cases, we show (i) tendon-driven robots in simulation, where we demonstrate real-time kinematics with uncertainty, tip force sensing from position feedback, and distributed load estimation from backbone strain, and (ii) a surgical concentric tube robot in experiment, where we validate accurate kinematics and tip force estimation, highlighting potential for surgical palpation.
comment: Public preprint for ICRA 2026
☆ Inverting Non-Injective Functions with Twin Neural Network Regression
Non-injective functions are not invertible. However, non-injective functions can be restricted to sub-domains on which they are locally injective and surjective and thus invertible if the dimensionality between input and output spaces are the same. Further, even if the dimensionalities do not match it is often possible to choose a preferred solution from many possible solutions. Twin neural network regression is naturally capable of incorporating these properties to invert non-injective functions. Twin neural network regression is trained to predict adjustments to well known input variables $\mathbf{x}^{\text{anchor}}$ to obtain an estimate for an unknown $\mathbf{x}^{\text{new}}$ under a change of the target variable from $\mathbf{y}^{\text{anchor}}$ to $\mathbf{y}^{\text{new}}$. In combination with k-nearest neighbor search, I propose a deterministic framework that finds input parameters to a given target variable of non-injective functions. The method is demonstrated by inverting non-injective functions describing toy problems and robot arm control that are a) defined by data or b) known as mathematical formula.
☆ PRISM: Protocol Refinement through Intelligent Simulation Modeling SC
Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates the design, validation, and execution of experimental protocols on a laboratory platform composed of off-the-shelf robotic instruments. PRISM uses a set of language-model-based agents that work together to generate and refine experimental steps. The process begins with automatically gathering relevant procedures from web-based sources describing experimental workflows. These are converted into structured experimental steps (e.g., liquid handling steps, deck layout and other related operations) through a planning, critique, and validation loop. The finalized steps are translated into the Argonne MADSci protocol format, which provides a unified interface for coordinating multiple robotic instruments (Opentrons OT-2 liquid handler, PF400 arm, Azenta plate sealer and peeler) without requiring human intervention between steps. To evaluate protocol-generation performance, we benchmarked both single reasoning models and multi-agent workflow across constrained and open-ended prompting paradigms. The resulting protocols were validated in a digital-twin environment built in NVIDIA Omniverse to detect physical or sequencing errors before execution. Using Luna qPCR amplification and Cell Painting as case studies, we demonstrate PRISM as a practical end-to-end workflow that bridges language-based protocol generation, simulation-based validation, and automated robotic execution.
comment: 43 pages, 8 figures, submitted to RSC Digital Discovery. Equal contribution: B. Hsu, P.V. Setty, R.M. Butler. Corresponding author: A. Ramanathan
☆ Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models
Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze Assisted Manipulation for Modular Autonomy), a system that leverages ego-centric gaze tracking and a vision-language model to infer user intent and autonomously execute robotic manipulation tasks. By contextualizing gaze fixations within the scene, the system maps visual attention to high-level semantic understanding, enabling skill selection and parameterization without task-specific training. We evaluate GAMMA on a range of table-top manipulation tasks and compare it against baseline gaze-based control without reasoning. Results demonstrate that GAMMA provides robust, intuitive, and generalizable control, highlighting the potential of combining foundation models and gaze for natural and scalable robot autonomy. Project website: https://gamma0.vercel.app/
comment: Accepted to 2025 RSS Robot Planning in the Era of Foundation Models (FM4RoboPlan) Workshop
♻ ☆ $π_0$: A Vision-Language-Action Flow Model for General Robot Control
Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obstacles in terms of data, generalization, and robustness. In this paper, we discuss how generalist robot policies (i.e., robot foundation models) can address these challenges, and how we can design effective generalist robot policies for complex and highly dexterous tasks. We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM) to inherit Internet-scale semantic knowledge. We then discuss how this model can be trained on a large and diverse dataset from multiple dexterous robot platforms, including single-arm robots, dual-arm robots, and mobile manipulators. We evaluate our model in terms of its ability to perform tasks in zero shot after pre-training, follow language instructions from people and from a high-level VLM policy, and its ability to acquire new skills via fine-tuning. Our results cover a wide variety of tasks, such as laundry folding, table cleaning, and assembling boxes.
comment: See project website for videos: https://physicalintelligence.company/blog/pi0 Published in RSS 2025
♻ ☆ Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
Reinforcement Learning (RL) has achieved impressive results in robotics, yet high-performing pipelines remain highly task-specific, with little reuse of prior data. Offline Model-based RL (MBRL) offers greater data efficiency by training policies entirely from existing datasets, but suffers from compounding errors and distribution shift in long-horizon rollouts. Although existing methods have shown success in controlled simulation benchmarks, robustly applying them to the noisy, biased, and partially observed datasets typical of real-world robotics remains challenging. We present a principled pipeline for making offline MBRL effective on physical robots. Our RWM-U extends autoregressive world models with epistemic uncertainty estimation, enabling temporally consistent multi-step rollouts with uncertainty effectively propagated over long horizons. We combine RWM-U with MOPO-PPO, which adapts uncertainty-penalized policy optimization to the stable, on-policy PPO framework for real-world control. We evaluate our approach on diverse manipulation and locomotion tasks in simulation and on real quadruped and humanoid, training policies entirely from offline datasets. The resulting policies consistently outperform model-free and uncertainty-unaware model-based baselines, and fusing real-world data in model learning further yields robust policies that surpass online model-free baselines trained solely in simulation.
♻ ☆ ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise into a flow policy's deterministic path, converting the flow into a discrete-time Markov Process for exact and straightforward likelihood computation. This conversion facilitates exploration and ensures training stability, enabling ReinFlow to fine-tune diverse flow model variants, including Rectified Flow [35] and Shortcut Models [19], particularly at very few or even one denoising step. We benchmark ReinFlow in representative locomotion and manipulation tasks, including long-horizon planning with visual input and sparse reward. The episode reward of Rectified Flow policies obtained an average net growth of 135.36% after fine-tuning in challenging legged locomotion tasks while saving denoising steps and 82.63% of wall time compared to state-of-the-art diffusion RL fine-tuning method DPPO [43]. The success rate of the Shortcut Model policies in state and visual manipulation tasks achieved an average net increase of 40.34% after fine-tuning with ReinFlow at four or even one denoising step, whose performance is comparable to fine-tuned DDIM policies while saving computation time for an average of 23.20%. Project webpage: https://reinflow.github.io/
comment: 38 pages
♻ ☆ ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning and improve exploration efficiency, their planning remains constrained by textual representations, which cannot adequately capture spatial occupancy or scene geometry--critical factors for navigation decisions. We explore whether Vision-Language Models (VLMs) can achieve mapless visual navigation using only onboard RGB/RGB-D streams, unlocking their potential for spatial perception and planning. We achieve this through an imagination-powered navigation framework, ImagineNav++, which imagines future observation images from candidate robot views and translates navigation planning into a simple best-view image selection problem for VLMs. First, a future-view imagination module distills human navigation preferences to generate semantically meaningful viewpoints with high exploration potential. These imagined views then serve as visual prompts for the VLM to identify the most informative viewpoint. To maintain spatial consistency, we develop a selective foveation memory mechanism, which hierarchically integrates keyframe observations via a sparse-to-dense framework, constructing a compact yet comprehensive memory for long-term spatial reasoning. This approach transforms goal-oriented navigation into a series of tractable point-goal navigation tasks. Extensive experiments on open-vocabulary object and instance navigation benchmarks show that ImagineNav++ achieves SOTA performance in mapless settings, even surpassing most map-based methods, highlighting the importance of scene imagination and memory in VLM-based spatial reasoning.
comment: 17 pages, 10 figures. arXiv admin note: text overlap with arXiv:2410.09874
♻ ☆ Cognitive-Hierarchy Guided End-to-End Planning for Autonomous Driving
While end-to-end autonomous driving has advanced significantly, prevailing methods remain fundamentally misaligned with human cognitive principles in both perception and planning. In this paper, we propose CogAD, a novel end-to-end autonomous driving model that emulates the hierarchical cognition mechanisms of human drivers. CogAD implements dual hierarchical mechanisms: global-to-local context processing for human-like perception and intent-conditioned multi-mode trajectory generation for cognitively-inspired planning. The proposed method demonstrates three principal advantages: comprehensive environmental understanding through hierarchical perception, robust planning exploration enabled by multi-level planning, and diverse yet reasonable multi-modal trajectory generation facilitated by dual-level uncertainty modeling. Extensive experiments on nuScenes and Bench2Drive demonstrate that CogAD achieves state-of-the-art performance in end-to-end planning, exhibiting particular superiority in long-tail scenarios and robust generalization to complex real-world driving conditions.
♻ ☆ Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning
This paper proposes an exploration-efficient Deep Reinforcement Learning with Reference policy (DRLR) framework for learning robotics tasks that incorporates demonstrations. The DRLR framework is developed based on an algorithm called Imitation Bootstrapped Reinforcement Learning (IBRL). We propose to improve IBRL by modifying the action selection module. The proposed action selection module provides a calibrated Q-value, which mitigates the bootstrapping error that otherwise leads to inefficient exploration. Furthermore, to prevent the RL policy from converging to a sub-optimal policy, SAC is used as the RL policy instead of TD3. The effectiveness of our method in mitigating bootstrapping error and preventing overfitting is empirically validated by learning two robotics tasks: bucket loading and open drawer, which require extensive interactions with the environment. Simulation results also demonstrate the robustness of the DRLR framework across tasks with both low and high state-action dimensions, and varying demonstration qualities. To evaluate the developed framework on a real-world industrial robotics task, the bucket loading task is deployed on a real wheel loader. The sim2real results validate the successful deployment of the DRLR framework.
comment: This paper has been accepted for Journal publication in Frontiers in Robotics and AI
♻ ☆ Properties of Lyapunov Subcenter Manifolds in Conservative Mechanical Systems
Multi-body mechanical systems have rich internal dynamics, whose solutions can be exploited as efficient control targets. Yet, solutions non-trivially depend on system parameters, obscuring feasible properties for use as target trajectories. For periodic regulation tasks in robotics applications, we investigate properties of nonlinear normal modes (NNMs) collected in Lyapunov subcenter manifolds (LSMs) of conservative mechanical systems. Using a time-symmetry of conservative mechanical systems, we show that mild non-resonance conditions guarantee LSMs to be Eigenmanifolds, in which NNMs are guaranteed to oscillate between two points of zero velocity. We also prove the existence of a unique generator, which is a connected, 1D manifold that collects these points of zero velocity for a given Eigenmanifold. Furthermore, we show that an additional spatial symmetry provides LSMs with yet stronger properties of Rosenberg manifolds. Here all brake trajectories pass through a unique equilibrium configuration, which can be favorable for control applications. These theoretical results are numerically confirmed on two mechanical systems: a double pendulum and a 5-link pendulum.
comment: 18 pages, 27 figures, submitted to Automatica
♻ ☆ SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection
Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated via game engine-based simulations provides a promising and cost-effective solution to overcome this issue. Therefore, we present SynDroneVision, a synthetic dataset specifically designed for RGB-based drone detection in surveillance applications. Featuring diverse backgrounds, lighting conditions, and drone models, SynDroneVision offers a comprehensive training foundation for deep learning algorithms. To evaluate the dataset's effectiveness, we perform a comparative analysis across a selection of recent YOLO detection models. Our findings demonstrate that SynDroneVision is a valuable resource for real-world data enrichment, achieving notable enhancements in model performance and robustness, while significantly reducing the time and costs of real-world data acquisition. SynDroneVision will be publicly released upon paper acceptance.
♻ ☆ RoboReward: General-Purpose Vision-Language Reward Models for Robotics
A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives. Vision-language models (VLMs) have shown promise as automatic reward models, yet their effectiveness on real robot tasks is poorly understood. In this work, we aim to close this gap by introducing (1) RoboReward, a robotics reward dataset and benchmark built on large-scale real-robot corpora from Open X-Embodiment (OXE) and RoboArena, and (2) vision-language reward models trained on this dataset (RoboReward 4B/8B). Because OXE is success-heavy and lacks failure examples, we propose a negative examples data augmentation pipeline that generates calibrated negative and near-misses via counterfactual relabeling of successful episodes and temporal clipping to create partial-progress outcomes from the same videos. Using this framework, we build a large training and evaluation dataset spanning diverse tasks and embodiments to test whether state-of-the-art VLMs can reliably provide rewards for robot learning. Our evaluation of open and proprietary VLMs finds that no model excels across tasks, highlighting substantial room for improvement. We then train general-purpose 4B- and 8B-parameter models that outperform much larger VLMs in assigning rewards for short-horizon robotic tasks. Finally, we deploy the 8B model in real-robot reinforcement learning and find that it improves policy learning over Gemini Robotics-ER 1.5 while narrowing the gap to RL training with human-provided rewards. We release the full dataset, trained reward models, and evaluation suite on our website to advance the development of general-purpose reward models in robotics: https://crfm.stanford.edu/helm/robo-reward-bench (project website).
♻ ☆ Human-Aided Trajectory Planning for Automated Vehicles through Teleoperation and Arbitration Graphs
Teleoperation enables remote human support of automated vehicles in scenarios where the automation is not able to find an appropriate solution. Remote assistance concepts, where operators provide discrete inputs to aid specific automation modules like planning, is gaining interest due to its reduced workload on the human remote operator and improved safety. However, these concepts are challenging to implement and maintain due to their deep integration and interaction with the automated driving system. In this paper, we propose a solution to facilitate the implementation of remote assistance concepts that intervene on planning level and extend the operational design domain of the vehicle at runtime. Using arbitration graphs, a modular decision-making framework, we integrate remote assistance into an existing automated driving system without modifying the original software components. Our simulative implementation demonstrates this approach in two use cases, allowing operators to adjust planner constraints and enable trajectory generation beyond nominal operational design domains.
comment: 7 pages, 8 figures, presented at IEEE Intelligent Vehicles Symposium 2025, video demonstration available at https://www.youtube.com/watch?v=fVSO-YOeGMk
♻ ☆ Bio-Skin: A Cost-Effective Thermostatic Tactile Sensor with Multi-Modal Force and Temperature Detection IROS2025
Tactile sensors can significantly enhance the perception of humanoid robotics systems by providing contact information that facilitates human-like interactions. However, existing commercial tactile sensors focus on improving the resolution and sensitivity of single-modal detection with high-cost components and densely integrated design, incurring complex manufacturing processes and unaffordable prices. In this work, we present Bio-Skin, a cost-effective multi-modal tactile sensor that utilizes single-axis Hall-effect sensors for planar normal force measurement and bar-shape piezo resistors for 2D shear force measurement. A thermistor coupling with a heating wire is integrated into a silicone body to achieve temperature sensation and thermostatic function analogous to human skin. We also present a cross-reference framework to validate the two modalities of the force sensing signal, improving the sensing fidelity in a complex electromagnetic environment. Bio-Skin has a multi-layer design, and each layer is manufactured sequentially and subsequently integrated, thereby offering a fast production pathway. After calibration, Bio-Skin demonstrates performance metrics-including signal-to-range ratio, sampling rate, and measurement range-comparable to current commercial products, with one-tenth of the cost. The sensor's real-world performance is evaluated using an Allegro hand in object grasping tasks, while its temperature regulation functionality was assessed in a material detection task.
comment: This work has been published by IROS2025
♻ ☆ Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems
The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor data. While foundation models excel in single-modal contexts, integrating their capabilities across diverse sensors like cameras and LiDAR to create a unified understanding remains a formidable challenge. This paper presents a comprehensive framework for multi-modal pre-training, identifying the core set of techniques driving progress toward this goal. We dissect the interplay between foundational sensor characteristics and learning strategies, evaluating the role of platform-specific datasets in enabling these advancements. Our central contribution is the formulation of a unified taxonomy for pre-training paradigms: ranging from single-modality baselines to sophisticated unified frameworks that learn holistic representations for advanced tasks like 3D object detection and semantic occupancy prediction. Furthermore, we investigate the integration of textual inputs and occupancy representations to facilitate open-world perception and planning. Finally, we identify critical bottlenecks, such as computational efficiency and model scalability, and propose a roadmap toward general-purpose multi-modal foundation models capable of achieving robust Spatial Intelligence for real-world deployment.
comment: Survey; 40 pages, 7 figures, 9 tables; GitHub Repo at https://github.com/worldbench/awesome-spatial-intelligence
♻ ☆ FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis
Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly challenging. In this paper, we present a synthetic garment dataset that can be used for robotic garment folding. We begin by constructing geometric garment templates based on keypoints and applying generative models to generate realistic texture patterns. Leveraging these keypoint annotations, we generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning. To improve robustness, we propose KG-DAgger, which uses a keypoint-based strategy to generate demonstration data for recovering from failures. KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25\%. After training with 15K trajectories (about 2M image-action pairs), the model achieves a 75\% success rate in the real world. Experiments in both simulation and real-world settings validate the effectiveness of our proposed framework.
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent approach involves training a world model from state-action trajectories and subsequently use it with a planning algorithm to solve new tasks. Planning is commonly performed in the input space, but a recent family of methods has introduced planning algorithms that optimize in the learned representation space of the world model, with the promise that abstracting irrelevant details yields more efficient planning. In this work, we characterize models from this family as JEPA-WMs and investigate the technical choices that make algorithms from this class work. We propose a comprehensive study of several key components with the objective of finding the optimal approach within the family. We conducted experiments using both simulated environments and real-world robotic data, and studied how the model architecture, the training objective, and the planning algorithm affect planning success. We combine our findings to propose a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks. Code, data and checkpoints are available at https://github.com/facebookresearch/jepa-wms.
comment: V2 of the article: - Added AdaLN-zero - Added table comparing JEPA-WMs with baselines with std translating per-seed variability only, no variability across epochs - Reordered figures in main body of the paper
♻ ☆ Grasp the Graph (GtG) 2.0: Ensemble of Graph Neural Networks for High-Precision Grasp Pose Detection in Clutter
Grasp pose detection in cluttered, real-world environments remains a significant challenge due to noisy and incomplete sensory data combined with complex object geometries. This paper introduces Grasp the Graph 2.0 (GtG 2.0) method, a lightweight yet highly effective hypothesis-and-test robotics grasping framework which leverages an ensemble of Graph Neural Networks for efficient geometric reasoning from point cloud data. Building on the success of GtG 1.0, which demonstrated the potential of Graph Neural Networks for grasp detection but was limited by assumptions of complete, noise-free point clouds and 4-Dof grasping, GtG 2.0 employs a conventional Grasp Pose Generator to efficiently produce 7-Dof grasp candidates. Candidates are assessed with an ensemble Graph Neural Network model which includes points within the gripper jaws (inside points) and surrounding contextual points (outside points). This improved representation boosts grasp detection performance over previous methods using the same generator. GtG 2.0 shows up to a 35% improvement in Average Precision on the GraspNet-1Billion benchmark compared to hypothesis-and-test and Graph Neural Network-based methods, ranking it among the top three frameworks. Experiments with a 3-Dof Delta Parallel robot and Kinect-v1 camera show a success rate of 91% and a clutter completion rate of 100%, demonstrating its flexibility and reliability.
comment: 20 pages
♻ ☆ Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agents AAAI
We introduce the Block Rearrangement Problem (BRaP), a challenging component of large warehouse management which involves rearranging storage blocks within dense grids to achieve a goal state. We formally define the BRaP as a graph search problem. Building on intuitions from sliding puzzle problems, we propose five search-based solution algorithms, leveraging joint configuration space search, classical planning, multi-agent pathfinding, and expert heuristics. We evaluate the five approaches empirically for plan quality and scalability. Despite the exponential relation between search space size and block number, our methods demonstrate efficiency in creating rearrangement plans for deeply buried blocks in up to 80x80 grids.
comment: AAAI Conference on Artificial Intelligence (AAAI-26)
Robotics 40
☆ Choreographing a World of Dynamic Objects
Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord
☆ Embedding Autonomous Agents in Resource-Constrained Robotic Platforms
Many embedded devices operate under resource constraints and in dynamic environments, requiring local decision-making capabilities. Enabling devices to make independent decisions in such environments can improve the responsiveness of the system and reduce the dependence on constant external control. In this work, we integrate an autonomous agent, programmed using AgentSpeak, with a small two-wheeled robot that explores a maze using its own decision-making and sensor data. Experimental results show that the agent successfully solved the maze in 59 seconds using 287 reasoning cycles, with decision phases taking less than one millisecond. These results indicate that the reasoning process is efficient enough for real-time execution on resource-constrained hardware. This integration demonstrates how high-level agent-based control can be applied to resource-constrained embedded systems for autonomous operation.
comment: This is an open-access, author-archived version of a manuscript published in European Conference on Multi-Agent Systems 2025
☆ Hierarchical GNN-Based Multi-Agent Learning for Dynamic Queue-Jump Lane and Emergency Vehicle Corridor Formation
Emergency vehicles require rapid passage through congested traffic, yet existing strategies fail to adapt to dynamic conditions. We propose a novel hierarchical graph neural network (GNN)-based multi-agent reinforcement learning framework to coordinate connected vehicles for emergency corridor formation. Our approach uses a high-level planner for global strategy and low-level controllers for trajectory execution, utilizing graph attention networks to scale with variable agent counts. Trained via Multi-Agent Proximal Policy Optimization (MAPPO), the system reduces emergency vehicle travel time by 28.3% compared to baselines and 44.6% compared to uncoordinated traffic in simulations. The design achieves near-zero collision rates (0.3%) while maintaining 81% of background traffic efficiency. Ablation and generalization studies confirm the framework's robustness across diverse scenarios. These results demonstrate the effectiveness of combining GNNs with hierarchical learning for intelligent transportation systems.
comment: 16 Pages, 5 Figures, 9 Tables, submitted to IEEE TITS
☆ Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test
As world models gain momentum in Embodied AI, an increasing number of works explore using video foundation models as predictive world models for downstream embodied tasks like 3D prediction or interactive generation. However, before exploring these downstream tasks, video foundation models still have two critical questions unanswered: (1) whether their generative generalization is sufficient to maintain perceptual fidelity in the eyes of human observers, and (2) whether they are robust enough to serve as a universal prior for real-world embodied agents. To provide a standardized framework for answering these questions, we introduce the Embodied Turing Test benchmark: WoW-World-Eval (Wow,wo,val). Building upon 609 robot manipulation data, Wow-wo-val examines five core abilities, including perception, planning, prediction, generalization, and execution. We propose a comprehensive evaluation protocol with 22 metrics to assess the models' generation ability, which achieves a high Pearson Correlation between the overall score and human preference (>0.93) and establishes a reliable foundation for the Human Turing Test. On Wow-wo-val, models achieve only 17.27 on long-horizon planning and at best 68.02 on physical consistency, indicating limited spatiotemporal consistency and physical reasoning. For the Inverse Dynamic Model Turing Test, we first use an IDM to evaluate the video foundation models' execution accuracy in the real world. However, most models collapse to $\approx$ 0% success, while WoW maintains a 40.74% success rate. These findings point to a noticeable gap between the generated videos and the real world, highlighting the urgency and necessity of benchmarking World Model in Embodied AI.
☆ CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from visual entanglement, capturing noise rather than manipulation skills. To address this, we propose Contrastive Latent Action Pretraining (CLAP), a framework that aligns the visual latent space from videos with a proprioceptive latent space from robot trajectories. By employing contrastive learning, CLAP maps video transitions onto a quantized, physically executable codebook. Building on this representation, we introduce a dual-formulation VLA framework offering both CLAP-NTP, an autoregressive model excelling at instruction following and object generalization, and CLAP-RF, a Rectified Flow-based policy designed for high-frequency, precise manipulation. Furthermore, we propose a Knowledge Matching (KM) regularization strategy to mitigate catastrophic forgetting during fine-tuning. Extensive experiments demonstrate that CLAP significantly outperforms strong baselines, enabling the effective transfer of skills from human videos to robotic execution. Project page: https://lin-shan.com/CLAP/.
comment: Project page: https://lin-shan.com/CLAP/
☆ Stable Language Guidance for Vision-Language-Action Models
Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose \textbf{Residual Semantic Steering (RSS)}, a probabilistic framework that disentangles physical affordance from semantic execution. RSS introduces two theoretical innovations: (1) \textbf{Monte Carlo Syntactic Integration}, which approximates the true semantic posterior via dense, LLM-driven distributional expansion, and (2) \textbf{Residual Affordance Steering}, a dual-stream decoding mechanism that explicitly isolates the causal influence of language by subtracting the visual affordance prior. Theoretical analysis suggests that RSS effectively maximizes the mutual information between action and intent while suppressing visual distractors. Empirical results across diverse manipulation benchmarks demonstrate that RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.
☆ CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM
Recent Vision-Language Models (VLMs) have demonstrated significant potential in robotic planning. However, they typically function as semantic reasoners, lacking an intrinsic understanding of the specific robot's physical capabilities. This limitation is particularly critical in interactive navigation, where robots must actively modify cluttered environments to create traversable paths. Existing VLM-based navigators are predominantly confined to passive obstacle avoidance, failing to reason about when and how to interact with objects to clear blocked paths. To bridge this gap, we propose Counterfactual Interactive Navigation via Skill-aware VLM (CoINS), a hierarchical framework that integrates skill-aware reasoning and robust low-level execution. Specifically, we fine-tune a VLM, named InterNav-VLM, which incorporates skill affordance and concrete constraint parameters into the input context and grounds them into a metric-scale environmental representation. By internalizing the logic of counterfactual reasoning through fine-tuning on the proposed InterNav dataset, the model learns to implicitly evaluate the causal effects of object removal on navigation connectivity, thereby determining interaction necessity and target selection. To execute the generated high-level plans, we develop a comprehensive skill library through reinforcement learning, specifically introducing traversability-oriented strategies to manipulate diverse objects for path clearance. A systematic benchmark in Isaac Sim is proposed to evaluate both the reasoning and execution aspects of interactive navigation. Extensive simulations and real-world experiments demonstrate that CoINS significantly outperforms representative baselines, achieving a 17\% higher overall success rate and over 80\% improvement in complex long-horizon scenarios compared to the best-performing baseline
comment: 17 pages, 13 figures
☆ An Event-Based Opto-Tactile Skin
This paper presents a neuromorphic, event-driven tactile sensing system for soft, large-area skin, based on the Dynamic Vision Sensors (DVS) integrated with a flexible silicone optical waveguide skin. Instead of repetitively scanning embedded photoreceivers, this design uses a stereo vision setup comprising two DVS cameras looking sideways through the skin. Such a design produces events as changes in brightness are detected, and estimates press positions on the 2D skin surface through triangulation, utilizing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to find the center of mass of contact events resulting from pressing actions. The system is evaluated over a 4620 mm2 probed area of the skin using a meander raster scan. Across 95 % of the presses visible to both cameras, the press localization achieved a Root-Mean-Squared Error (RMSE) of 4.66 mm. The results highlight the potential of this approach for wide-area flexible and responsive tactile sensors in soft robotics and interactive environments. Moreover, we examined how the system performs when the amount of event data is strongly reduced. Using stochastic down-sampling, the event stream was reduced to 1/1024 of its original size. Under this extreme reduction, the average localization error increased only slightly (from 4.66 mm to 9.33 mm), and the system still produced valid press localizations for 85 % of the trials. This reduction in pass rate is expected, as some presses no longer produce enough events to form a reliable cluster for triangulation. These results show that the sensing approach remains functional even with very sparse event data, which is promising for reducing power consumption and computational load in future implementations. The system exhibits a detection latency distribution with a characteristic width of 31 ms.
comment: Accepted for publication in Frontiers in Neuromorphic Engineering. 23 pages, 9 figures
☆ Towards Safe Autonomous Driving: A Real-Time Motion Planning Algorithm on Embedded Hardware
Ensuring the functional safety of Autonomous Vehicles (AVs) requires motion planning modules that not only operate within strict real-time constraints but also maintain controllability in case of system faults. Existing safeguarding concepts, such as Online Verification (OV), provide safety layers that detect infeasible planning outputs. However, they lack an active mechanism to ensure safe operation in the event that the main planner fails. This paper presents a first step toward an active safety extension for fail-operational Autonomous Driving (AD). We deploy a lightweight sampling-based trajectory planner on an automotive-grade, embedded platform running a Real-Time Operating System (RTOS). The planner continuously computes trajectories under constrained computational resources, forming the foundation for future emergency planning architectures. Experimental results demonstrate deterministic timing behavior with bounded latency and minimal jitter, validating the feasibility of trajectory planning on safety-certifiable hardware. The study highlights both the potential and the remaining challenges of integrating active fallback mechanisms as an integral part of next-generation safeguarding frameworks. The code is available at: https://github.com/TUM-AVS/real-time-motion-planning
comment: 7 pages, submitted to the IEEE Intelligent Vehicles Symposium (IV 2026), Detroit, MI, United States
☆ Bayesian Monocular Depth Refinement via Neural Radiance Fields
Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine geometric detail needed for accurate scene understanding. We propose MDENeRF, an iterative framework that refines monocular depth estimates using depth information from Neural Radiance Fields (NeRFs). MDENeRF consists of three components: (1) an initial monocular estimate for global structure, (2) a NeRF trained on perturbed viewpoints, with per-pixel uncertainty, and (3) Bayesian fusion of the noisy monocular and NeRF depths. We derive NeRF uncertainty from the volume rendering process to iteratively inject high-frequency fine details. Meanwhile, our monocular prior maintains global structure. We demonstrate superior performance on key metrics and experiments using indoor scenes from the SUN RGB-D dataset.
comment: IEEE 8th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2025). Oral presentation; Best Presenter Award
☆ Integrating Sample Inheritance into Bayesian Optimization for Evolutionary Robotics
In evolutionary robotics, robot morphologies are designed automatically using evolutionary algorithms. This creates a body-brain optimization problem, where both morphology and control must be optimized together. A common approach is to include controller optimization for each morphology, but starting from scratch for every new body may require a high controller learning budget. We address this by using Bayesian optimization for controller optimization, exploiting its sample efficiency and strong exploration capabilities, and using sample inheritance as a form of Lamarckian inheritance. Under a deliberately low controller learning budget for each morphology, we investigate two types of sample inheritance: (1) transferring all the parent's samples to the offspring to be used as prior without evaluating them, and (2) reevaluating the parent's best samples on the offspring. Both are compared to a baseline without inheritance. Our results show that reevaluation performs best, with prior-based inheritance also outperforming no inheritance. Analysis reveals that while the learning budget is too low for a single morphology, generational inheritance compensates for this by accumulating learned adaptations across generations. Furthermore, inheritance mainly benefits offspring morphologies that are similar to their parents. Finally, we demonstrate the critical role of the environment, with more challenging environments resulting in more stable walking gaits. Our findings highlight that inheritance mechanisms can boost performance in evolutionary robotics without needing large learning budgets, offering an efficient path toward more capable robot design.
☆ Generational Replacement and Learning for High-Performing and Diverse Populations in Evolvable Robots
Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimization of body and control is challenging, because controllers need some time to adapt to the evolving morphology - which may make it difficult for new and promising designs to enter the evolving population. A solution to this is to add intra-life learning, defined as an additional controller optimization loop, to each individual in the evolving population. A related problem is the lack of diversity often seen in evolving populations as evolution narrows the search down to a few promising designs too quickly. This problem can be mitigated by implementing full generational replacement, where offspring robots replace the whole population. This solution for increasing diversity usually comes at the cost of lower performance compared to using elitism. In this work, we show that combining such generational replacement with intra-life learning can increase diversity while retaining performance. We also highlight the importance of performance metrics when studying learning in morphologically evolving robots, showing that evaluating according to function evaluations versus according to generations of evolution can give different conclusions.
☆ PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
Humans anticipate, from a glance and a contemplated action of their bodies, how the 3D world will respond, a capability that is equally vital for robotic manipulation. We introduce PointWorld, a large pre-trained 3D world model that unifies state and action in a shared 3D space as 3D point flows: given one or few RGB-D images and a sequence of low-level robot action commands, PointWorld forecasts per-pixel displacements in 3D that respond to the given actions. By representing actions as 3D point flows instead of embodiment-specific action spaces (e.g., joint positions), this formulation directly conditions on physical geometries of robots while seamlessly integrating learning across embodiments. To train our 3D world model, we curate a large-scale dataset spanning real and simulated robotic manipulation in open-world environments, enabled by recent advances in 3D vision and simulated environments, totaling about 2M trajectories and 500 hours across a single-arm Franka and a bimanual humanoid. Through rigorous, large-scale empirical studies of backbones, action representations, learning objectives, partial observability, data mixtures, domain transfers, and scaling, we distill design principles for large-scale 3D world modeling. With a real-time (0.1s) inference speed, PointWorld can be efficiently integrated in the model-predictive control (MPC) framework for manipulation. We demonstrate that a single pre-trained checkpoint enables a real-world Franka robot to perform rigid-body pushing, deformable and articulated object manipulation, and tool use, without requiring any demonstrations or post-training and all from a single image captured in-the-wild. Project website at https://point-world.github.io/.
☆ Dual-Attention Heterogeneous GNN for Multi-robot Collaborative Area Search via Deep Reinforcement Learning
In multi-robot collaborative area search, a key challenge is to dynamically balance the two objectives of exploring unknown areas and covering specific targets to be rescued. Existing methods are often constrained by homogeneous graph representations, thus failing to model and balance these distinct tasks. To address this problem, we propose a Dual-Attention Heterogeneous Graph Neural Network (DA-HGNN) trained using deep reinforcement learning. Our method constructs a heterogeneous graph that incorporates three entity types: robot nodes, frontier nodes, and interesting nodes, as well as their historical states. The dual-attention mechanism comprises the relational-aware attention and type-aware attention operations. The relational-aware attention captures the complex spatio-temporal relationships among robots and candidate goals. Building on this relational-aware heterogeneous graph, the type-aware attention separately computes the relevance between robots and each goal type (frontiers vs. points of interest), thereby decoupling the exploration and coverage from the unified tasks. Extensive experiments conducted in interactive 3D scenarios within the iGibson simulator, leveraging the Gibson and MatterPort3D datasets, validate the superior scalability and generalization capability of the proposed approach.
☆ Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection
Monocular 3D object detection offers a low-cost alternative to LiDAR, yet remains less accurate due to the difficulty of estimating metric depth from a single image. We systematically evaluate how depth backbones and feature engineering affect a monocular Pseudo-LiDAR pipeline on the KITTI validation split. Specifically, we compare NeWCRFs (supervised metric depth) against Depth Anything V2 Metric-Outdoor (Base) under an identical pseudo-LiDAR generation and PointRCNN detection protocol. NeWCRFs yields stronger downstream 3D detection, achieving 10.50\% AP$_{3D}$ at IoU$=0.7$ on the Moderate split using grayscale intensity (Exp~2). We further test point-cloud augmentations using appearance cues (grayscale intensity) and semantic cues (instance segmentation confidence). Contrary to the expectation that semantics would substantially close the gap, these features provide only marginal gains, and mask-based sampling can degrade performance by removing contextual geometry. Finally, we report a depth-accuracy-versus-distance diagnostic using ground-truth 2D boxes (including Ped/Cyc), highlighting that coarse depth correctness does not fully predict strict 3D IoU. Overall, under an off-the-shelf LiDAR detector, depth-backbone choice and geometric fidelity dominate performance, outweighing secondary feature injection.
comment: 7 pages, 4 figures
☆ Locomotion Beyond Feet
Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under chairs, knee-high walls, knee-high platforms, and steep ascending and descending stairs. Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains. To this end, we combine physics-grounded keyframe animation with reinforcement learning. Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware, while reinforcement learning transforms these references into robust, physically accurate motions. We further employ a hierarchical framework consisting of terrain-specific motion-tracking policies, failure recovery mechanisms, and a vision-based skill planner. Real-world experiments demonstrate that Locomotion Beyond Feet achieves robust whole-body locomotion and generalizes across obstacle sizes, obstacle instances, and terrain sequences.
comment: Project website: https://locomotion-beyond-feet.github.io/
☆ From Score to Sound: An End-to-End MIDI-to-Motion Pipeline for Robotic Cello Performance
Robot musicians require precise control to obtain proper note accuracy, sound quality, and musical expression. Performance of string instruments, such as violin and cello, presents a significant challenge due to the precise control required over bow angle and pressure to produce the desired sound. While prior robotic cellists focus on accurate bowing trajectories, these works often rely on expensive motion capture techniques, and fail to sightread music in a human-like way. We propose a novel end-to-end MIDI score to robotic motion pipeline which converts musical input directly into collision-aware bowing motions for a UR5e robot cellist. Through use of Universal Robot Freedrive feature, our robotic musician can achieve human-like sound without the need for motion capture. Additionally, this work records live joint data via Real-Time Data Exchange (RTDE) as the robot plays, providing labeled robotic playing data from a collection of five standard pieces to the research community. To demonstrate the effectiveness of our method in comparison to human performers, we introduce the Musical Turing Test, in which a collection of 132 human participants evaluate our robot's performance against a human baseline. Human reference recordings are also released, enabling direct comparison for future studies. This evaluation technique establishes the first benchmark for robotic cello performance. Finally, we outline a residual reinforcement learning methodology to improve upon baseline robotic controls, highlighting future opportunities for improved string-crossing efficiency and sound quality.
☆ A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields
Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This paper introduces a new robust model that employs parallel layers of place fields at multiple spatial scales, a replay-based reward mechanism, and dynamic scale fusion. Simulations show that the model improves path efficiency and accelerates learning compared to single-scale baselines, highlighting the value of multiscale spatial representations for adaptive robot navigation.
comment: 11 pages, 8 figures. Submitted to IEEE Transactions on Cognitive and Developmental Systems
☆ A Vision-Language-Action Model with Visual Prompt for OFF-Road Autonomous Driving
Efficient trajectory planning in off-road terrains presents a formidable challenge for autonomous vehicles, often necessitating complex multi-step pipelines. However, traditional approaches exhibit limited adaptability in dynamic environments. To address these limitations, this paper proposes OFF-EMMA, a novel end-to-end multimodal framework designed to overcome the deficiencies of insufficient spatial perception and unstable reasoning in visual-language-action (VLA) models for off-road autonomous driving scenarios. The framework explicitly annotates input images through the design of a visual prompt block and introduces a chain-of-thought with self-consistency (COT-SC) reasoning strategy to enhance the accuracy and robustness of trajectory planning. The visual prompt block utilizes semantic segmentation masks as visual prompts, enhancing the spatial understanding ability of pre-trained visual-language models for complex terrains. The COT- SC strategy effectively mitigates the error impact of outliers on planning performance through a multi-path reasoning mechanism. Experimental results on the RELLIS-3D off-road dataset demonstrate that OFF-EMMA significantly outperforms existing methods, reducing the average L2 error of the Qwen backbone model by 13.3% and decreasing the failure rate from 16.52% to 6.56%.
Transformer-based Multi-agent Reinforcement Learning for Separation Assurance in Structured and Unstructured Airspaces
Conventional optimization-based metering depends on strict adherence to precomputed schedules, which limits the flexibility required for the stochastic operations of Advanced Air Mobility (AAM). In contrast, multi-agent reinforcement learning (MARL) offers a decentralized, adaptive framework that can better handle uncertainty, required for safe aircraft separation assurance. Despite this advantage, current MARL approaches often overfit to specific airspace structures, limiting their adaptability to new configurations. To improve generalization, we recast the MARL problem in a relative polar state space and train a transformer encoder model across diverse traffic patterns and intersection angles. The learned model provides speed advisories to resolve conflicts while maintaining aircraft near their desired cruising speeds. In our experiments, we evaluated encoder depths of 1, 2, and 3 layers in both structured and unstructured airspaces, and found that a single encoder configuration outperformed deeper variants, yielding near-zero near mid-air collision rates and shorter loss-of-separation infringements than the deeper configurations. Additionally, we showed that the same configuration outperforms a baseline model designed purely with attention. Together, our results suggest that the newly formulated state representation, novel design of neural network architecture, and proposed training strategy provide an adaptable and scalable decentralized solution for aircraft separation assurance in both structured and unstructured airspaces.
comment: 9 pages, 4 figures, 4 tables. Presented at SESAR Innovation Days 2025
☆ Enhanced-FQL($λ$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay
This paper introduces a fuzzy reinforcement learning framework, Enhanced-FQL($λ$), that integrates novel Fuzzified Eligibility Traces (FET) and Segmented Experience Replay (SER) into fuzzy Q-learning with Fuzzified Bellman Equation (FBE) for continuous control tasks. The proposed approach employs an interpretable fuzzy rule base instead of complex neural architectures, while maintaining competitive performance through two key innovations: a fuzzified Bellman equation with eligibility traces for stable multi-step credit assignment, and a memory-efficient segment-based experience replay mechanism for enhanced sample efficiency. Theoretical analysis proves the proposed method convergence under standard assumptions. Extensive evaluations in continuous control domains demonstrate that Enhanced-FQL($λ$) achieves superior sample efficiency and reduced variance compared to n-step fuzzy TD and fuzzy SARSA($λ$) baselines, while maintaining substantially lower computational complexity than deep RL alternatives such as DDPG. The framework's inherent interpretability, combined with its computational efficiency and theoretical convergence guarantees, makes it particularly suitable for safety-critical applications where transparency and resource constraints are essential.
comment: Submitted to ECC26 conference
☆ UNIC: Learning Unified Multimodal Extrinsic Contact Estimation
Contact-rich manipulation requires reliable estimation of extrinsic contacts-the interactions between a grasped object and its environment which provide essential contextual information for planning, control, and policy learning. However, existing approaches often rely on restrictive assumptions, such as predefined contact types, fixed grasp configurations, or camera calibration, that hinder generalization to novel objects and deployment in unstructured environments. In this paper, we present UNIC, a unified multimodal framework for extrinsic contact estimation that operates without any prior knowledge or camera calibration. UNIC directly encodes visual observations in the camera frame and integrates them with proprioceptive and tactile modalities in a fully data-driven manner. It introduces a unified contact representation based on scene affordance maps that captures diverse contact formations and employs a multimodal fusion mechanism with random masking, enabling robust multimodal representation learning. Extensive experiments demonstrate that UNIC performs reliably. It achieves a 9.6 mm average Chamfer distance error on unseen contact locations, performs well on unseen objects, remains robust under missing modalities, and adapts to dynamic camera viewpoints. These results establish extrinsic contact estimation as a practical and versatile capability for contact-rich manipulation.
☆ Autonomous Reasoning for Spacecraft Control: A Large Language Model Framework with Group Relative Policy Optimization
This paper presents a learning-based guidance-and-control approach that couples a reasoning-enabled Large Language Model (LLM) with Group Relative Policy Optimization (GRPO). A two-stage procedure consisting of Supervised Fine-Tuning (SFT) to learn formatting and control primitives, followed by GRPO for interaction-driven policy improvement, trains controllers for each environment. The framework is demonstrated on four control problems spanning a gradient of dynamical complexity, from canonical linear systems through nonlinear oscillatory dynamics to three-dimensional spacecraft attitude control with gyroscopic coupling and thrust constraints. Results demonstrate that an LLM with explicit reasoning, optimized via GRPO, can synthesize feasible stabilizing policies under consistent training settings across both linear and nonlinear systems. The two-stage training methodology enables models to generate control sequences while providing human-readable explanations of their decision-making process. This work establishes a foundation for applying GRPO-based reasoning to autonomous control systems, with potential applications in aerospace and other safety-critical domains.
☆ Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control
We introduce online action-stacking, an inference-time wrapper for reinforcement learning policies that produces realistic air traffic control commands while allowing training on a much smaller discrete action space. Policies are trained with simple incremental heading or level adjustments, together with an action-damping penalty that reduces instruction frequency and leads agents to issue commands in short bursts. At inference, online action-stacking compiles these bursts of primitive actions into domain-appropriate compound clearances. Using Proximal Policy Optimisation and the BluebirdDT digital twin platform, we train agents to navigate aircraft along lateral routes, manage climb and descent to target flight levels, and perform two-aircraft collision avoidance under a minimum separation constraint. In our lateral navigation experiments, action stacking greatly reduces the number of issued instructions relative to a damped baseline and achieves comparable performance to a policy trained with a 37-dimensional action space, despite operating with only five actions. These results indicate that online action-stacking helps bridge a key gap between standard reinforcement learning formulations and operational ATC requirements, and provides a simple mechanism for scaling to more complex control scenarios.
☆ Correcting Autonomous Driving Object Detection Misclassifications with Automated Commonsense Reasoning
Autonomous Vehicle (AV) technology has been heavily researched and sought after, yet there are no SAE Level 5 AVs available today in the marketplace. We contend that over-reliance on machine learning technology is the main reason. Use of automated commonsense reasoning technology, we believe, can help achieve SAE Level 5 autonomy. In this paper, we show how automated common-sense reasoning technology can be deployed in situations where there are not enough data samples available to train a deep learning-based AV model that can handle certain abnormal road scenarios. Specifically, we consider two situations where (i) a traffic signal is malfunctioning at an intersection and (ii) all the cars ahead are slowing down and steering away due to an unexpected obstruction (e.g., animals on the road). We show that in such situations, our commonsense reasoning-based solution accurately detects traffic light colors and obstacles not correctly captured by the AV's perception model. We also provide a pathway for efficiently invoking commonsense reasoning by measuring uncertainty in the computer vision model and using commonsense reasoning to handle uncertain scenarios. We describe our experiments conducted using the CARLA simulator and the results obtained. The main contribution of our research is to show that automated commonsense reasoning effectively corrects AV-based object detection misclassifications and that hybrid models provide an effective pathway to improving AV perception.
comment: In Proceedings ICLP 2025, arXiv:2601.00047
♻ ☆ Supercomputing for High-speed Avoidance and Reactive Planning in Robots
This paper presents SHARP (Supercomputing for High-speed Avoidance and Reactive Planning), a proof-of-concept study demonstrating how high-performance computing (HPC) can enable millisecond-scale responsiveness in robotic control. While modern robots face increasing demands for reactivity in human-robot shared workspaces, onboard processors are constrained by size, power, and cost. Offloading to HPC offers massive parallelism for trajectory planning, but its feasibility for real-time robotics remains uncertain due to network latency and jitter. We evaluate SHARP in a stress-test scenario where a 7-DOF manipulator must dodge high-speed foam projectiles. Using a hash-distributed multi-goal A* search implemented with MPI on both local and remote HPC clusters, the system achieves mean planning latencies of 22.9 ms (local) and 30.0 ms (remote, ~300 km away), with avoidance success rates of 84% and 88%, respectively. These results show that when round-trip latency remains within the tens-of-milliseconds regime, HPC-side computation is no longer the bottleneck, enabling avoidance well below human reaction times. The SHARP results motivate hybrid control architectures: low-level reflexes remain onboard for safety, while bursty, high-throughput planning tasks are offloaded to HPC for scalability. By reporting per-stage timing and success rates, this study provides a reproducible template for assessing real-time feasibility of HPC-driven robotics. Collectively, SHARP reframes HPC offloading as a viable pathway toward dependable, reactive robots in dynamic environments.
comment: Error in the graph size calculation, recalculated and resubmitted
♻ ☆ Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
Reinforcement Learning (RL) has achieved impressive results in robotics, yet high-performing pipelines remain highly task-specific, with little reuse of prior data. Offline Model-based RL (MBRL) offers greater data efficiency by training policies entirely from existing datasets, but suffers from compounding errors and distribution shift in long-horizon rollouts. Although existing methods have shown success in controlled simulation benchmarks, robustly applying them to the noisy, biased, and partially observed datasets typical of real-world robotics remains challenging. We present a principled pipeline for making offline MBRL effective on physical robots. Our RWM-U extends autoregressive world models with epistemic uncertainty estimation, enabling temporally consistent multi-step rollouts with uncertainty effectively propagated over long horizons. We combine RWM-U with MOPO-PPO, which adapts uncertainty-penalized policy optimization to the stable, on-policy PPO framework for real-world control. We evaluate our approach on diverse manipulation and locomotion tasks in simulation and on real quadruped and humanoid, training policies entirely from offline datasets. The resulting policies consistently outperform model-free and uncertainty-unaware model-based baselines, and fusing real-world data in model learning further yields robust policies that surpass online model-free baselines trained solely in simulation.
♻ ☆ Real-time Velocity Profile Optimization for Time-Optimal Maneuvering with Generic Acceleration Constraints
The computation of time-optimal velocity profiles along prescribed paths, subject to generic acceleration constraints, is a crucial problem in robot trajectory planning, with particular relevance to autonomous racing. However, the existing methods either support arbitrary acceleration constraints at high computational cost or use conservative box constraints for computational efficiency. We propose FBGA, a new \underline{F}orward-\underline{B}ackward algorithm with \underline{G}eneric \underline{A}cceleration constraints, which achieves both high accuracy and low computation time. FBGA operates forward and backward passes to maximize the velocity profile in short, discretized path segments, while satisfying user-defined performance limits. Tested on five racetracks and two vehicle classes, FBGA handles complex, non-convex acceleration constraints with custom formulations. Its maneuvers and lap times closely match optimal control baselines (within $0.11\%$-$0.36\%$), while being up to three orders of magnitude faster. FBGA maintains high accuracy even with coarse discretization, making it well-suited for online multi-query trajectory planning. Our open-source \texttt{C++} implementation is available at: https://anonymous.4open.science/r/FB_public_RAL.
♻ ☆ The Combined Problem of Online Task Assignment and Lifelong Path Finding in Logistics Warehouses: Rule-Based Systems Matter
We study the combined problem of online task assignment and lifelong path finding, which is crucial for the logistics industries. However, most literature either (1) focuses on lifelong path finding assuming a given task assigner, or (2) studies the offline version of this problem where tasks are known in advance. We argue that, to maximize the system throughput, the online version that integrates these two components should be tackled directly. To this end, we introduce a formal framework of the combined problem and its solution concept. Then, we design a rule-based lifelong planner under a practical robot model that works well even in environments with severe local congestion. Upon that, we automate the search for the task assigner with respect to the underlying path planner. Simulation experiments conducted in warehouse scenarios at Meituan, one of the largest shopping platforms in China, demonstrate that (a)in terms of time efficiency, our system requires only 83.77% of the execution time needed for the currently deployed system at Meituan, outperforming other SOTA algorithms by 8.09%; (b)in terms of economic efficiency, ours can achieve the same throughput with only 60% of the agents currently in use. The code and demos are available at https://github.com/Fernadoo/Online-TAPF.
comment: In Proceedings ICLP 2025, arXiv:2601.00047
♻ ☆ Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
This paper addresses the Kidnapped Robot Problem (KRP), a core localization challenge of relocalizing a robot in a known map without prior pose estimate when localization loss or at SLAM initialization. For this purpose, a passive 2-D global relocalization framework is proposed. It estimates the global pose efficiently and reliably from a single LiDAR scan and an occupancy grid map while the robot remains stationary, thereby enhancing the long-term autonomy of mobile robots. The proposed framework casts global relocalization as a non-convex problem and solves it via the multi-hypothesis scheme with batched multi-stage inference and early termination, balancing completeness and efficiency. The Rapidly-exploring Random Tree (RRT), under traversability constraints, asymptotically covers the reachable space to generate sparse, uniformly distributed feasible positional hypotheses, fundamentally reducing the sampling space. The hypotheses are preliminarily ordered by the proposed Scan Mean Absolute Difference (SMAD), a coarse beam-error level metric that facilitates the early termination by prioritizing high-likelihood candidates. The SMAD computation is optimized for non-panoramic scans. The Translation-Affinity Scan-to-Map Alignment Metric (TAM) is proposed for reliable orientation selection at hypothesized positions and accurate final pose evaluation to mitigate degradation in conventional likelihood-field metrics under translational uncertainty induced by sparse hypotheses, as well as non-panoramic LiDAR scan and environmental changes. Real-world experiments on a resource-constrained mobile robot with non-panoramic LiDAR scans show that the proposed framework achieves competitive performance in both global relocalization success rate and computational efficiency.
comment: 10 pages, 8 figures. This work has been submitted to the IEEE for possible publication
♻ ☆ Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision-grounded, causally linked reasoning traces aligned with driving behaviors; (2) a modular VLA architecture combining Cosmos-Reason, a vision-language model pre-trained for Physical AI, with a diffusion-based trajectory decoder that generates dynamically feasible trajectories in real time; (3) a multi-stage training strategy using supervised fine-tuning to elicit reasoning and reinforcement learning (RL) to enforce reasoning-action consistency and optimize reasoning quality. AR1 achieves up to a 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline, with a 35% reduction in close encounter rate in closed-loop simulation. RL post-training improves reasoning quality by 45% and reasoning-action consistency by 37%. Model scaling from 0.5B to 7B parameters shows consistent improvements. On-vehicle road tests confirm real-time performance (99 ms latency) and successful urban deployment. By bridging interpretable reasoning with precise control, AR1 demonstrates a practical path towards Level 4 autonomous driving. Model weights are available at https://huggingface.co/nvidia/Alpamayo-R1-10B with inference code at https://github.com/NVlabs/alpamayo.
♻ ☆ From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous Driving
While end-to-end autonomous driving has achieved remarkable progress in geometric control, current systems remain constrained by a command-following paradigm that relies on simple navigational instructions. Transitioning to genuinely intelligent agents requires the capability to interpret and fulfill high-level, abstract human intentions. However, this advancement is hindered by the lack of dedicated benchmarks and semantic-aware evaluation metrics. In this paper, we formally define the task of Intention-Driven End-to-End Autonomous Driving and present Intention-Drive, a comprehensive benchmark designed to bridge this gap. We construct a large-scale dataset featuring complex natural language intentions paired with high-fidelity sensor data. To overcome the limitations of conventional trajectory-based metrics, we introduce the Imagined Future Alignment (IFA), a novel evaluation protocol leveraging generative world models to assess the semantic fulfillment of human goals beyond mere geometric accuracy. Furthermore, we explore the solution space by proposing two distinct paradigms: an end-to-end vision-language planner and a hierarchical agent-based framework. The experiments reveal a critical dichotomy where existing models exhibit satisfactory driving stability but struggle significantly with intention fulfillment. Notably, the proposed frameworks demonstrate superior alignment with human intentions.
♻ ☆ Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization
We present a low-cost data generation pipeline that integrates physics-based simulation, human demonstrations, and model-based planning to efficiently generate large-scale, high-quality datasets for contact-rich robotic manipulation tasks. Starting with a small number of embodiment-flexible human demonstrations collected in a virtual reality simulation environment, the pipeline refines these demonstrations using optimization-based kinematic retargeting and trajectory optimization to adapt them across various robot embodiments and physical parameters. This process yields a diverse, physically consistent dataset that enables cross-embodiment data transfer, and offers the potential to reuse legacy datasets collected under different hardware configurations or physical parameters. We validate the pipeline's effectiveness by training diffusion policies from the generated datasets for challenging contact-rich manipulation tasks across multiple robot embodiments, including a floating Allegro hand and bimanual robot arms. The trained policies are deployed zero-shot on hardware for bimanual iiwa arms, achieving high success rates with minimal human input. Project website: https://lujieyang.github.io/physicsgen/.
♻ ☆ OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
Embodied navigation presents a core challenge for intelligent robots, requiring the comprehension of visual environments, natural language instructions, and autonomous exploration. Existing models often fall short in offering a unified solution across diverse navigation paradigms, resulting in low success rates and limited generalization. We introduce OmniNav, a unified framework addressing instruct-goal, object-goal, point-goal navigation, and frontier-based exploration within a single architecture. Our approach features a lightweight, low-latency policy that accurately predicts continuous-space waypoints (coordinates and orientations). This policy surpasses action-chunk methods in precision and supports real-world deployment at control frequencies up to 5 Hz. Architecturally, OmniNav employs a fast-slow system design: a fast module generates waypoints using short-horizon visual context and subtasks, while a slow module performs deliberative planning with long-horizon observations and candidate frontiers to select subsequent subgoals and subtasks. This collaboration enhances path efficiency and maintains trajectory coherence, particularly in exploration and memory-intensive scenarios. Crucially, we identify that the primary bottleneck isn't merely navigation policy learning, but a robust understanding of general instructions and objects. To boost generalization, OmniNav integrates large-scale, general-purpose training datasets, including those for image captioning and visual recognition, into a joint multi-task regimen. This significantly improves success rates and robustness. Extensive experiments confirm OmniNav's state-of-the-art performance across various navigation benchmarks, with real-world deployment further validating its efficacy. OmniNav provides practical insights for embodied navigation, charting a scalable path towards versatile, highly generalizable robotic intelligence.
♻ ☆ Real-time Sampling-based Model Predictive Control based on Reverse Kullback-Leibler Divergence and Its Adaptive Acceleration
Sampling-based model predictive control (MPC) has the potential for use in a wide variety of robotic systems. However, its unstable updates and poor convergence render it unsuitable for real-time control of robotic systems. This study addresses this challenge with a novel approach from reverse Kullback-Leibler divergence, which has a mode-seeking property and is likely to find one of the locally optimal solutions early. Using this approach, a weighted maximum likelihood estimation with positive and negative weights is obtained and solved using the mirror descent (MD) algorithm. Negative weights eliminate unnecessary actions, but a practical implementation needs to be designed to avoid interference with positive and negative updates based on rejection sampling. In addition, Nesterov's acceleration method for the proposed MD is modified to improve heuristic step size adaptive to the noise estimated in update amounts. Real-time simulations show that the proposed method can solve a wider variety of tasks statistically than the conventional method. In addition, higher degrees-of-freedom tasks can be solved by the improved acceleration even with a CPU only. The real-world applicability of the proposed method is also demonstrated by optimizing the operability in a variable impedance control of a force-driven mobile robot. https://youtu.be/D8bFMzct1XM
comment: 18 pages, 16 figures
♻ ☆ Adaptive Anomaly Recovery for Telemanipulation: A Diffusion Model Approach to Vision-Based Tracking
Dexterous telemanipulation critically relies on the continuous and stable tracking of the human operator's commands to ensure robust operation. Vison-based tracking methods are widely used but have low stability due to anomalies such as occlusions, inadequate lighting, and loss of sight. Traditional filtering, regression, and interpolation methods are commonly used to compensate for explicit information such as angles and positions. These approaches are restricted to low-dimensional data and often result in information loss compared to the original high-dimensional image and video data. Recent advances in diffusion-based approaches, which can operate on high-dimensional data, have achieved remarkable success in video reconstruction and generation. However, these methods have not been fully explored in continuous control tasks in robotics. This work introduces the Diffusion-Enhanced Telemanipulation (DET) framework, which incorporates the Frame-Difference Detection (FDD) technique to identify and segment anomalies in video streams. These anomalous clips are replaced after reconstruction using diffusion models, ensuring robust telemanipulation performance under challenging visual conditions. We validated this approach in various anomaly scenarios and compared it with the baseline methods. Experiments show that DET achieves an average RMSE reduction of 17.2% compared to the cubic spline and 51.1% compared to FFT-based interpolation for different occlusion durations.
comment: This work has been submitted to the IEEE for possible publication
♻ ☆ Nonholonomic Robot Parking by Feedback -- Part I: Modular Strict CLF Designs
It has been known in the robotics literature since about 1995 that, in polar coordinates, the nonholonomic unicycle is asymptotically stabilizable by smooth feedback, even globally. We introduce a modular design framework that selects the forward velocity to decouple the radial coordinate, allowing the steering subsystem to be stabilized independently. Within this structure, we develop families of feedback laws using passivity, backstepping, and integrator forwarding. Each law is accompanied by a strict control Lyapunov function, including barrier variants that enforce angular constraints. These strict CLFs provide constructive class KL convergence estimates and enable eigenvalue assignment at the target equilibrium. The framework generalizes and extends prior modular and nonmodular approaches, while preparing the ground for inverse optimal and adaptive redesigns in the sequel paper.
comment: arXiv admin note: text overlap with arXiv:2509.25575
♻ ☆ Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey
Bipedal robots are gaining global recognition due to their potential applications and advancements in artificial intelligence, particularly through Deep Reinforcement Learning (DRL). While DRL has significantly advanced bipedal locomotion, the development of a unified framework capable of handling a wide range of tasks remains an ongoing challenge. This survey systematically categorises, compares, and analyses existing DRL frameworks for bipedal locomotion, organising them into end-to-end and hierarchical control schemes. End-to-end frameworks are evaluated based on their learning approaches, while hierarchical frameworks are examined in terms of layered structures that integrate learning-based or traditional model-based methods. We provide a detailed evaluation of the composition, strengths, limitations, and capabilities of each framework. Additionally, this survey identifies key research gaps and proposes future directions aimed at creating a more integrated and efficient framework for bipedal locomotion, with wide-ranging applications in real-world environments.
comment: Published in Artificial Intelligence Review
♻ ☆ Enhancing Sampling-based Planning with a Library of Paths
Path planning for 3D solid objects is a challenging problem, requiring a search in a six-dimensional configuration space, which is, nevertheless, essential in many robotic applications such as bin-picking and assembly. The commonly used sampling-based planners, such as Rapidly-exploring Random Trees, struggle with narrow passages where the sampling probability is low, increasing the time needed to find a solution. In scenarios like robotic bin-picking, various objects must be transported through the same environment. However, traditional planners start from scratch each time, losing valuable information gained during the planning process. We address this by using a library of past solutions, allowing the reuse of previous experiences even when planning for a new, previously unseen object. Paths for a set of objects are stored, and when planning for a new object, we find the most similar one in the library and use its paths as approximate solutions, adjusting for possible mutual transformations. The configuration space is then sampled along the approximate paths. Our method is tested in various narrow passage scenarios and compared with state-of-the-art methods from the OMPL library. Results show significant speed improvements (up to 85% decrease in the required time) of our method, often finding a solution in cases where the other planners fail. Our implementation of the proposed method is released as an open-source package.
♻ ☆ Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation
We present a generative predictive control (GPC) framework that amortizes sampling-based Model Predictive Control (SPC) by bootstrapping it with conditional flow-matching models trained on SPC control sequences collected in simulation. Unlike prior work relying on iterative refinement or gradient-based solvers, we show that meaningful proposal distributions can be learned directly from noisy SPC data, enabling more efficient and informed sampling during online planning. We further demonstrate, for the first time, the application of this approach to real-world contact-rich loco-manipulation with a quadruped robot. Extensive experiments in simulation and on hardware show that our method improves sample efficiency, reduces planning horizon requirements, and generalizes robustly across task variations.
comment: 9 pages, 4 figures
Robotics 50
☆ FIRE-VLM: A Vision-Language-Driven Reinforcement Learning Framework for UAV Wildfire Tracking in a Physics-Grounded Fire Digital Twin
Wildfire monitoring demands autonomous systems capable of reasoning under extreme visual degradation, rapidly evolving physical dynamics, and scarce real-world training data. Existing UAV navigation approaches rely on simplified simulators and supervised perception pipelines, and lack embodied agents interacting with physically realistic fire environments. We introduce FIRE-VLM, the first end-to-end vision-language model (VLM) guided reinforcement learning (RL) framework trained entirely within a high-fidelity, physics-grounded wildfire digital twin. Built from USGS Digital Elevation Model (DEM) terrain, LANDFIRE fuel inventories, and semi-physical fire-spread solvers, this twin captures terrain-induced runs, wind-driven acceleration, smoke plume occlusion, and dynamic fuel consumption. Within this environment, a PPO agent with dual-view UAV sensing is guided by a CLIP-style VLM. Wildfire-specific semantic alignment scores, derived from a single prompt describing active fire and smoke plumes, are integrated as potential-based reward shaping signals. Our contributions are: (1) a GIS-to-simulation pipeline for constructing wildfire digital twins; (2) a VLM-guided RL agent for UAV firefront tracking; and (3) a wildfire-aware reward design that combines physical terms with VLM semantics. Across five digital-twin evaluation tasks, our VLM-guided policy reduces time-to-detection by up to 6 times, increases time-in-FOV, and is, to our knowledge, the first RL-based UAV wildfire monitoring system demonstrated in kilometer-scale, physics-grounded digital-twin fires.
☆ Cost-Effective Radar Sensors for Field-Based Water Level Monitoring with Sub-Centimeter Accuracy
Water level monitoring is critical for flood management, water resource allocation, and ecological assessment, yet traditional methods remain costly and limited in coverage. This work explores radar-based sensing as a low-cost alternative for water level estimation, leveraging its non-contact nature and robustness to environmental conditions. Commercial radar sensors are evaluated in real-world field tests, applying statistical filtering techniques to improve accuracy. Results show that a single radar sensor can achieve centimeter-scale precision with minimal calibration, making it a practical solution for autonomous water monitoring using drones and robotic platforms.
comment: 10 pages, 6 figures. Preliminary results presented as a poster at an academic conference
☆ Towards Zero-Knowledge Task Planning via a Language-based Approach
In this work, we introduce and formalize the Zero-Knowledge Task Planning (ZKTP) problem, i.e., formulating a sequence of actions to achieve some goal without task-specific knowledge. Additionally, we present a first investigation and approach for ZKTP that leverages a large language model (LLM) to decompose natural language instructions into subtasks and generate behavior trees (BTs) for execution. If errors arise during task execution, the approach also uses an LLM to adjust the BTs on-the-fly in a refinement loop. Experimental validation in the AI2-THOR simulator demonstrate our approach's effectiveness in improving overall task performance compared to alternative approaches that leverage task-specific knowledge. Our work demonstrates the potential of LLMs to effectively address several aspects of the ZKTP problem, providing a robust framework for automated behavior generation with no task-specific setup.
☆ Modeling and Control for UAV with Off-center Slung Load
Unmanned aerial vehicle (UAV) with slung load system is a classic air transportation system. In practical applications, the suspension point of the slung load does not always align with the center of mass (CoM) of the UAV due to mission requirements or mechanical interference. This offset creates coupling in the system's nonlinear dynamics which leads to a complicated motion control problem. In existing research, modeling of the system are performed about the UAV's CoM. In this work we use the point of suspension instead. Based on the new model, a cascade control strategy is developed. In the middle-loop controller, the acceleration of the suspension point is used to regulate the swing angle of the slung load without the need for considering the coupling between the slung load and the UAV. Using the off-center reference frame, an inner-loop controller is designed to track the UAV's attitude without the need of simplification on the coupling effects. We prove local exponential stability of the closed-loop using Lyapunov approach. Finally, simulations and experiments are conducted to validate the proposed control system.
☆ Lunar Rover Cargo Transport: Mission Concept and Field Test
In future operations on the lunar surface, automated vehicles will be required to transport cargo between known locations. Such vehicles must be able to navigate precisely in safe regions to avoid natural hazards, human-constructed infrastructure, and dangerous dark shadows. Rovers must be able to park their cargo autonomously within a small tolerance to achieve a successful pickup and delivery. In this field test, Lidar Teach and Repeat provides an ideal autonomy solution for transporting cargo in this way. A one-tonne path-to-flight rover was driven in a semi-autonomous remote-control mode to create a network of safe paths. Once the route was taught, the rover immediately repeated the entire network of paths autonomously while carrying cargo. The closed-loop performance is accurate enough to align the vehicle to the cargo and pick it up. This field report describes a two-week deployment at the Canadian Space Agency's Analogue Terrain, culminating in a simulated lunar operation to evaluate the system's capabilities. Successful cargo collection and delivery were demonstrated in harsh environmental conditions.
comment: 15 Pages, 13 Figures, to appear in IEEE Transactions on Field Robotics
☆ Revisiting Continuous-Time Trajectory Estimation via Gaussian Processes and the Magnus Expansion
Continuous-time state estimation has been shown to be an effective means of (i) handling asynchronous and high-rate measurements, (ii) introducing smoothness to the estimate, (iii) post hoc querying the estimate at times other than those of the measurements, and (iv) addressing certain observability issues related to scanning-while-moving sensors. A popular means of representing the trajectory in continuous time is via a Gaussian process (GP) prior, with the prior's mean and covariance functions generated by a linear time-varying (LTV) stochastic differential equation (SDE) driven by white noise. When the state comprises elements of Lie groups, previous works have resorted to a patchwork of local GPs each with a linear time-invariant SDE kernel, which while effective in practice, lacks theoretical elegance. Here we revisit the full LTV GP approach to continuous-time trajectory estimation, deriving a global GP prior on Lie groups via the Magnus expansion, which offers a more elegant and general solution. We provide a numerical comparison between the two approaches and discuss their relative merits.
comment: 21 pages, 12 figures
☆ Nonlinear Spectral Modeling and Control of Soft-Robotic Muscles from Data
Artificial muscles are essential for compliant musculoskeletal robotics but complicate control due to nonlinear multiphysics dynamics. Hydraulically amplified electrostatic (HASEL) actuators, a class of soft artificial muscles, offer high performance but exhibit memory effects and hysteresis. Here we present a data-driven reduction and control strategy grounded in spectral submanifold (SSM) theory. In the adiabatic regime, where inputs vary slowly relative to intrinsic transients, trajectories rapidly converge to a low-dimensional slow manifold. We learn an explicit input-to-output map on this manifold from forced-response trajectories alone, avoiding decay experiments that can trigger hysteresis. We deploy the SSM-based model for real-time control of an antagonistic HASEL-clutch joint. This approach yields a substantial reduction in tracking error compared to feedback-only and feedforward-only baselines under identical settings. This record-and-control workflow enables rapid characterization and high-performance control of soft muscles and muscle-driven joints without detailed physics-based modeling.
☆ A High-Fidelity Digital Twin for Robotic Manipulation Based on 3D Gaussian Splatting
Developing high-fidelity, interactive digital twins is crucial for enabling closed-loop motion planning and reliable real-world robot execution, which are essential to advancing sim-to-real transfer. However, existing approaches often suffer from slow reconstruction, limited visual fidelity, and difficulties in converting photorealistic models into planning-ready collision geometry. We present a practical framework that constructs high-quality digital twins within minutes from sparse RGB inputs. Our system employs 3D Gaussian Splatting (3DGS) for fast, photorealistic reconstruction as a unified scene representation. We enhance 3DGS with visibility-aware semantic fusion for accurate 3D labelling and introduce an efficient, filter-based geometry conversion method to produce collision-ready models seamlessly integrated with a Unity-ROS2-MoveIt physics engine. In experiments with a Franka Emika Panda robot performing pick-and-place tasks, we demonstrate that this enhanced geometric accuracy effectively supports robust manipulation in real-world trials. These results demonstrate that 3DGS-based digital twins, enriched with semantic and geometric consistency, offer a fast, reliable, and scalable path from perception to manipulation in unstructured environments.
comment: Under review of Journal of Robot Learning
☆ Limited Linguistic Diversity in Embodied AI Datasets
Language plays a critical role in Vision-Language-Action (VLA) models, yet the linguistic characteristics of the datasets used to train and evaluate these systems remain poorly documented. In this work, we present a systematic dataset audit of several widely used VLA corpora, aiming to characterize what kinds of instructions these datasets actually contain and how much linguistic variety they provide. We quantify instruction language along complementary dimensions-including lexical variety, duplication and overlap, semantic similarity, and syntactic complexity. Our analysis shows that many datasets rely on highly repetitive, template-like commands with limited structural variation, yielding a narrow distribution of instruction forms. We position these findings as descriptive documentation of the language signal available in current VLA training and evaluation data, intended to support more detailed dataset reporting, more principled dataset selection, and targeted curation or augmentation strategies that broaden language coverage.
☆ Dual-quaternion learning control for autonomous vehicle trajectory tracking with safety guarantees
We propose a learning-based trajectory tracking controller for autonomous robotic platforms whose motion can be described kinematically on $\mathrm{SE}(3)$. The controller is formulated in the dual quaternion framework and operates at the velocity level, assuming direct command of angular and linear velocities, as is standard in many aerial vehicles and omnidirectional mobile robots. Gaussian Process (GP) regression is integrated into a geometric feedback law to learn and compensate online for unknown, state-dependent disturbances and modeling imperfections affecting both attitude and position, while preserving the algebraic structure and coupling properties inherent to rigid-body motion. The proposed approach does not rely on explicit parametric models of the unknown effects, making it well-suited for robotic systems subject to sensor-induced disturbances, unmodeled actuation couplings, and environmental uncertainties. A Lyapunov-based analysis establishes probabilistic ultimate boundedness of the pose tracking error under bounded GP uncertainty, providing formal stability guarantees for the learning-based controller. Simulation results demonstrate accurate and smooth trajectory tracking in the presence of realistic, localized disturbances, including correlated rotational and translational effects arising from magnetometer perturbations. These results illustrate the potential of combining geometric modeling and probabilistic learning to achieve robust, data-efficient pose control for autonomous robotic systems.
☆ HEXAR: a Hierarchical Explainability Architecture for Robots
As robotic systems become increasingly complex, the need for explainable decision-making becomes critical. Existing explainability approaches in robotics typically either focus on individual modules, which can be difficult to query from the perspective of high-level behaviour, or employ monolithic approaches, which do not exploit the modularity of robotic architectures. We present HEXAR (Hierarchical EXplainability Architecture for Robots), a novel framework that provides a plug-in, hierarchical approach to generate explanations about robotic systems. HEXAR consists of specialised component explainers using diverse explanation techniques (e.g., LLM-based reasoning, causal models, feature importance, etc) tailored to specific robot modules, orchestrated by an explainer selector that chooses the most appropriate one for a given query. We implement and evaluate HEXAR on a TIAGo robot performing assistive tasks in a home environment, comparing it against end-to-end and aggregated baseline approaches across 180 scenario-query variations. We observe that HEXAR significantly outperforms baselines in root cause identification, incorrect information exclusion, and runtime, offering a promising direction for transparent autonomous systems.
comment: 8 pages, 6 figures
☆ A Fast Semidefinite Convex Relaxation for Optimal Control Problems With Spatio-Temporal Constraints
Solving optimal control problems (OCPs) of autonomous agents operating under spatial and temporal constraints fast and accurately is essential in applications ranging from eco-driving of autonomous vehicles to quadrotor navigation. However, the nonlinear programs approximating the OCPs are inherently nonconvex due to the coupling between the dynamics and the event timing, and therefore, they are challenging to solve. Most approaches address this challenge by predefining waypoint times or just using nonconvex trajectory optimization, which simplifies the problem but often yields suboptimal solutions. To significantly improve the numerical properties, we propose a formulation with a time-scaling direct multiple shooting scheme that partitions the prediction horizon into segments aligned with characteristic time constraints. Moreover, we develop a fast semidefinite-programming-based convex relaxation that exploits the sparsity pattern of the lifted formulation. Comprehensive simulation studies demonstrate the solution optimality and computational efficiency. Furthermore, real-world experiments on a quadrotor waypoint flight task with constrained open time windows validate the practical applicability of the approach in complex environments.
comment: 9 pages, 6 figures
☆ SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality. Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific, limiting effective on-policy adaptation and scalable learning from real-world interaction. We introduce a Scalable Online Post-training (SOP) system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world. SOP tightly couples execution and learning through a closed-loop architecture in which a fleet of robots continuously streams on-policy experience and human intervention signals to a centralized cloud learner, and asynchronously receives updated policies. This design supports prompt on-policy correction, scales experience collection through parallel deployment, and preserves generality during adaptation. SOP is agnostic to the choice of post-training algorithm; we instantiate it with both interactive imitation learning (HG-DAgger) and reinforcement learning (RECAP). Across a range of real-world manipulation tasks including cloth folding, box assembly, and grocery restocking, we show that SOP substantially improves the performance of large pretrained VLA models while maintaining a single shared policy across tasks. Effective post-training can be achieved within hours of real-world interaction, and performance scales near-linearly with the number of robots in the fleet. These results suggest that tightly coupling online learning with fleet-scale deployment is instrumental to enabling efficient, reliable, and scalable post-training of generalist robot policies in the physical world.
☆ PiDR: Physics-Informed Inertial Dead Reckoning for Autonomous Platforms
A fundamental requirement for full autonomy is the ability to sustain accurate navigation in the absence of external data, such as GNSS signals or visual information. In these challenging environments, the platform must rely exclusively on inertial sensors, leading to pure inertial navigation. However, the inherent noise and other error terms of the inertial sensors in such real-world scenarios will cause the navigation solution to drift over time. Although conventional deep-learning models have emerged as a possible approach to inertial navigation, they are inherently black-box in nature. Furthermore, they struggle to learn effectively with limited supervised sensor data and often fail to preserve physical principles. To address these limitations, we propose PiDR, a physics-informed inertial dead-reckoning framework for autonomous platforms in situations of pure inertial navigation. PiDR offers transparency by explicitly integrating inertial navigation principles into the network training process through the physics-informed residual component. PiDR plays a crucial role in mitigating abrupt trajectory deviations even under limited or sparse supervision. We evaluated PiDR on real-world datasets collected by a mobile robot and an autonomous underwater vehicle. We obtained more than 29% positioning improvement in both datasets, demonstrating the ability of PiDR to generalize different platforms operating in various environments and dynamics. Thus, PiDR offers a robust, lightweight, yet effective architecture and can be deployed on resource-constrained platforms, enabling real-time pure inertial navigation in adverse scenarios.
comment: 11 pages and 7 figures
☆ Validating Generalist Robots with Situation Calculus and STL Falsification
Generalist robots are becoming a reality, capable of interpreting natural language instructions and executing diverse operations. However, their validation remains challenging because each task induces its own operational context and correctness specification, exceeding the assumptions of traditional validation methods. We propose a two-layer validation framework that combines abstract reasoning with concrete system falsification. At the abstract layer, situation calculus models the world and derives weakest preconditions, enabling constraint-aware combinatorial testing to systematically generate diverse, semantically valid world-task configurations with controllable coverage strength. At the concrete layer, these configurations are instantiated for simulation-based falsification with STL monitoring. Experiments on tabletop manipulation tasks show that our framework effectively uncovers failure cases in the NVIDIA GR00T controller, demonstrating its promise for validating general-purpose robot autonomy.
☆ A Bi-directional Adaptive Framework for Agile UAV Landing
Autonomous landing on mobile platforms is crucial for extending quadcopter operational flexibility, yet conventional methods are often too inefficient for highly dynamic scenarios. The core limitation lies in the prevalent ``track-then-descend'' paradigm, which treats the platform as a passive target and forces the quadcopter to perform complex, sequential maneuvers. This paper challenges that paradigm by introducing a bi-directional cooperative landing framework that redefines the roles of the vehicle and the platform. The essential innovation is transforming the problem from a single-agent tracking challenge into a coupled system optimization. Our key insight is that the mobile platform is not merely a target, but an active agent in the landing process. It proactively tilts its surface to create an optimal, stable terminal attitude for the approaching quadcopter. This active cooperation fundamentally breaks the sequential model by parallelizing the alignment and descent phases. Concurrently, the quadcopter's planning pipeline focuses on generating a time-optimal and dynamically feasible trajectory that minimizes energy consumption. This bi-directional coordination allows the system to execute the recovery in an agile manner, characterized by aggressive trajectory tracking and rapid state synchronization within transient windows. The framework's effectiveness, validated in dynamic scenarios, significantly improves the efficiency, precision, and robustness of autonomous quadrotor recovery in complex and time-constrained missions.
comment: This work has been submitted to the IEEE Robotics and Automation Letters (RA-L) for possible publication
☆ Learning to Act Robustly with View-Invariant Latent Actions
Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is unavoidable and can significantly disrupt policy performance. Existing methods typically learn invariance from multi-view observations at the scene level, but such approaches rely on visual appearance and fail to incorporate the physical dynamics essential for robust generalization. We propose View-Invariant Latent Action (VILA), which models a latent action capturing transition patterns across trajectories to learn view-invariant representations grounded in physical dynamics. VILA aligns these latent actions across viewpoints using an action-guided objective based on ground-truth action sequences. Experiments in both simulation and the real world show that VILA-based policies generalize effectively to unseen viewpoints and transfer well to new tasks, establishing VILA as a strong pretraining framework that improves robustness and downstream learning performance.
comment: Website: https://joon-stack.github.io/VILA/
☆ Parameter-Robust MPPI for Safe Online Learning of Unknown Parameters
Robots deployed in dynamic environments must remain safe even when key physical parameters are uncertain or change over time. We propose Parameter-Robust Model Predictive Path Integral (PRMPPI) control, a framework that integrates online parameter learning with probabilistic safety constraints. PRMPPI maintains a particle-based belief over parameters via Stein Variational Gradient Descent, evaluates safety constraints using Conformal Prediction, and optimizes both a nominal performance-driven and a safety-focused backup trajectory in parallel. This yields a controller that is cautious at first, improves performance as parameters are learned, and ensures safety throughout. Simulation and hardware experiments demonstrate higher success rates, lower tracking error, and more accurate parameter estimates than baselines.
☆ LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation models. To address this limitation, we propose LOST-3DSG, a lightweight open-vocabulary 3D scene graph designed to track dynamic objects in real-world environments. Our method adopts a semantic approach to entity tracking based on word2vec and sentence embeddings, enabling an open-vocabulary representation while avoiding the necessity of storing dense CLIP visual features. As a result, LOST-3DSG achieves superior performance compared to approaches that rely on high-dimensional visual embeddings. We evaluate our method through qualitative and quantitative experiments conducted in a real 3D environment using a TIAGo robot. The results demonstrate the effectiveness and efficiency of LOST-3DSG in dynamic object tracking. Code and supplementary material are publicly available on the project website at https://lab-rococo-sapienza.github.io/lost-3dsg/.
☆ Warm-Starting Collision-Free Model Predictive Control With Object-Centric Diffusion
Acting in cluttered environments requires predicting and avoiding collisions while still achieving precise control. Conventional optimization-based controllers can enforce physical constraints, but they struggle to produce feasible solutions quickly when many obstacles are present. Diffusion models can generate diverse trajectories around obstacles, yet prior approaches lacked a general and efficient way to condition them on scene structure. In this paper, we show that combining diffusion-based warm-starting conditioned with a latent object-centric representation of the scene and with a collision-aware model predictive controller (MPC) yields reliable and efficient motion generation under strict time limits. Our approach conditions a diffusion transformer on the system state, task, and surroundings, using an object-centric slot attention mechanism to provide a compact obstacle representation suitable for control. The sampled trajectories are refined by an optimal control problem that enforces rigid-body dynamics and signed-distance collision constraints, producing feasible motions in real time. On benchmark tasks, this hybrid method achieved markedly higher success rates and lower latency than sampling-based planners or either component alone. Real-robot experiments with a torque-controlled Panda confirm reliable and safe execution with MPC.
comment: An open-source implementation is provided https://cozy-fairy-0e0139.netlify.app/
☆ Soft Responsive Materials Enhance Humanoid Safety
Humanoid robots are envisioned as general-purpose platforms in human-centered environments, yet their deployment is limited by vulnerability to falls and the risks posed by rigid metal-plastic structures to people and surroundings. We introduce a soft-rigid co-design framework that leverages non-Newtonian fluid-based soft responsive materials to enhance humanoid safety. The material remains compliant during normal interaction but rapidly stiffens under impact, absorbing and dissipating fall-induced forces. Physics-based simulations guide protector placement and thickness and enable learning of active fall policies. Applied to a 42 kg life-size humanoid, the protector markedly reduces peak impact and allows repeated falls without hardware damage, including drops from 3 m and tumbles down long staircases. Across diverse scenarios, the approach improves robot robustness and environmental safety. By uniting responsive materials, structural co-design, and learning-based control, this work advances interact-safe, industry-ready humanoid robots.
comment: 40 pages, 11 figures
☆ Reinforcement Learning for Follow-the-Leader Robotic Endoscopic Navigation via Synthetic Data
Autonomous navigation is crucial for both medical and industrial endoscopic robots, enabling safe and efficient exploration of narrow tubular environments without continuous human intervention, where avoiding contact with the inner walls has been a longstanding challenge for prior approaches. We present a follow-the-leader endoscopic robot based on a flexible continuum structure designed to minimize contact between the endoscope body and intestinal walls, thereby reducing patient discomfort. To achieve this objective, we propose a vision-based deep reinforcement learning framework guided by monocular depth estimation. A realistic intestinal simulation environment was constructed in \textit{NVIDIA Omniverse} to train and evaluate autonomous navigation strategies. Furthermore, thousands of synthetic intraluminal images were generated using NVIDIA Replicator to fine-tune the Depth Anything model, enabling dense three-dimensional perception of the intestinal environment with a single monocular camera. Subsequently, we introduce a geometry-aware reward and penalty mechanism to enable accurate lumen tracking. Compared with the original Depth Anything model, our method improves $δ_{1}$ depth accuracy by 39.2% and reduces the navigation J-index by 0.67 relative to the second-best method, demonstrating the robustness and effectiveness of the proposed approach.
☆ Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation
Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities, but training control policies that can directly deploy on real hardware remains difficult due to contact-rich physics and imperfect actuation. We close this gap with a practical sim-to-real reinforcement learning (RL) framework that utilizes dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective sim-to-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling to bridge the actuation gaps with randomization of non-ideal effects such as backlash, torque-speed saturation. Using an asymmetric actor-critic PPO pipeline trained entirely in simulation, our policies deploy directly to a five-finger hand. The resulting policies demonstrated two essential skills: (1) command-based, controllable grasp force tracking, and (2) reorientation of objects in the hand, both of which were robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with effective sensing/actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.
☆ M-SEVIQ: A Multi-band Stereo Event Visual-Inertial Quadruped-based Dataset for Perception under Rapid Motion and Challenging Illumination
Agile locomotion in legged robots poses significant challenges for visual perception. Traditional frame-based cameras often fail in these scenarios for producing blurred images, particularly under low-light conditions. In contrast, event cameras capture changes in brightness asynchronously, offering low latency, high temporal resolution, and high dynamic range. These advantages make them suitable for robust perception during rapid motion and under challenging illumination. However, existing event camera datasets exhibit limitations in stereo configurations and multi-band sensing domains under various illumination conditions. To address this gap, we present M-SEVIQ, a multi-band stereo event visual and inertial quadruped dataset collected using a Unitree Go2 equipped with stereo event cameras, a frame-based camera, an inertial measurement unit (IMU), and joint encoders. This dataset contains more than 30 real-world sequences captured across different velocity levels, illumination wavelengths, and lighting conditions. In addition, comprehensive calibration data, including intrinsic, extrinsic, and temporal alignments, are provided to facilitate accurate sensor fusion and benchmarking. Our M-SEVIQ can be used to support research in agile robot perception, sensor fusion, semantic segmentation and multi-modal vision in challenging environments.
comment: 6 pages, 7 figures
☆ Advancing Assistive Robotics: Multi-Modal Navigation and Biophysical Monitoring for Next-Generation Wheelchairs
Assistive electric-powered wheelchairs (EPWs) have become essential mobility aids for people with disabilities such as amyotrophic lateral sclerosis (ALS), post-stroke hemiplegia, and dementia-related mobility impairment. This work presents a novel multi-modal EPW control system designed to prioritize patient needs while allowing seamless switching between control modes. Four complementary interfaces, namely joystick, speech, hand gesture, and electrooculography (EOG), are integrated with a continuous vital sign monitoring framework measuring heart rate variability, oxygen saturation (SpO2), and skin temperature. This combination enables greater patient independence while allowing caregivers to maintain real-time supervision and early intervention capability. Two-point calibration of the biophysical sensors against clinical reference devices resulted in root mean square errors of at most 2 bpm for heart rate, 0.5 degree Celsius for skin temperature, and 1 percent for SpO2. Experimental evaluation involved twenty participants with mobility impairments executing a total of 500 indoor navigation commands. The achieved command recognition accuracies were 99 percent for joystick control, 97 percent plus or minus 2 percent for speech, and 95 percent plus or minus 3 percent for hand gesture, with an average closed-loop latency of 20 plus or minus 0.5 milliseconds. Caregivers receive real-time alerts through an Android application following encrypted cloud transmission of physiological data. By integrating multi-modal mobility control with cloud-enabled health monitoring and reporting latency and energy budgets, the proposed prototype addresses key challenges in assistive robotics, contributes toward compliance with ISO 7176-31 and IEC 80601-2-78 safety standards, and establishes a foundation for future adaptive machine learning enhancements.
☆ Unified Meta-Representation and Feedback Calibration for General Disturbance Estimation
Precise control in modern robotic applications is always an open issue due to unknown time-varying disturbances. Existing meta-learning-based approaches require a shared representation of environmental structures, which lack flexibility for realistic non-structural disturbances. Besides, representation error and the distribution shifts can lead to heavy degradation in prediction accuracy. This work presents a generalizable disturbance estimation framework that builds on meta-learning and feedback-calibrated online adaptation. By extracting features from a finite time window of past observations, a unified representation that effectively captures general non-structural disturbances can be learned without predefined structural assumptions. The online adaptation process is subsequently calibrated by a state-feedback mechanism to attenuate the learning residual originating from the representation and generalizability limitations. Theoretical analysis shows that simultaneous convergence of both the online learning error and the disturbance estimation error can be achieved. Through the unified meta-representation, our framework effectively estimates multiple rapidly changing disturbances, as demonstrated by quadrotor flight experiments. See the project page for video, supplementary material and code: https://nonstructural-metalearn.github.io.
comment: 8 pages, 10 figures
☆ Towards Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups ICCV 2025
Some deep learning-based point cloud registration methods struggle with zero-shot generalization, often requiring dataset-specific hyperparameter tuning or retraining for new environments. We identify three critical limitations: (a) fixed user-defined parameters (e.g., voxel size, search radius) that fail to generalize across varying scales, (b) learned keypoint detectors exhibit poor cross-domain transferability, and (c) absolute coordinates amplify scale mismatches between datasets. To address these three issues, we present BUFFER-X, a training-free registration framework that achieves zero-shot generalization through: (a) geometric bootstrapping for automatic hyperparameter estimation, (b) distribution-aware farthest point sampling to replace learned detectors, and (c) patch-level coordinate normalization to ensure scale consistency. Our approach employs hierarchical multi-scale matching to extract correspondences across local, middle, and global receptive fields, enabling robust registration in diverse environments. For efficiency-critical applications, we introduce BUFFER-X-Lite, which reduces total computation time by 43% (relative to BUFFER-X) through early exit strategies and fast pose solvers while preserving accuracy. We evaluate on a comprehensive benchmark comprising 12 datasets spanning object-scale, indoor, and outdoor scenes, including cross-sensor registration between heterogeneous LiDAR configurations. Results demonstrate that our approach generalizes effectively without manual tuning or prior knowledge of test domains. Code: https://github.com/MIT-SPARK/BUFFER-X.
comment: 18 pages, 15 figures. Extended version of our ICCV 2025 highlight paper [arXiv:2503.07940]. arXiv admin note: substantial text overlap with arXiv:2503.07940
☆ Optimizing Control-Friendly Trajectories with Self-Supervised Residual Learning
Real-world physics can only be analytically modeled with a certain level of precision for modern intricate robotic systems. As a result, tracking aggressive trajectories accurately could be challenging due to the existence of residual physics during controller synthesis. This paper presents a self-supervised residual learning and trajectory optimization framework to address the aforementioned challenges. At first, unknown dynamic effects on the closed-loop model are learned and treated as residuals of the nominal dynamics, jointly forming a hybrid model. We show that learning with analytic gradients can be achieved using only trajectory-level data while enjoying accurate long-horizon prediction with an arbitrary integration step size. Subsequently, a trajectory optimizer is developed to compute the optimal reference trajectory with the residual physics along it minimized. It ends up with trajectories that are friendly to the following control level. The agile flight of quadrotors illustrates that by utilizing the hybrid dynamics, the proposed optimizer outputs aggressive motions that can be precisely tracked.
comment: 10 pages, 9 figures
☆ Loop Closure using AnyLoc Visual Place Recognition in DPV-SLAM
Loop closure is crucial for maintaining the accuracy and consistency of visual SLAM. We propose a method to improve loop closure performance in DPV-SLAM. Our approach integrates AnyLoc, a learning-based visual place recognition technique, as a replacement for the classical Bag of Visual Words (BoVW) loop detection method. In contrast to BoVW, which relies on handcrafted features, AnyLoc utilizes deep feature representations, enabling more robust image retrieval across diverse viewpoints and lighting conditions. Furthermore, we propose an adaptive mechanism that dynamically adjusts similarity threshold based on environmental conditions, removing the need for manual tuning. Experiments on both indoor and outdoor datasets demonstrate that our method significantly outperforms the original DPV-SLAM in terms of loop closure accuracy and robustness. The proposed method offers a practical and scalable solution for enhancing loop closure performance in modern SLAM systems.
comment: Accepted at IEEE/SICE International Symposium on System Integration(SII) 2026. 6 pages, 14 figures
☆ Analysis of Various Manipulator Configurations Based on Multi-Objective Black-Box Optimization
Various 6-degree-of-freedom (DOF) and 7-DOF manipulators have been developed to date. Over a long history, their joint configurations and link length ratios have been determined empirically. In recent years, the development of robotic foundation models has become increasingly active, leading to the continuous proposal of various manipulators to support these models. However, none of these manipulators share exactly the same structure, as the order of joints and the ratio of link lengths differ among robots. Therefore, in order to discuss the optimal structure of a manipulator, we performed multi-objective optimization from the perspectives of end-effector reachability and joint torque. We analyze where existing manipulator structures stand within the sampling results of the optimization and provide insights for future manipulator design.
comment: Accepted to Advanced Robotics, website: https://haraduka.github.io/bbo-manip-design
☆ Learning to Nudge: A Scalable Barrier Function Framework for Safe Robot Interaction in Dense Clutter
Robots operating in everyday environments must navigate and manipulate within densely cluttered spaces, where physical contact with surrounding objects is unavoidable. Traditional safety frameworks treat contact as unsafe, restricting robots to collision avoidance and limiting their ability to function in dense, everyday settings. As the number of objects grows, model-based approaches for safe manipulation become computationally intractable; meanwhile, learned methods typically tie safety to the task at hand, making them hard to transfer to new tasks without retraining. In this work we introduce Dense Contact Barrier Functions(DCBF). Our approach bypasses the computational complexity of explicitly modeling multi-object dynamics by instead learning a composable, object-centric function that implicitly captures the safety constraints arising from physical interactions. Trained offline on interactions with a few objects, the learned DCBFcomposes across arbitrary object sets at runtime, producing a single global safety filter that scales linearly and transfers across tasks without retraining. We validate our approach through simulated experiments in dense clutter, demonstrating its ability to enable collision-free navigation and safe, contact-rich interaction in suitable settings.
☆ CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception
We present CageDroneRF (CDRF), a large-scale benchmark for Radio-Frequency (RF) drone detection and identification built from real-world captures and systematically generated synthetic variants. CDRF addresses the scarcity and limited diversity of existing RF datasets by coupling extensive raw recordings with a principled augmentation pipeline that (i) precisely controls Signal-to-Noise Ratio (SNR), (ii) injects interfering emitters, and (iii) applies frequency shifts with label-consistent bounding-box transformations for detection. This dataset spans a wide range of contemporary drone models, many unavailable in current public datasets, and acquisition conditions, derived from data collected at the Rowan University campus and within a controlled RF-cage facility. CDRF is released with interoperable open-source tools for data generation, preprocessing, augmentation, and evaluation that also operate on existing public benchmarks. CDRF enables standardized benchmarking for classification, open-set recognition, and object detection, supporting rigorous comparisons and reproducible pipelines. By releasing this comprehensive benchmark and tooling, CDRF aims to accelerate progress toward robust, generalizable RF perception models.
☆ Effective Online 3D Bin Packing with Lookahead Parcels Using Monte Carlo Tree Search
Online 3D Bin Packing (3D-BP) with robotic arms is crucial for reducing transportation and labor costs in modern logistics. While Deep Reinforcement Learning (DRL) has shown strong performance, it often fails to adapt to real-world short-term distribution shifts, which arise as different batches of goods arrive sequentially, causing performance drops. We argue that the short-term lookahead information available in modern logistics systems is key to mitigating this issue, especially during distribution shifts. We formulate online 3D-BP with lookahead parcels as a Model Predictive Control (MPC) problem and adapt the Monte Carlo Tree Search (MCTS) framework to solve it. Our framework employs a dynamic exploration prior that automatically balances a learned RL policy and a robust random policy based on the lookahead characteristics. Additionally, we design an auxiliary reward to penalize long-term spatial waste from individual placements. Extensive experiments on real-world datasets show that our method consistently outperforms state-of-the-art baselines, achieving over 10\% gains under distributional shifts, 4\% average improvement in online deployment, and up to more than 8\% in the best case--demonstrating the effectiveness of our framework.
☆ Making Infeasible Tasks Feasible: Planning to Reconfigure Disconnected 3D Environments with Movable Objects
Several planners have been developed to compute dynamically feasible, collision-free robot paths from an initial to a goal configuration. A key assumption in these works is that the goal region is reachable; an assumption that often fails in practice when environments are disconnected. Motivated by this limitation, we consider known 3D environments comprising objects, also called blocks, that form distinct navigable support surfaces (planes), and that are either non-movable (e.g., tables) or movable (e.g., boxes). These surfaces may be mutually disconnected due to height differences, holes, or lateral separations. Our focus is on tasks where the robot must reach a goal region residing on an elevated plane that is unreachable. Rather than declaring such tasks infeasible, an effective strategy is to enable the robot to interact with the environment, rearranging movable objects to create new traversable connections; a problem known as Navigation Among Movable Objects (NAMO). Existing NAMO planners typically address 2D environments, where obstacles are pushed aside to clear a path. These methods cannot directly handle the considered 3D setting; in such cases, obstacles must be placed strategically to bridge these physical disconnections. We address this challenge by developing BRiDGE (Block-based Reconfiguration in Disconnected 3D Geometric Environments), a sampling-based planner that incrementally builds trees over robot and object configurations to compute feasible plans specifying which objects to move, where to place them, and in what order, while accounting for a limited number of movable objects. To accelerate planning, we introduce non-uniform sampling strategies. We show that our method is probabilistically complete and we provide extensive numerical and hardware experiments validating its effectiveness.
♻ ☆ Characterizing the Robustness of Black-Box LLM Planners Under Perturbed Observations with Adaptive Stress Testing
Large language models (LLMs) have recently demonstrated success in decision-making tasks including planning, control, and prediction, but their tendency to hallucinate unsafe and undesired outputs poses risks. This unwanted behavior is further exacerbated in environments where sensors are noisy or unreliable. Characterizing the behavior of LLM planners to varied observations is necessary to proactively avoid failures in safety-critical scenarios. We specifically investigate the response of LLMs along two different perturbation dimensions. Like prior works, one dimension generates semantically similar prompts with varied phrasing by randomizing order of details, modifying access to few-shot examples, etc. Unique to our work, the second dimension simulates access to varied sensors and noise to mimic raw sensor or detection algorithm failures. An initial case study in which perturbations are manually applied show that both dimensions lead LLMs to hallucinate in a multi-agent driving environment. However, manually covering the entire perturbation space for several scenarios is infeasible. As such, we propose a novel method for efficiently searching the space of prompt perturbations using adaptive stress testing (AST) with Monte-Carlo tree search (MCTS). Our AST formulation enables discovery of scenarios, sensor configurations, and prompt phrasing that cause language models to act with high uncertainty or even crash. By generating MCTS prompt perturbation trees across diverse scenarios, we show through extensive experiments that offline analyses can be used to proactively understand potential failures that may arise at runtime.
comment: 30 pages, 24 figures, 6 tables
♻ ☆ Indicating Robot Vision Capabilities with Augmented Reality
Research indicates that humans can mistakenly assume that robots and humans have the same field of view, possessing an inaccurate mental model of robots. This misperception may lead to failures during human-robot collaboration tasks where robots might be asked to complete impossible tasks about out-of-view objects. The issue is more severe when robots do not have a chance to scan the scene to update their world model while focusing on assigned tasks. To help align humans' mental models of robots' vision capabilities, we propose four field-of-view indicators in augmented reality and conducted a human-subjects experiment (N=41) to evaluate them in a collaborative assembly task regarding accuracy, confidence, task efficiency, and workload. These indicators span a spectrum of positions: two at robot's eye and head space -- deepening eye socket and adding blocks to two sides of the eyes (i.e., egocentric), and two anchoring in the robot's task space -- adding extended blocks from the sides of eyes to the table and placing blocks directly on the tables (i.e., allocentric). Results showed that, when placed directly in the task space, the allocentric indicator yields the highest accuracy, although with a delay in interpreting the robot's field of view. When placed at the robot's eyes, the egocentric indicator of deeper eye sockets, possible for physical alteration, also increased accuracy. In all indicators, participants' confidence was high while cognitive load remained low. Finally, we contribute six guidelines for practitioners to apply our augmented reality indicators or physical alterations to align humans' mental models with robots' vision capabilities.
♻ ☆ FICO: Finite-Horizon Closed-Loop Factorization for Unified Multi-Agent Path Finding
Multi-Agent Path Finding is a fundamental problem in robotics and AI, yet most existing formulations treat planning and execution separately and address variants of the problem in an ad hoc manner. This paper presents a system-level framework for MAPF that integrates planning and execution, generalizes across variants, and explicitly models uncertainties. At its core is the MAPF system, a formal model that casts MAPF as a control design problem encompassing classical and uncertainty-aware formulations. To solve it, we introduce Finite-Horizon Closed-Loop Factorization (FICO), a factorization-based algorithm inspired by receding-horizon control that exploits compositional structure for efficient closed-loop operation. FICO enables real-time responses -- commencing execution within milliseconds -- while scaling to thousands of agents and adapting seamlessly to execution-time uncertainties. Extensive case studies demonstrate that it reduces computation time by up to two orders of magnitude compared with open-loop baselines, while delivering significantly higher throughput under stochastic delays and agent arrivals. These results establish a principled foundation for analyzing and advancing MAPF through system-level modeling, factorization, and closed-loop design.
♻ ☆ Evaluating Gemini Robotics Policies in a Veo World Simulator
Generative world models hold significant potential for simulating interactions with visuomotor policies in varied environments. Frontier video models can enable generation of realistic observations and environment interactions in a scalable and general manner. However, the use of video models in robotics has been limited primarily to in-distribution evaluations, i.e., scenarios that are similar to ones used to train the policy or fine-tune the base video model. In this report, we demonstrate that video models can be used for the entire spectrum of policy evaluation use cases in robotics: from assessing nominal performance to out-of-distribution (OOD) generalization, and probing physical and semantic safety. We introduce a generative evaluation system built upon a frontier video foundation model (Veo). The system is optimized to support robot action conditioning and multi-view consistency, while integrating generative image-editing and multi-view completion to synthesize realistic variations of real-world scenes along multiple axes of generalization. We demonstrate that the system preserves the base capabilities of the video model to enable accurate simulation of scenes that have been edited to include novel interaction objects, novel visual backgrounds, and novel distractor objects. This fidelity enables accurately predicting the relative performance of different policies in both nominal and OOD conditions, determining the relative impact of different axes of generalization on policy performance, and performing red teaming of policies to expose behaviors that violate physical or semantic safety constraints. We validate these capabilities through 1600+ real-world evaluations of eight Gemini Robotics policy checkpoints and five tasks for a bimanual manipulator.
♻ ☆ DDBot: Differentiable Physics-based Digging Robot for Unknown Granular Materials
Automating the manipulation of granular materials poses significant challenges due to complex contact dynamics, unpredictable material properties, and intricate system states. Existing approaches often fail to achieve efficiency and accuracy in such tasks. To fill the research gap, this article studies the small-scale and high-precision granular material digging task with unknown physical properties. A key scientific problem addressed is the feasibility of applying first-order gradient-based optimization to complex differentiable granular material simulation and overcoming associated numerical instability. A new framework, named differentiable digging robot (DDBot), is proposed to manipulate granular materials, including sand and soil. Specifically, we equip DDBot with a differentiable physics-based simulator, tailored for granular material manipulation, powered by GPU-accelerated parallel computing and automatic differentiation. DDBot can perform efficient differentiable system identification and high-precision digging skill optimization for unknown granular materials, which is enabled by a differentiable skill-to-action mapping, a task-oriented demonstration method, gradient clipping and line search-based gradient descent. Experimental results show that DDBot can efficiently (converge within 5 to 20 minutes) identify unknown granular material dynamics and optimize digging skills, with high-precision results in zero-shot real-world deployments, highlighting its practicality. Benchmark results against state-of-the-art baselines also confirm the robustness and efficiency of DDBot in such digging tasks.
comment: Published as a regular paper by the IEEE Transactions on Robotics
♻ ☆ An Informative Planning Framework for Target Tracking and Active Mapping in Dynamic Environments with ASVs
Mobile robot platforms are increasingly being used to automate information gathering tasks such as environmental monitoring. Efficient target tracking in dynamic environments is critical for applications such as search and rescue and pollutant cleanups. In this letter, we study active mapping of floating targets that drift due to environmental disturbances such as wind and currents. This is a challenging problem as it involves predicting both spatial and temporal variations in the map due to changing conditions. We introduce an integrated framework combining dynamic occupancy grid mapping and an informative planning approach to actively map and track freely drifting targets with an autonomous surface vehicle. A key component of our adaptive planning approach is a spatiotemporal prediction network that predicts target position distributions over time. We further propose a planning objective for target tracking that leverages these predictions. Simulation experiments show that this planning objective improves target tracking performance compared to existing methods that consider only entropy reduction as the planning objective. Finally, we validate our approach in field tests, showcasing its ability to track targets in real-world monitoring scenarios.
comment: Accepted for publication in Robotics and Automation Letters (RA-L)
♻ ☆ Augmented Reality for RObots (ARRO): Pointing Visuomotor Policies Towards Visual Robustness
Visuomotor policies trained on human expert demonstrations have recently shown strong performance across a wide range of robotic manipulation tasks. However, these policies remain highly sensitive to domain shifts stemming from background or robot embodiment changes, which limits their generalization capabilities. In this paper, we present ARRO, a novel visual representation that leverages zero-shot open-vocabulary segmentation and object detection models to efficiently mask out task-irrelevant regions of the scene in real time without requiring additional training, modeling of the setup, or camera calibration. By filtering visual distractors and overlaying virtual guides during both training and inference, ARRO improves robustness to scene variations and reduces the need for additional data collection. We extensively evaluate ARRO with Diffusion Policy on a range of tabletop manipulation tasks in both simulation and real-world environments, and further demonstrate its compatibility and effectiveness with generalist robot policies, such as Octo, OpenVLA and Pi Zero. Across all settings in our evaluation, ARRO yields consistent performance gains, allows for selective masking to choose between different objects, and shows robustness even to challenging segmentation conditions. Videos showcasing our results are available at: https://augmented-reality-for-robots.github.io/
♻ ☆ RobotDiffuse: Diffusion-Based Motion Planning for Redundant Manipulators with the ROP Obstacle Avoidance Dataset
Redundant manipulators, with their higher Degrees of Freedom (DoFs), offer enhanced kinematic performance and versatility, making them suitable for applications like manufacturing, surgical robotics, and human-robot collaboration. However, motion planning for these manipulators is challenging due to increased DoFs and complex, dynamic environments. While traditional motion planning algorithms struggle with high-dimensional spaces, deep learning-based methods often face instability and inefficiency in complex tasks. This paper introduces RobotDiffuse, a diffusion model-based approach for motion planning in redundant manipulators. By integrating physical constraints with a point cloud encoder and replacing the U-Net structure with an encoder-only transformer, RobotDiffuse improves the model's ability to capture temporal dependencies and generate smoother, more coherent motion plans. We validate the approach using a complex simulator and release a new dataset, Robot-obtalcles-panda (ROP), with 35M robot poses and 0.14M obstacle avoidance scenarios. The highest overall score obtained in the experiment demonstrates the effectiveness of RobotDiffuse and the promise of diffusion models for motion planning tasks. The dataset can be accessed at https://github.com/ACRoboT-buaa/RobotDiffuse.
♻ ☆ VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a wide range of vision-language tasks. However, their performance as embodied agents, which requires multi-round dialogue spatial reasoning and sequential action prediction, needs further exploration. Our work investigates this potential in the context of Vision-and-Language Navigation (VLN) by introducing a unified and extensible evaluation framework to probe MLLMs as zero-shot agents by bridging traditional navigation datasets into a standardized benchmark, named VLN-MME. We simplify the evaluation with a highly modular and accessible design. This flexibility streamlines experiments, enabling structured comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks. Crucially, enabled by our framework, we observe that enhancing our baseline agent with Chain-of-Thought (CoT) reasoning and self-reflection leads to an unexpected performance decrease. This suggests MLLMs exhibit poor context awareness in embodied navigation tasks; although they can follow instructions and structure their output, their 3D spatial reasoning fidelity is low. VLN-MME lays the groundwork for systematic evaluation of general-purpose MLLMs in embodied navigation settings and reveals limitations in their sequential decision-making capabilities. We believe these findings offer crucial guidance for MLLM post-training as embodied agents.
♻ ☆ Steering Flexible Linear Objects in Planar Environments by Two Robot Hands Using Euler's Elastica Solutions
The manipulation of flexible objects such as cables, wires and fresh food items by robot hands forms a special challenge in robot grasp mechanics. This paper considers the steering of flexible linear objects in planar environments by two robot hands. The flexible linear object, modeled as an elastic non-stretchable rod, is manipulated by varying the gripping endpoint positions while keeping equal endpoint tangents. The flexible linear object shape has a closed form solution in terms of the grasp endpoint positions and tangents, called Euler's elastica. This paper obtains the elastica solutions under the optimal control framework, then uses the elastica solutions to obtain closed-form criteria for non self-intersection, stability and obstacle avoidance of the flexible linear object. The new tools are incorporated into a planning scheme for steering flexible linear objects in planar environments populated by sparsely spaced obstacles. The scheme is fully implemented and demonstrated with detailed examples.
♻ ☆ Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation
We present Chain-of-Action (CoA), a novel visuo-motor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuo-motor policy. Empirically, we observe CoA achieves the state-of-the-art performance across 60 RLBench tasks and 8 real-world manipulation tasks.
♻ ☆ Efficient Swept Volume-Based Trajectory Generation for Arbitrary-Shaped Ground Robot Navigation
Navigating an arbitrary-shaped ground robot safely in cluttered environments remains a challenging problem. The existing trajectory planners that account for the robot's physical geometry severely suffer from the intractable runtime. To achieve both computational efficiency and Continuous Collision Avoidance (CCA) of arbitrary-shaped ground robot planning, we proposed a novel coarse-to-fine navigation framework that significantly accelerates planning. In the first stage, a sampling-based method selectively generates distinct topological paths that guarantee a minimum inflated margin. In the second stage, a geometry-aware front-end strategy is designed to discretize these topologies into full-state robot motion sequences while concurrently partitioning the paths into SE(2) sub-problems and simpler R2 sub-problems for back-end optimization. In the final stage, an SVSDF-based optimizer generates trajectories tailored to these sub-problems and seamlessly splices them into a continuous final motion plan. Extensive benchmark comparisons show that the proposed method is one to several orders of magnitude faster than the cutting-edge methods in runtime while maintaining a high planning success rate and ensuring CCA.
♻ ☆ RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence
While data-driven imitation learning has revolutionized robotic manipulation, current approaches remain constrained by the scarcity of large-scale, diverse real-world demonstrations. Consequently, the ability of existing models to generalize across long-horizon bimanual tasks and mobile manipulation in unstructured environments remains limited. To bridge this gap, we present RoboMIND 2.0, a comprehensive real-world dataset comprising over 310K dual-arm manipulation trajectories collected across six distinct robot embodiments and 739 complex tasks. Crucially, to support research in contact-rich and spatially extended tasks, the dataset incorporates 12K tactile-enhanced episodes and 20K mobile manipulation trajectories. Complementing this physical data, we construct high-fidelity digital twins of our real-world environments, releasing an additional 20K-trajectory simulated dataset to facilitate robust sim-to-real transfer. To fully exploit the potential of RoboMIND 2.0, we propose MIND-2 system, a hierarchical dual-system frame-work optimized via offline reinforcement learning. MIND-2 integrates a high-level semantic planner (MIND-2-VLM) to decompose abstract natural language instructions into grounded subgoals, coupled with a low-level Vision-Language-Action executor (MIND-2-VLA), which generates precise, proprioception-aware motor actions.
♻ ☆ RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics
Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reasoning via reinforcement fine-tuning (RFT) with metric-sensitive process rewards, supervising key intermediate perceptual cues to accurately generate spatial traces. To support SFT and RFT training, we introduce TraceSpatial, a large-scale dataset of 30M QA pairs, spanning outdoor/indoor/tabletop scenes and supporting complex reasoning processes (up to 9 steps). We further present TraceSpatial-Bench, a challenging benchmark filling the gap to evaluate spatial tracing. Experimental results show that RoboTracer surpasses baselines in spatial understanding, measuring, and referring, with an average success rate of 79.1%, and also achieves SOTA performance on TraceSpatial-Bench by a large margin, exceeding Gemini-2.5-Pro by 36% accuracy. Notably, RoboTracer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (UR5, G1 humanoid) in cluttered real-world scenes. See the project page at https://zhoues.github.io/RoboTracer.
comment: Project page: https://zhoues.github.io/RoboTracer
♻ ☆ AdaVLN: Towards Visual Language Navigation in Continuous Indoor Environments with Moving Humans
Visual Language Navigation is a task that challenges robots to navigate in realistic environments based on natural language instructions. While previous research has largely focused on static settings, real-world navigation must often contend with dynamic human obstacles. Hence, we propose an extension to the task, termed Adaptive Visual Language Navigation (AdaVLN), which seeks to narrow this gap. AdaVLN requires robots to navigate complex 3D indoor environments populated with dynamically moving human obstacles, adding a layer of complexity to navigation tasks that mimic the real-world. To support exploration of this task, we also present AdaVLN simulator and AdaR2R datasets. The AdaVLN simulator enables easy inclusion of fully animated human models directly into common datasets like Matterport3D. We also introduce a "freeze-time" mechanism for both the navigation task and simulator, which pauses world state updates during agent inference, enabling fair comparisons and experimental reproducibility across different hardware. We evaluate several baseline models on this task, analyze the unique challenges introduced by AdaVLN, and demonstrate its potential to bridge the sim-to-real gap in VLN research.
♻ ☆ DarkEQA: Benchmarking Vision-Language Models for Embodied Question Answering in Low-Light Indoor Environments
Vision Language Models (VLMs) are increasingly adopted as central reasoning modules for embodied agents. Existing benchmarks evaluate their capabilities under ideal, well-lit conditions, yet robust 24/7 operation demands performance under a wide range of visual degradations, including low-light conditions at night or in dark environments--a core necessity that has been largely overlooked. To address this underexplored challenge, we present DarkEQA, an open-source benchmark for evaluating EQA-relevant perceptual primitives under multi-level low-light conditions. DarkEQA isolates the perception bottleneck by evaluating question answering from egocentric observations under controlled degradations, enabling attributable robustness analysis. A key design feature of DarkEQA is its physical fidelity: visual degradations are modeled in linear RAW space, simulating physics-based illumination drop and sensor noise followed by an ISP-inspired rendering pipeline. We demonstrate the utility of DarkEQA by evaluating a wide range of state-of-the-art VLMs and Low-Light Image Enhancement (LLIE) models. Our analysis systematically reveals VLMs' limitations when operating under these challenging visual conditions. Project website: https://darkeqa-benchmark.github.io/
comment: Submitted to IEEE Robotics and Automation Letters (RA-L)
Robotics 33
☆ CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding
Current work on robot failure detection and correction typically operate in a post hoc manner, analyzing errors and applying corrections only after failures occur. This work introduces CycleVLA, a system that equips Vision-Language-Action models (VLAs) with proactive self-correction, the capability to anticipate incipient failures and recover before they fully manifest during execution. CycleVLA achieves this by integrating a progress-aware VLA that flags critical subtask transition points where failures most frequently occur, a VLM-based failure predictor and planner that triggers subtask backtracking upon predicted failure, and a test-time scaling strategy based on Minimum Bayes Risk (MBR) decoding to improve retry success after backtracking. Extensive experiments show that CycleVLA improves performance for both well-trained and under-trained VLAs, and that MBR serves as an effective zero-shot test-time scaling strategy for VLAs. Project Page: https://dannymcy.github.io/cyclevla/
comment: Project Page: https://dannymcy.github.io/cyclevla/
☆ Differential Barometric Altimetry for Submeter Vertical Localization and Floor Recognition Indoors
Accurate altitude estimation and reliable floor recognition are critical for mobile robot localization and navigation within complex multi-storey environments. In this paper, we present a robust, low-cost vertical estimation framework leveraging differential barometric sensing integrated within a fully ROS-compliant software package. Our system simultaneously publishes real-time altitude data from both a stationary base station and a mobile sensor, enabling precise and drift-free vertical localization. Empirical evaluations conducted in challenging scenarios -- such as fully enclosed stairwells and elevators, demonstrate that our proposed barometric pipeline achieves sub-meter vertical accuracy (RMSE: 0.29 m) and perfect (100%) floor-level identification. In contrast, our results confirm that standalone height estimates, obtained solely from visual- or LiDAR-based SLAM odometry, are insufficient for reliable vertical localization. The proposed ROS-compatible barometric module thus provides a practical and cost-effective solution for robust vertical awareness in real-world robotic deployments. The implementation of our method is released as open source at https://github.com/witsir/differential-barometric.
☆ SingingBot: An Avatar-Driven System for Robotic Face Singing Performance
Equipping robotic faces with singing capabilities is crucial for empathetic Human-Robot Interaction. However, existing robotic face driving research primarily focuses on conversations or mimicking static expressions, struggling to meet the high demands for continuous emotional expression and coherence in singing. To address this, we propose a novel avatar-driven framework for appealing robotic singing. We first leverage portrait video generation models embedded with extensive human priors to synthesize vivid singing avatars, providing reliable expression and emotion guidance. Subsequently, these facial features are transferred to the robot via semantic-oriented mapping functions that span a wide expression space. Furthermore, to quantitatively evaluate the emotional richness of robotic singing, we propose the Emotion Dynamic Range metric to measure the emotional breadth within the Valence-Arousal space, revealing that a broad emotional spectrum is crucial for appealing performances. Comprehensive experiments prove that our method achieves rich emotional expressions while maintaining lip-audio synchronization, significantly outperforming existing approaches.
☆ Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots
Strawberry harvesting robots faced persistent challenges such as low integration of visual perception, fruit-gripper misalignment, empty grasping, and strawberry slippage from the gripper due to insufficient gripping force, all of which compromised harvesting stability and efficiency in orchard environments. To overcome these issues, this paper proposed a visual fault diagnosis and self-recovery framework that integrated multi-task perception with corrective control strategies. At the core of this framework was SRR-Net, an end-to-end multi-task perception model that simultaneously performed strawberry detection, segmentation, and ripeness estimation, thereby unifying visual perception with fault diagnosis. Based on this integrated perception, a relative error compensation method based on the simultaneous target-gripper detection was designed to address positional misalignment, correcting deviations when error exceeded the tolerance threshold. To mitigate empty grasping and fruit-slippage faults, an early abort strategy was implemented. A micro-optical camera embedded in the end-effector provided real-time visual feedback, enabling grasp detection during the deflating stage and strawberry slip prediction during snap-off through MobileNet V3-Small classifier and a time-series LSTM classifier. Experiments demonstrated that SRR-Net maintained high perception accuracy. For detection, it achieved a precision of 0.895 and recall of 0.813 on strawberries, and 0.972/0.958 on hands. In segmentation, it yielded a precision of 0.887 and recall of 0.747 for strawberries, and 0.974/0.947 for hands. For ripeness estimation, SRR-Net attained a mean absolute error of 0.035, while simultaneously supporting multi-task perception and sustaining a competitive inference speed of 163.35 FPS.
☆ Realistic adversarial scenario generation via human-like pedestrian model for autonomous vehicle control parameter optimisation
Autonomous vehicles (AVs) are rapidly advancing and are expected to play a central role in future mobility. Ensuring their safe deployment requires reliable interaction with other road users, not least pedestrians. Direct testing on public roads is costly and unsafe for rare but critical interactions, making simulation a practical alternative. Within simulation-based testing, adversarial scenarios are widely used to probe safety limits, but many prioritise difficulty over realism, producing exaggerated behaviours which may result in AV controllers that are overly conservative. We propose an alternative method, instead using a cognitively inspired pedestrian model featuring both inter-individual and intra-individual variability to generate behaviourally plausible adversarial scenarios. We provide a proof of concept demonstration of this method's potential for AV control optimisation, in closed-loop testing and tuning of an AV controller. Our results show that replacing the rule-based CARLA pedestrian with the human-like model yields more realistic gap acceptance patterns and smoother vehicle decelerations. Unsafe interactions occur only for certain pedestrian individuals and conditions, underscoring the importance of human variability in AV testing. Adversarial scenarios generated by this model can be used to optimise AV control towards safer and more efficient behaviour. Overall, this work illustrates how incorporating human-like road user models into simulation-based adversarial testing can enhance the credibility of AV evaluation and provide a practical basis to behaviourally informed controller optimisation.
☆ Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot
The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training data and reliable evaluation benchmarks. Collecting data in the physical world poses prohibitive costs and scalability challenges, and prevailing simulation benchmarks frequently suffer from fragmentation, narrow scope, or insufficient fidelity to enable effective sim-to-real transfer. To address these challenges, we introduce Genie Sim 3.0, a unified simulation platform for robotic manipulation. We present Genie Sim Generator, a large language model (LLM)-powered tool that constructs high-fidelity scenes from natural language instructions. Its principal strength resides in rapid and multi-dimensional generalization, facilitating the synthesis of diverse environments to support scalable data collection and robust policy evaluation. We introduce the first benchmark that pioneers the application of LLM for automated evaluation. It leverages LLM to mass-generate evaluation scenarios and employs Vision-Language Model (VLM) to establish an automated assessment pipeline. We also release an open-source dataset comprising more than 10,000 hours of synthetic data across over 200 tasks. Through systematic experimentation, we validate the robust zero-shot sim-to-real transfer capability of our open-source dataset, demonstrating that synthetic data can server as an effective substitute for real-world data under controlled conditions for scalable policy training. For code and dataset details, please refer to: https://github.com/AgibotTech/genie_sim.
☆ VIT-Ped: Visionary Intention Transformer for Pedestrian Behavior Analysis
Pedestrian Intention prediction is one of the key technologies in the transition from level 3 to level 4 autonomous driving. To understand pedestrian crossing behaviour, several elements and features should be taken into consideration to make the roads of tomorrow safer for everybody. We introduce a transformer / video vision transformer based algorithm of different sizes which uses different data modalities .We evaluated our algorithms on popular pedestrian behaviour dataset, JAAD, and have reached SOTA performance and passed the SOTA in metrics like Accuracy, AUC and F1-score. The advantages brought by different model design choices are investigated via extensive ablation studies.
☆ Deep Robust Koopman Learning from Noisy Data
Koopman operator theory has emerged as a leading data-driven approach that relies on a judicious choice of observable functions to realize global linear representations of nonlinear systems in the lifted observable space. However, real-world data is often noisy, making it difficult to obtain an accurate and unbiased approximation of the Koopman operator. The Koopman operator generated from noisy datasets is typically corrupted by noise-induced bias that severely degrades prediction and downstream tracking performance. In order to address this drawback, this paper proposes a novel autoencoder-based neural architecture to jointly learn the appropriate lifting functions and the reduced-bias Koopman operator from noisy data. The architecture initially learns the Koopman basis functions that are consistent for both the forward and backward temporal dynamics of the system. Subsequently, by utilizing the learned forward and backward temporal dynamics, the Koopman operator is synthesized with a reduced bias making the method more robust to noise compared to existing techniques. Theoretical analysis is used to demonstrate significant bias reduction in the presence of training noise. Dynamics prediction and tracking control simulations are conducted for multiple serial manipulator arms, including performance comparisons with leading alternative designs, to demonstrate its robustness under various noise levels. Experimental studies with the Franka FR3 7-DoF manipulator arm are further used to demonstrate the effectiveness of the proposed approach in a practical setting.
☆ What you reward is what you learn: Comparing rewards for online speech policy optimization in public HRI
Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, online learning can adapt to non-stationary conditions. In this paper, we study how to adapt a social robot's speech policy in the wild. During a 12-day in-situ deployment with over 1,400 public encounters, we cast online policy optimization as a multi-armed bandit problem and use Thompson sampling to select among six actions defined by speech rate (slow/normal/fast) and verbosity (concise/detailed). We compare three complementary binary rewards--Ru (user rating), Rc (conversation closure), and Rt (>=2 turns)--and show that each induces distinct arm distributions and interaction behaviors. We complement the online results with offline evaluations that analyze contextual factors (e.g., crowd level, group size) using video-annotated data. Taken together, we distill ready-to-use design lessons for deploying online optimization of speech policies in real public HRI settings.
☆ Learning Diffusion Policy from Primitive Skills for Robot Manipulation AAAI2026
Diffusion policies (DP) have recently shown great promise for generating actions in robotic manipulation. However, existing approaches often rely on global instructions to produce short-term control signals, which can result in misalignment in action generation. We conjecture that the primitive skills, referred to as fine-grained, short-horizon manipulations, such as ``move up'' and ``open the gripper'', provide a more intuitive and effective interface for robot learning. To bridge this gap, we propose SDP, a skill-conditioned DP that integrates interpretable skill learning with conditional action planning. SDP abstracts eight reusable primitive skills across tasks and employs a vision-language model to extract discrete representations from visual observations and language instructions. Based on them, a lightweight router network is designed to assign a desired primitive skill for each state, which helps construct a single-skill policy to generate skill-aligned actions. By decomposing complex tasks into a sequence of primitive skills and selecting a single-skill policy, SDP ensures skill-consistent behavior across diverse tasks. Extensive experiments on two challenging simulation benchmarks and real-world robot deployments demonstrate that SDP consistently outperforms SOTA methods, providing a new paradigm for skill-based robot learning with diffusion policies.
comment: Accepted to AAAI2026
☆ From Metrics to Meaning: Insights from a Mixed-Methods Field Experiment on Retail Robot Deployment
We report a mixed-methods field experiment of a conversational service robot deployed under everyday staffing discretion in a live bedding store. Over 12 days we alternated three conditions--Baseline (no robot), Robot-only, and Robot+Fixture--and video-annotated the service funnel from passersby to purchase. An explanatory sequential design then used six post-experiment staff interviews to interpret the quantitative patterns. Quantitatively, the robot increased stopping per passerby (highest with the fixture), yet clerk-led downstream steps per stopper--clerk approach, store entry, assisted experience, and purchase--decreased. Interviews explained this divergence: clerks avoided interrupting ongoing robot-customer talk, struggled with ambiguous timing amid conversational latency, and noted child-centered attraction that often satisfied curiosity at the doorway. The fixture amplified visibility but also anchored encounters at the threshold, creating a well-defined micro-space where needs could ``close'' without moving inside. We synthesize these strands into an integrative account from the initial show of interest on the part of a customer to their entering the store and derive actionable guidance. The results advance the understanding of interactions between customers, staff members, and the robot and offer practical recommendations for deploying service robots in high-touch retail.
☆ CausalNav: A Long-term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios
Autonomous language-guided navigation in large-scale outdoor environments remains a key challenge in mobile robotics, due to difficulties in semantic reasoning, dynamic conditions, and long-term stability. We propose CausalNav, the first scene graph-based semantic navigation framework tailored for dynamic outdoor environments. We construct a multi-level semantic scene graph using LLMs, referred to as the Embodied Graph, that hierarchically integrates coarse-grained map data with fine-grained object entities. The constructed graph serves as a retrievable knowledge base for Retrieval-Augmented Generation (RAG), enabling semantic navigation and long-range planning under open-vocabulary queries. By fusing real-time perception with offline map data, the Embodied Graph supports robust navigation across varying spatial granularities in dynamic outdoor environments. Dynamic objects are explicitly handled in both the scene graph construction and hierarchical planning modules. The Embodied Graph is continuously updated within a temporal window to reflect environmental changes and support real-time semantic navigation. Extensive experiments in both simulation and real-world settings demonstrate superior robustness and efficiency.
comment: Accepted by IEEE Robotics and Automation Letters (RA-L)
☆ DisCo-FLoc: Using Dual-Level Visual-Geometric Contrasts to Disambiguate Depth-Aware Visual Floorplan Localization
Since floorplan data is readily available, long-term persistent, and robust to changes in visual appearance, visual Floorplan Localization (FLoc) has garnered significant attention. Existing methods either ingeniously match geometric priors or utilize sparse semantics to reduce FLoc uncertainty. However, they still suffer from ambiguous FLoc caused by repetitive structures within minimalist floorplans. Moreover, expensive but limited semantic annotations restrict their applicability. To address these issues, we propose DisCo-FLoc, which utilizes dual-level visual-geometric Contrasts to Disambiguate depth-aware visual Floc, without requiring additional semantic labels. Our solution begins with a ray regression predictor tailored for ray-casting-based FLoc, predicting a series of FLoc candidates using depth estimation expertise. In addition, a novel contrastive learning method with position-level and orientation-level constraints is proposed to strictly match depth-aware visual features with the corresponding geometric structures in the floorplan. Such matches can effectively eliminate FLoc ambiguity and select the optimal imaging pose from FLoc candidates. Exhaustive comparative studies on two standard visual Floc benchmarks demonstrate that our method outperforms the state-of-the-art semantic-based method, achieving significant improvements in both robustness and accuracy.
comment: 7 pages, 4 figures
☆ AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
End-to-end autonomous driving has rapidly progressed, enabling joint perception and planning in complex environments. In the planning stage, state-of-the-art (SOTA) end-to-end autonomous driving models decouple planning into parallel lateral and longitudinal predictions. While effective, this parallel design can lead to i) coordination failures between the planned path and speed, and ii) underutilization of the drive path as a prior for longitudinal planning, thus redundantly encoding static information. To address this, we propose a novel cascaded framework that explicitly conditions longitudinal planning on the drive path, enabling coordinated and collision-aware lateral and longitudinal planning. Specifically, we introduce a path-conditioned formulation that explicitly incorporates the drive path into longitudinal planning. Building on this, the model predicts longitudinal displacements along the drive path rather than full 2D trajectory waypoints. This design simplifies longitudinal reasoning and more tightly couples it with lateral planning. Additionally, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events, such as vehicle cut-ins, by adding agents and relabeling longitudinal targets to avoid collision. Evaluated on the challenging Bench2Drive benchmark, our method sets a new SOTA, achieving a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety
comment: underreview
☆ Simulations and Advancements in MRI-Guided Power-Driven Ferric Tools for Wireless Therapeutic Interventions
Designing a robotic system that functions effectively within the specific environment of a Magnetic Resonance Imaging (MRI) scanner requires solving numerous technical issues, such as maintaining the robot's precision and stability under strong magnetic fields. This research focuses on enhancing MRI's role in medical imaging, especially in its application to guide intravascular interventions using robot-assisted devices. A newly developed computational system is introduced, designed for seamless integration with the MRI scanner, including a computational unit and user interface. This system processes MR images to delineate the vascular network, establishing virtual paths and boundaries within vessels to prevent procedural damage. Key findings reveal the system's capability to create tailored magnetic field gradient patterns for device control, considering the vessel's geometry and safety norms, and adapting to different blood flow characteristics for finer navigation. Additionally, the system's modeling aspect assesses the safety and feasibility of navigating pre-set vascular paths. Conclusively, this system, based on the Qt framework and C/C++, with specialized software modules, represents a major step forward in merging imaging technology with robotic aid, significantly enhancing precision and safety in intravascular procedures.
comment: 10 pages, 7 figures
☆ Explicit World Models for Reliable Human-Robot Collaboration AAAI-26
This paper addresses the topic of robustness under sensing noise, ambiguous instructions, and human-robot interaction. We take a radically different tack to the issue of reliable embodied AI: instead of focusing on formal verification methods aimed at achieving model predictability and robustness, we emphasise the dynamic, ambiguous and subjective nature of human-robot interactions that requires embodied AI systems to perceive, interpret, and respond to human intentions in a manner that is consistent, comprehensible and aligned with human expectations. We argue that when embodied agents operate in human environments that are inherently social, multimodal, and fluid, reliability is contextually determined and only has meaning in relation to the goals and expectations of humans involved in the interaction. This calls for a fundamentally different approach to achieving reliable embodied AI that is centred on building and updating an accessible "explicit world model" representing the common ground between human and AI, that is used to align robot behaviours with human expectations.
comment: Accepted to AAAI-26 Bridge Program B10: Making Embodied AI Reliable with Testing and Formal Verification
☆ Real-Time Lane Detection via Efficient Feature Alignment and Covariance Optimization for Low-Power Embedded Systems
Real-time lane detection in embedded systems encounters significant challenges due to subtle and sparse visual signals in RGB images, often constrained by limited computational resources and power consumption. Although deep learning models for lane detection categorized into segmentation-based, anchor-based, and curve-based methods there remains a scarcity of universally applicable optimization techniques tailored for low-power embedded environments. To overcome this, we propose an innovative Covariance Distribution Optimization (CDO) module specifically designed for efficient, real-time applications. The CDO module aligns lane feature distributions closely with ground-truth labels, significantly enhancing detection accuracy without increasing computational complexity. Evaluations were conducted on six diverse models across all three method categories, including two optimized for real-time applications and four state-of-the-art (SOTA) models, tested comprehensively on three major datasets: CULane, TuSimple, and LLAMAS. Experimental results demonstrate accuracy improvements ranging from 0.01% to 1.5%. The proposed CDO module is characterized by ease of integration into existing systems without structural modifications and utilizes existing model parameters to facilitate ongoing training, thus offering substantial benefits in performance, power efficiency, and operational flexibility in embedded systems.
☆ AMC26: High-performance DOb for robust position control
This paper presents a new HPDOb that significantly improves disturbance estimation accuracy and robustness in motion control systems, surpassing the capabilities of conventional DObs. The proposed observer is analysed and synthesised in the discrete-time domain, providing a realistic representation of their dynamic behaviour and enabling enhanced controller design for practical applications. The core contribution of the HPDOb is a novel synthesis method that incorporates higher-order truncation error dynamics into disturbance estimation. Unlike conventional DObs, which are limited to zero-order truncation error, the HPDOb achieves first-order truncation error, yielding markedly improved estimation accuracy and robustness against disturbances in motion control systems. Simulation and experiments verify the stability and performance of HPDOb.
☆ Learning and Optimizing the Efficacy of Spatio-Temporal Task Allocation under Temporal and Resource Constraints
Complex multi-robot missions often require heterogeneous teams to jointly optimize task allocation, scheduling, and path planning to improve team performance under strict constraints. We formalize these complexities into a new class of problems, dubbed Spatio-Temporal Efficacy-optimized Allocation for Multi-robot systems (STEAM). STEAM builds upon trait-based frameworks that model robots using their capabilities (e.g., payload and speed), but goes beyond the typical binary success-failure model by explicitly modeling the efficacy of allocations as trait-efficacy maps. These maps encode how the aggregated capabilities assigned to a task determine performance. Further, STEAM accommodates spatio-temporal constraints, including a user-specified time budget (i.e., maximum makespan). To solve STEAM problems, we contribute a novel algorithm named Efficacy-optimized Incremental Task Allocation Graph Search (E-ITAGS) that simultaneously optimizes task performance and respects time budgets by interleaving task allocation, scheduling, and path planning. Motivated by the fact that trait-efficacy maps are difficult, if not impossible, to specify, E-ITAGS efficiently learns them using a realizability-aware active learning module. Our approach is realizability-aware since it explicitly accounts for the fact that not all combinations of traits are realizable by the robots available during learning. Further, we derive experimentally-validated bounds on E-ITAGS' suboptimality with respect to efficacy. Detailed numerical simulations and experiments using an emergency response domain demonstrate that E-ITAGS generates allocations of higher efficacy compared to baselines, while respecting resource and spatio-temporal constraints. We also show that our active learning approach is sample efficient and establishes a principled tradeoff between data and computational efficiency.
comment: The journal extension version of our conference paper: arXiv:2404.07902, which has been accepted by ISRR 2024
☆ InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, but they inherently lack the capability to deduce physical world dynamics. Consequently, recent approaches have shifted toward World Models, typically formulated via video prediction; however, these methods often suffer from a lack of semantic grounding and exhibit brittleness when handling prediction errors. To synergize semantic understanding with dynamic predictive capabilities, we present InternVLA-A1. This model employs a unified Mixture-of-Transformers architecture, coordinating three experts for scene understanding, visual foresight generation, and action execution. These components interact seamlessly through a unified masked self-attention mechanism. Building upon InternVL3 and Qwen3-VL, we instantiate InternVLA-A1 at 2B and 3B parameter scales. We pre-train these models on hybrid synthetic-real datasets spanning InternData-A1 and Agibot-World, covering over 533M frames. This hybrid training strategy effectively harnesses the diversity of synthetic simulation data while minimizing the sim-to-real gap. We evaluated InternVLA-A1 across 12 real-world robotic tasks and simulation benchmark. It significantly outperforms leading models like pi0 and GR00T N1.5, achieving a 14.5\% improvement in daily tasks and a 40\%-73.3\% boost in dynamic settings, such as conveyor belt sorting.
comment: Homepage: https://internrobotics.github.io/internvla-a1.github.io/
♻ ☆ LIMOncello: Iterated Error-State Kalman Filter on the SGal(3) Manifold for Fast LiDAR-Inertial Odometry
This work introduces LIMOncello, a tightly coupled LiDAR-Inertial Odometry system that models 6-DoF motion on the $\mathrm{SGal}(3)$ manifold within an iterated error-state Kalman filter backend. Compared to state representations defined on $\mathrm{SO}(3)\times\mathbb{R}^6$, the use of $\mathrm{SGal}(3)$ provides a coherent and numerically stable discrete-time propagation model that helps limit drift in low-observability conditions. LIMOncello also includes a lightweight incremental i-Octree mapping backend that enables faster updates and substantially lower memory usage than incremental kd-tree style map structures, without relying on locality-restricted search heuristics. Experiments on multiple real-world datasets show that LIMOncello achieves competitive accuracy while improving robustness in geometrically sparse environments. The system maintains real-time performance with stable memory growth and is released as an extensible open-source implementation at https://github.com/CPerezRuiz335/LIMOncello.
♻ ☆ FORTE: Tactile Force and Slip Sensing on Compliant Fingers for Delicate Manipulation
Handling fragile objects remains a major challenge for robotic manipulation. Tactile sensing and soft robotics can improve delicate object handling, but typically involve high integration complexity or slow response times. We address these issues through FORTE, an easy-to-fabricate tactile sensing system. FORTE uses 3D-printed fin-ray grippers with internal air channels to provide low-latency force and slip feedback. This feedback allows us to apply just enough force to grasp objects without damaging them. We accurately estimate grasping forces from 0-8 N with an average error of 0.2 N, and detect slip events within 100 ms of occurring. FORTE can grasp a wide range of slippery, fragile, and deformable objects, including raspberries and potato chips with 92% success and achieves 93% accuracy in detecting slip events. These results highlight FORTE's potential as a robust solution for delicate robotic manipulation. Project page: https://merge-lab.github.io/FORTE/
♻ ☆ Volume-Consistent Kneading-Based Deformation Manufacturing for Material-Efficient Shaping
Conventional subtractive manufacturing inevitably involves material loss during geometric realization, while additive manufacturing still suffers from limitations in surface quality, process continuity, and productivity when fabricating complex geometries. To address these challenges, this paper proposes a volume-consistent kneading-based forming method for plastic materials, enabling continuous and controllable three-dimensional deformation under mass conservation. An integrated kneading-based manufacturing system is developed, in which geometry-aware kneading command generation, layer-wise kneading execution, and in-process point-cloud scanning are tightly coupled to form a closed-loop workflow of scanning, forming, and feedback compensation. Target geometries are analyzed through layer-wise point-cloud processing and classified into enveloping and non-enveloping types. Accordingly, an Envelope Shaping First strategy and a Similar Gradient Method are adopted to ensure stable material flow and continuous deformation. An RMSE-based compensation scheme is further introduced to correct systematic geometric deviations induced by elastic rebound and material redistribution. Experimental validation on five representative geometries demonstrates high geometric fidelity, with material utilization consistently exceeding 98%. The results indicate that kneading-based forming provides a promising alternative manufacturing paradigm for low-waste, customizable production.
comment: 39 pages, 31 figures
♻ ☆ Compositional Diffusion with Guided Search for Long-Horizon Planning
Generative models have emerged as powerful tools for planning, with compositional approaches offering particular promise for modeling long-horizon task distributions by composing together local, modular generative models. This compositional paradigm spans diverse domains, from multi-step manipulation planning to panoramic image synthesis to long video generation. However, compositional generative models face a critical challenge: when local distributions are multimodal, existing composition methods average incompatible modes, producing plans that are neither locally feasible nor globally coherent. We propose Compositional Diffusion with Guided Search (CDGS), which addresses this mode averaging problem by embedding search directly within the diffusion denoising process. Our method explores diverse combinations of local modes through population-based sampling, prunes infeasible candidates using likelihood-based filtering, and enforces global consistency through iterative resampling between overlapping segments. CDGS matches oracle performance on seven robot manipulation tasks, outperforming baselines that lack compositionality or require long-horizon training data. The approach generalizes across domains, enabling coherent text-guided panoramic images and long videos through effective local-to-global message passing. More details: https://cdgsearch.github.io/
comment: 38 pages, 18 figures
♻ ☆ Interconnection and Damping Assignment Passivity-Based Control using Sparse Neural ODEs
Interconnection and Damping Assignment Passivity-Based Control (IDA-PBC) is a nonlinear control technique that assigns a port-Hamiltonian (pH) structure to a controlled system using a state-feedback law. While IDA-PBC has been extensively studied and applied to many systems, its practical implementation often remains confined to academic examples and, almost exclusively, to stabilization tasks. The main limitation of IDA-PBC stems from the complexity of analytically solving a set of partial differential equations (PDEs), referred to as the matching conditions, which enforce the pH structure of the closed-loop system. However, this is extremely challenging, especially for complex physical systems and tasks. In this work, we propose a novel numerical approach for designing IDA-PBC controllers without solving the matching PDEs exactly. We cast the IDA-PBC problem as the learning of a neural ordinary differential equation. In particular, we rely on sparse dictionary learning to parametrize the desired closed-loop system as a sparse linear combination of nonlinear state-dependent functions. Optimization of the controller parameters is achieved by solving a multi-objective optimization problem whose cost function is composed of a generic task-dependent cost and a matching condition-dependent cost. Our numerical results show that the proposed method enables (i) IDA-PBC to be applicable to complex tasks beyond stabilization, such as the discovery of periodic oscillatory behaviors, (ii) the derivation of closed-form expressions of the controlled system, including residual terms in case of approximate matching, and (iii) stability analysis of the learned controller.
♻ ☆ Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models
The draft IMO MASS Code requires autonomous and remotely supervised maritime vessels to detect departures from their operational design domain, enter a predefined fallback that notifies the operator, permit immediate human override, and avoid changing the voyage plan without approval. Meeting these obligations in the alert-to-takeover gap calls for a short-horizon, human-overridable fallback maneuver. Classical maritime autonomy stacks struggle when the correct action depends on meaning (e.g., diver-down flag means people in the water, fire close by means hazard). We argue (i) that vision-language models (VLMs) provide semantic awareness for such out-of-distribution situations, and (ii) that a fast-slow anomaly pipeline with a short-horizon, human-overridable fallback maneuver makes this practical in the handover window. We introduce Semantic Lookout, a camera-only, candidate-constrained VLM fallback maneuver selector that selects one cautious action (or station-keeping) from water-valid, world-anchored trajectories under continuous human authority. On 40 harbor scenes we measure per-call scene understanding and latency, alignment with human consensus (model majority-of-three voting), short-horizon risk-relief on fire hazard scenes, and an on-water alert->fallback maneuver->operator handover. Sub-10 s models retain most of the awareness of slower state-of-the-art models. The fallback maneuver selector outperforms geometry-only baselines and increases standoff distance on fire scenes. A field run verifies end-to-end operation. These results support VLMs as semantic fallback maneuver selectors compatible with the draft IMO MASS Code, within practical latency budgets, and motivate future work on domain-adapted, hybrid autonomy that pairs foundation-model semantics with multi-sensor bird's-eye-view perception and short-horizon replanning. Website: kimachristensen.github.io/bridge_policy
comment: 17 pages without bibliography or appendix. The main paper has 16 figures. Paper webpage can be found at https://kimachristensen.github.io/bridge_policy/
♻ ☆ MOON: Multi-Objective Optimization-Driven Object-Goal Navigation Using a Variable-Horizon Set-Orienteering Planner
This paper proposes MOON (Multi-Objective Optimization-driven Object-goal Navigation), a novel framework designed for efficient navigation in large-scale, complex indoor environments. While existing methods often rely on local heuristics, they frequently fail to address the strategic trade-offs between competing objectives in vast areas. To overcome this, we formulate the task as a multi-objective optimization problem (MOO) that balances frontier-based exploration with the exploitation of observed landmarks. Our prototype integrates three key pillars: (1) QOM [IROS05] for discriminative landmark encoding; (2) StructNav [RSS23] to enhance the navigation pipeline; and (3) a variable-horizon Set Orienteering Problem (SOP) formulation for globally coherent planning. To further support the framework's scalability, we provide a detailed theoretical foundation for the budget-constrained SOP formulation and the data-driven mode-switching strategy that enables long-horizon resource allocation. Additionally, we introduce a high-speed neural planner that distills the expert solver into a transformer-based model, reducing decision latency by a factor of nearly 10 while maintaining high planning quality.
comment: 9 pages, 7 figures, technical report
♻ ☆ Multi-Robot Data-Free Continual Communicative Learning (CCL) from Black-Box Visual Place Recognition Models
In emerging multi-robot societies, heterogeneous agents must continually extract and integrate local knowledge from one another through communication, even when their internal models are completely opaque. Existing approaches to continual or collaborative learning for visual place recognition (VPR) largely assume white-box access to model parameters or shared training datasets, which is unrealistic when robots encounter unknown peers in the wild. This paper introduces \emph{Continual Communicative Learning (CCL)}, a data-free multi-robot framework in which a traveler robot (student) continually improves its VPR capability by communicating with black-box teacher models via a constrained query--response channel. We repurpose Membership Inference Attacks (MIA), originally developed as privacy attacks on machine learning models, as a constructive communication primitive to reconstruct pseudo-training sets from black-box VPR teachers without accessing their parameters or raw data. To overcome the intrinsic communication bottleneck caused by the low sampling efficiency of black-box MIA, we propose a prior-based query strategy that leverages the student's own VPR prior to focus queries on informative regions of the embedding space, thereby reducing the knowledge transfer (KT) cost. Experimental results on a standard multi-session VPR benchmark demonstrate that the proposed CCL framework yields substantial performance gains for low-performing robots under modest communication budgets, highlighting CCL as a promising building block for scalable and fault-tolerant multi-robot systems.
comment: 6 pages, 4 figures, technical report
♻ ☆ AdaVLN: Towards Visual Language Navigation in Continuous Indoor Environments with Moving Humans
Visual Language Navigation is a task that challenges robots to navigate in realistic environments based on natural language instructions. While previous research has largely focused on static settings, real-world navigation must often contend with dynamic human obstacles. Hence, we propose an extension to the task, termed Adaptive Visual Language Navigation (AdaVLN), which seeks to narrow this gap. AdaVLN requires robots to navigate complex 3D indoor environments populated with dynamically moving human obstacles, adding a layer of complexity to navigation tasks that mimic the real-world. To support exploration of this task, we also present AdaVLN simulator and AdaR2R datasets. The AdaVLN simulator enables easy inclusion of fully animated human models directly into common datasets like Matterport3D. We also introduce a "freeze-time" mechanism for both the navigation task and simulator, which pauses world state updates during agent inference, enabling fair comparisons and experimental reproducibility across different hardware. We evaluate several baseline models on this task, analyze the unique challenges introduced by AdaVLN, and demonstrate its potential to bridge the sim-to-real gap in VLN research.
♻ ☆ RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation
Physical feasibility in 3D bin packing is a key requirement in modern industrial logistics and robotic automation. With the growing adoption of industrial automation, online bin packing has gained increasing attention. However, inconsistencies in problem settings, test datasets, and evaluation metrics have hindered progress in the field, and there is a lack of a comprehensive benchmarking system. Direct testing on real hardware is costly, and building a realistic simulation environment is also challenging. To address these limitations, we introduce RoboBPP, a benchmarking system designed for robotic online bin packing. RoboBPP integrates a physics-based simulator to assess physical feasibility. In our simulation environment, we introduce a robotic arm and boxes at real-world scales to replicate real industrial packing workflows. By simulating conditions that arise in real industrial applications, we ensure that evaluated algorithms are practically deployable. In addition, prior studies often rely on synthetic datasets whose distributions differ from real-world industrial data. To address this issue, we collect three datasets from real industrial workflows, including assembly-line production, logistics packing, and furniture manufacturing. The benchmark comprises three carefully designed test settings and extends existing evaluation metrics with new metrics for structural stability and operational safety. We design a scoring system and derive a range of insights from the evaluation results. RoboBPP is fully open-source and is equipped with visualization tools and an online leaderboard, providing a reproducible and extensible foundation for future research and industrial applications (https://robot-bin-packing-benchmark.github.io).
comment: Under review at the International Journal of Robotics Research (IJRR)
♻ ☆ RNBF: Real-Time RGB-D Based Neural Barrier Functions for Safe Robotic Navigation
Autonomous safe navigation in unstructured and novel environments poses significant challenges, especially when environment information can only be provided through low-cost vision sensors. Although safe reactive approaches have been proposed to ensure robot safety in complex environments, many base their theory off the assumption that the robot has prior knowledge on obstacle locations and geometries. In this paper, we present a real-time, vision-based framework that constructs continuous, first-order differentiable Signed Distance Fields (SDFs) of unknown environments entirely online, without any pre-training, and is fully compatible with established SDF-based reactive controllers. To achieve robust performance under practical sensing conditions, our approach explicitly accounts for noise in affordable RGB-D cameras, refining the neural SDF representation online for smoother geometry and stable gradient estimates. We validate the proposed method in simulation and real-world experiments using a Fetch robot. Videos and supplementary material are available at https://satyajeetburla.github.io/rnbf/.
♻ ☆ SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling
Data scarcity remains a fundamental barrier to achieving fully autonomous surgical robots. While large scale vision language action (VLA) models have shown impressive generalization in household and industrial manipulation by leveraging paired video action data from diverse domains, surgical robotics suffers from the paucity of datasets that include both visual observations and accurate robot kinematics. In contrast, vast corpora of surgical videos exist, but they lack corresponding action labels, preventing direct application of imitation learning or VLA training. In this work, we aim to alleviate this problem by learning policy models from SurgWorld, a world model designed for surgical physical AI. We curated the Surgical Action Text Alignment (SATA) dataset with detailed action description specifically for surgical robots. Then we built SurgeWorld based on the most advanced physical AI world model and SATA. It's able to generate diverse, generalizable and realistic surgery videos. We are also the first to use an inverse dynamics model to infer pseudokinematics from synthetic surgical videos, producing synthetic paired video action data. We demonstrate that a surgical VLA policy trained with these augmented data significantly outperforms models trained only on real demonstrations on a real surgical robot platform. Our approach offers a scalable path toward autonomous surgical skill acquisition by leveraging the abundance of unlabeled surgical video and generative world modeling, thus opening the door to generalizable and data efficient surgical robot policies.
♻ ☆ Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge
The 2025 BEHAVIOR Challenge is designed to rigorously track progress toward solving long-horizon tasks by physical agents in simulated environments. BEHAVIOR-1K focuses on everyday household tasks that people most want robots to assist with and these tasks introduce long-horizon mobile manipulation challenges in realistic settings, bridging the gap between current research and real-world, human-centric applications. This report presents our solution to the 2025 BEHAVIOR Challenge in a very close 2nd place and substantially outperforms the rest of the submissions. Building on $π_{0.5}$, we focus on systematically building our solution by studying the effects of training techniques and data. Through careful ablation studies, we reveal the scaling benefits in both the pre-training and post-training phases, leading to a validation Q-score of 0.345, significantly surpassing previous state-of-the-art performance. We summarize our practical lessons and design recommendations that we hope will provide actionable insights for the broader embodied AI community when adapting powerful foundation models to complex embodied scenarios. Project page: https://github.com/mli0603/openpi-comet
comment: Post-challenge bug fix
Robotics 21
☆ VisuoTactile 6D Pose Estimation of an In-Hand Object using Vision and Tactile Sensor Data ICRA 2022
Knowledge of the 6D pose of an object can benefit in-hand object manipulation. In-hand 6D object pose estimation is challenging because of heavy occlusion produced by the robot's grippers, which can have an adverse effect on methods that rely on vision data only. Many robots are equipped with tactile sensors at their fingertips that could be used to complement vision data. In this paper, we present a method that uses both tactile and vision data to estimate the pose of an object grasped in a robot's hand. To address challenges like lack of standard representation for tactile data and sensor fusion, we propose the use of point clouds to represent object surfaces in contact with the tactile sensor and present a network architecture based on pixel-wise dense fusion. We also extend NVIDIA's Deep Learning Dataset Synthesizer to produce synthetic photo-realistic vision data and corresponding tactile point clouds. Results suggest that using tactile data in addition to vision data improves the 6D pose estimate, and our network generalizes successfully from synthetic training to real physical robots.
comment: Accepted for publication in IEEE Robotics and Automation Letters (RA-L), January 2022. Presented at ICRA 2022. This is the author's version of the manuscript
☆ DemoBot: Efficient Learning of Bimanual Manipulation with Dexterous Hands From Third-Person Human Videos
This work presents DemoBot, a learning framework that enables a dual-arm, multi-finger robotic system to acquire complex manipulation skills from a single unannotated RGB-D video demonstration. The method extracts structured motion trajectories of both hands and objects from raw video data. These trajectories serve as motion priors for a novel reinforcement learning (RL) pipeline that learns to refine them through contact-rich interactions, thereby eliminating the need to learn from scratch. To address the challenge of learning long-horizon manipulation skills, we introduce: (1) Temporal-segment based RL to enforce temporal alignment of the current state with demonstrations; (2) Success-Gated Reset strategy to balance the refinement of readily acquired skills and the exploration of subsequent task stages; and (3) Event-Driven Reward curriculum with adaptive thresholding to guide the RL learning of high-precision manipulation. The novel video processing and RL framework successfully achieved long-horizon synchronous and asynchronous bimanual assembly tasks, offering a scalable approach for direct skill acquisition from human videos.
☆ Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
Long-horizon robotic manipulation is increasingly important for real-world deployment, requiring spatial disambiguation in complex layouts and temporal resilience under dynamic interaction. However, existing end-to-end and hierarchical Vision-Language-Action (VLA) policies often rely on text-only cues while keeping plan intent latent, which undermines referential grounding in cluttered or underspecified scenes, impedes effective task decomposition of long-horizon goals with close-loop interaction, and limits causal explanation by obscuring the rationale behind action choices. To address these issues, we first introduce Visual Sketch, an implausible visual intermediate that renders points, boxes, arrows, and typed relations in the robot's current views to externalize spatial intent, connect language to scene geometry. Building on Visual Sketch, we present Action-Sketcher, a VLA framework that operates in a cyclic See-Think-Sketch-Act workflow coordinated by adaptive token-gated strategy for reasoning triggers, sketch revision, and action issuance, thereby supporting reactive corrections and human interaction while preserving real-time action prediction. To enable scalable training and evaluation, we curate diverse corpus with interleaved images, text, Visual Sketch supervision, and action sequences, and train Action-Sketcher with a multi-stage curriculum recipe that combines interleaved sequence alignment for modality unification, language-to-sketch consistency for precise linguistic grounding, and imitation learning augmented with sketch-to-action reinforcement for robustness. Extensive experiments on cluttered scenes and multi-object tasks, in simulation and on real-world tasks, show improved long-horizon success, stronger robustness to dynamic scene changes, and enhanced interpretability via editable sketches and step-wise plans. Project website: https://action-sketcher.github.io
comment: 26 pages, 14 figures
☆ HanoiWorld : A Joint Embedding Predictive Architecture BasedWorld Model for Autonomous Vehicle Controller
Current attempts of Reinforcement Learning for Autonomous Controller are data-demanding while the results are under-performed, unstable, and unable to grasp and anchor on the concept of safety, and over-concentrating on noise features due to the nature of pixel reconstruction. While current Self-Supervised Learningapproachs that learning on high-dimensional representations by leveraging the JointEmbedding Predictive Architecture (JEPA) are interesting and an effective alternative, as the idea mimics the natural ability of the human brain in acquiring new skill usingimagination and minimal samples of observations. This study introduces Hanoi-World, a JEPA-based world model that using recurrent neural network (RNN) formaking longterm horizontal planning with effective inference time. Experimentsconducted on the Highway-Env package with difference enviroment showcase the effective capability of making a driving plan while safety-awareness, with considerablecollision rate in comparison with SOTA baselines
☆ AIMS: An Adaptive Integration of Multi-Sensor Measurements for Quadrupedal Robot Localization
This paper addresses the problem of accurate localization for quadrupedal robots operating in narrow tunnel-like environments. Due to the long and homogeneous characteristics of such scenarios, LiDAR measurements often provide weak geometric constraints, making traditional sensor fusion methods susceptible to accumulated motion estimation errors. To address these challenges, we propose AIMS, an adaptive LiDAR-IMU-leg odometry fusion method for robust quadrupedal robot localization in degenerate environments. The proposed method is formulated within an error-state Kalman filtering framework, where LiDAR and leg odometry measurements are integrated with IMU-based state prediction, and measurement noise covariance matrices are adaptively adjusted based on online degeneracy-aware reliability assessment. Experimental results obtained in narrow corridor environments demonstrate that the proposed method improves localization accuracy and robustness compared with state-of-the-art approaches.
☆ DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving, this vision gives rise to driving world models: generative simulators that imagine ego and agent futures, enabling scalable simulation, safe testing of corner cases, and rich synthetic data generation. Yet, despite fast-growing research activity, the field lacks a rigorous benchmark to measure progress and guide priorities. Existing evaluations remain limited: generic video metrics overlook safety-critical imaging factors; trajectory plausibility is rarely quantified; temporal and agent-level consistency is neglected; and controllability with respect to ego conditioning is ignored. Moreover, current datasets fail to cover the diversity of conditions required for real-world deployment. To address these gaps, we present DrivingGen, the first comprehensive benchmark for generative driving world models. DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources, spanning varied weather, time of day, geographic regions, and complex maneuvers, with a suite of new metrics that jointly assess visual realism, trajectory plausibility, temporal coherence, and controllability. Benchmarking 14 state-of-the-art models reveals clear trade-offs: general models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality. DrivingGen offers a unified evaluation framework to foster reliable, controllable, and deployable driving world models, enabling scalable simulation, planning, and data-driven decision-making.
comment: 10 pages, 4 figures; Project Website: https://drivinggen-bench.github.io/
☆ Online Estimation and Manipulation of Articulated Objects
From refrigerators to kitchen drawers, humans interact with articulated objects effortlessly every day while completing household chores. For automating these tasks, service robots must be capable of manipulating arbitrary articulated objects. Recent deep learning methods have been shown to predict valuable priors on the affordance of articulated objects from vision. In contrast, many other works estimate object articulations by observing the articulation motion, but this requires the robot to already be capable of manipulating the object. In this article, we propose a novel approach combining these methods by using a factor graph for online estimation of articulation which fuses learned visual priors and proprioceptive sensing during interaction into an analytical model of articulation based on Screw Theory. With our method, a robotic system makes an initial prediction of articulation from vision before touching the object, and then quickly updates the estimate from kinematic and force sensing during manipulation. We evaluate our method extensively in both simulations and real-world robotic manipulation experiments. We demonstrate several closed-loop estimation and manipulation experiments in which the robot was capable of opening previously unseen drawers. In real hardware experiments, the robot achieved a 75% success rate for autonomous opening of unknown articulated objects.
comment: This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this article is published in Autonomous Robots, and is available online at [Link will be updated when available]
☆ Sampling Strategy Design for Model Predictive Path Integral Control on Legged Robot Locomotion
Model Predictive Path Integral (MPPI) control has emerged as a powerful sampling-based optimal control method for complex, nonlinear, and high-dimensional systems. However, directly applying MPPI to legged robotic systems presents several challenges. This paper systematically investigates the role of sampling strategy design within the MPPI framework for legged robot locomotion. Based upon the idea of structured control parameterization, we explore and compare multiple sampling strategies within the framework, including both unstructured and spline-based approaches. Through extensive simulations on a quadruped robot platform, we evaluate how different sampling strategies affect control smoothness, task performance, robustness, and sample efficiency. The results provide new insights into the practical implications of sampling design for deploying MPPI on complex legged systems.
♻ ☆ How Robot Dogs See the Unseeable: Improving Visual Interpretability via Peering for Exploratory Robots
In vegetated environments, such as forests, exploratory robots play a vital role in navigating complex, cluttered environments where human access is limited and traditional equipment struggles. Visual occlusion from obstacles, such as foliage, can severely obstruct a robot's sensors, impairing scene understanding. We show that "peering", a characteristic side-to-side movement used by insects to overcome their visual limitations, can also allow robots to markedly improve visual reasoning under partial occlusion. This is accomplished by applying core signal processing principles, specifically optical synthetic aperture sensing, together with the vision reasoning capabilities of modern large multimodal models. Peering enables real-time, high-resolution, and wavelength-independent perception, which is crucial for vision-based scene understanding across a wide range of applications. The approach is low-cost and immediately deployable on any camera-equipped robot. We investigated different peering motions and occlusion masking strategies, demonstrating that, unlike peering, state-of-the-art multi-view 3D vision techniques fail in these conditions due to their high susceptibility to occlusion. Our experiments were carried out on an industrial-grade quadrupedal robot. However, the ability to peer is not limited to such platforms, but potentially also applicable to bipedal, hexapod, wheeled, or crawling platforms. Robots that can effectively see through partial occlusion will gain superior perception abilities - including enhanced scene understanding, situational awareness, camouflage breaking, and advanced navigation in complex environments.
♻ ☆ General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning AAMAS 2026
Understanding an agent's goal through its behavior is a common AI problem called Goal Recognition (GR). This task becomes particularly challenging in dynamic environments where goals are numerous and ever-changing. We introduce the General Dynamic Goal Recognition (GDGR) problem, a broader definition of GR aimed at real-time adaptation of GR systems. This paper presents two novel approaches to tackle GDGR: (1) GC-AURA, generalizing to new goals using Model-Free Goal-Conditioned Reinforcement Learning, and (2) Meta-AURA, adapting to novel environments with Meta-Reinforcement Learning. We evaluate these methods across diverse environments, demonstrating their ability to achieve rapid adaptation and high GR accuracy under dynamic and noisy conditions. This work is a significant step forward in enabling GR in dynamic and unpredictable real-world environments.
comment: Accepted for publication at AAMAS 2026
♻ ☆ Standing Tall: Sim to Real Fall Classification and Lead Time Prediction for Bipedal Robots
This paper extends a previously proposed fall prediction algorithm to a real-time (online) setting, with implementations in both hardware and simulation. The system is validated on the full-sized bipedal robot Digit, where the real-time version achieves performance comparable to the offline implementation while maintaining a zero false positive rate, an average lead time (defined as the difference between the true and predicted fall time) of 1.1s (well above the required minimum of 0.2s), and a maximum lead time error of just 0.03s. It also achieves a high recovery rate of 0.97, demonstrating its effectiveness in real-world deployment. In addition to the real-time implementation, this work identifies key limitations of the original algorithm, particularly under omnidirectional faults, and introduces a fine-tuned strategy to improve robustness. The enhanced algorithm shows measurable improvements across all evaluated metrics, including a 0.05 reduction in average false positive rate and a 1.19s decrease in the maximum error of the average predicted lead time.
comment: This work has been submitted to the IEEE for possible publication
♻ ☆ Phase-based Nonlinear Model Predictive Control for Humanoid Walking Stabilization with Single and Double Support Time Adjustments
The contact sequence of humanoid walking consists of single and double support phases (SSP and DSP), and their coordination through proper duration and dynamic transition based on the robot's state is crucial for maintaining walking stability. Numerous studies have investigated phase duration optimization as an effective means of improving walking stability. This paper presents a phase-based Nonlinear Model Predictive Control (NMPC) framework that jointly optimizes Zero Moment Point (ZMP) modulation, step location, SSP duration (step timing), and DSP duration within a single formulation. Specifically, the proposed framework reformulates the nonlinear DCM (Divergent Component of Motion) error dynamics into a phase-consistent representation and incorporates them as dynamic constraints within the NMPC. The proposed framework also guarantees ZMP input continuity during contact-phase transitions and disables footstep updates during the DSP, thereby enabling dynamically reliable balancing control regardless of whether the robot is in SSP or DSP. The effectiveness of the proposed method is validated through extensive simulation and hardware experiments, demonstrating improved balance performance under external disturbances.
comment: 15 pages, 9 figures
♻ ☆ H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos
Large-scale pre-training using videos has proven effective for robot learning. However, the models pre-trained on such data can be suboptimal for robot learning due to the significant visual gap between human hands and those of different robots. To remedy this, we propose H2R, a simple data augmentation technique that detects human hand keypoints, synthesizes robot motions in simulation, and composites rendered robots into egocentric videos. This process explicitly bridges the visual gap between human and robot embodiments during pre-training. We apply H2R to augment large-scale egocentric human video datasets such as Ego4D and SSv2, replacing human hands with simulated robotic arms to generate robot-centric training data. Based on this, we construct and release a family of 1M-scale datasets covering multiple robot embodiments (UR5 with gripper/Leaphand, Franka) and data sources (SSv2, Ego4D). To verify the effectiveness of the augmentation pipeline, we introduce a CLIP-based image-text similarity metric that quantitatively evaluates the semantic fidelity of robot-rendered frames to the original human actions. We validate H2R across three simulation benchmarks: Robomimic, RLBench and PushT and real-world manipulation tasks with a UR5 robot equipped with Gripper and Leaphand end-effectors. H2R consistently improves downstream success rates, yielding gains of 5.0%-10.2% in simulation and 6.7%-23.3% in real-world tasks across various visual encoders and policy learning methods. These results indicate that H2R improves the generalization ability of robotic policies by mitigating the visual discrepancies between human and robot domains.
♻ ☆ Multimodal Classification Network Guided Trajectory Planning for Four-Wheel Independent Steering Autonomous Parking Considering Obstacle Attributes
Four-wheel Independent Steering (4WIS) vehicles have attracted increasing attention for their superior maneuverability. Human drivers typically choose to cross or drive over the low-profile obstacles (e.g., plastic bags) to efficiently navigate through narrow spaces, while existing planners neglect obstacle attributes, leading to suboptimal efficiency or planning failures. To address this issue, we propose a novel multimodal trajectory planning framework that employs a neural network for scene perception, combines 4WIS hybrid A* search to generate a warm start, and utilizes an optimal control problem (OCP) for trajectory optimization. Specifically, a multimodal perception network fusing visual information and vehicle states is employed to capture semantic and contextual scene understanding, enabling the planner to adapt the strategy according to scene complexity (hard or easy task). For hard tasks, guided points are introduced to decompose complex tasks into local subtasks, improving the search efficiency. The multiple steering modes of 4WIS vehicles, Ackermann, diagonal, and zero-turn, are also incorporated as kinematically feasible motion primitives. Moreover, a hierarchical obstacle handling strategy, which categorizes obstacles as "non-traversable", "crossable", and "drive-over", is incorporated into the node expansion process, explicitly linking obstacle attributes to planning actions to enable efficient decisions. Furthermore, to address dynamic obstacles with motion uncertainty, we introduce a probabilistic risk field model, constructing risk-aware driving corridors that serve as linear collision constraints in OCP. Experimental results demonstrate the proposed framework's effectiveness in generating safe, efficient, and smooth trajectories for 4WIS vehicles, especially in constrained environments.
♻ ☆ Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
Autonomous driving has long relied on modular "Perception-Decision-Action" pipelines, where hand-crafted interfaces and rule-based components often break down in complex or long-tailed scenarios. Their cascaded design further propagates perception errors, degrading downstream planning and control. Vision-Action (VA) models address some limitations by learning direct mappings from visual inputs to actions, but they remain opaque, sensitive to distribution shifts, and lack structured reasoning or instruction-following capabilities. Recent progress in Large Language Models (LLMs) and multimodal learning has motivated the emergence of Vision-Language-Action (VLA) frameworks, which integrate perception with language-grounded decision making. By unifying visual understanding, linguistic reasoning, and actionable outputs, VLAs offer a pathway toward more interpretable, generalizable, and human-aligned driving policies. This work provides a structured characterization of the emerging VLA landscape for autonomous driving. We trace the evolution from early VA approaches to modern VLA frameworks and organize existing methods into two principal paradigms: End-to-End VLA, which integrates perception, reasoning, and planning within a single model, and Dual-System VLA, which separates slow deliberation (via VLMs) from fast, safety-critical execution (via planners). Within these paradigms, we further distinguish subclasses such as textual vs. numerical action generators and explicit vs. implicit guidance mechanisms. We also summarize representative datasets and benchmarks for evaluating VLA-based driving systems and highlight key challenges and open directions, including robustness, interpretability, and instruction fidelity. Overall, this work aims to establish a coherent foundation for advancing human-compatible autonomous driving systems.
comment: Survey; 47 pages, 7 figures, 9 tables; GitHub Repo at https://github.com/worldbench/awesome-vla-for-ad
♻ ☆ VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs
In most existing embodied navigation tasks, instructions are well-defined and unambiguous, such as instruction following and object searching. Under this idealized setting, agents are required solely to produce effective navigation outputs conditioned on vision and language inputs. However, real-world navigation instructions are often vague and ambiguous, requiring the agent to resolve uncertainty and infer user intent through active dialog. To address this gap, we propose Interactive Instance Goal Navigation (IIGN), a task that requires agents not only to generate navigation actions but also to produce language outputs via active dialog, thereby aligning more closely with practical settings. IIGN extends Instance Goal Navigation (IGN) by allowing agents to freely consult an oracle in natural language while navigating. Building on this task, we present the Vision Language-Language Navigation (VL-LN) benchmark, which provides a large-scale, automatically generated dataset and a comprehensive evaluation protocol for training and assessing dialog-enabled navigation models. VL-LN comprises over 41k long-horizon dialog-augmented trajectories for training and an automatic evaluation protocol with an oracle capable of responding to agent queries. Using this benchmark, we train a navigation model equipped with dialog capabilities and show that it achieves significant improvements over the baselines. Extensive experiments and analyses further demonstrate the effectiveness and reliability of VL-LN for advancing research on dialog-enabled embodied navigation. Code and dataset: https://0309hws.github.io/VL-LN.github.io/
♻ ☆ Evaluation of Impression Difference of a Domestic Mobile Manipulator with Autonomous and/or Remote Control in Fetch-and-Carry Tasks
A single service robot can present two distinct agencies: its onboard autonomy and an operator-mediated agency, yet users experience them through one physical body. We formalize this dual-agency structure as a User-Robot-Operator triad in an autonomous remote-control setting that integrates teleoperation with autonomous execution and human-in-the-loop remote assistance. Prior to the recent surge of language-based and multimodal interfaces, we developed and evaluated an early-stage prototype in 2020 that combined natural-language text chat with a sketch-based interface enabling freehand on-image annotation over the robot's live camera view to support remote intervention. We evaluated three modes - remote control via teleoperation, autonomous control, and autonomous remote control (a hybrid mode representing different levels of autonomy) - in controlled fetch-and-carry mobile manipulation tasks using a domestic mobile manipulator, the Human Support Robot (HSR), on a World Robot Summit 2020 rule-compliant test field. The results show systematic mode-dependent differences in user-rated affinity and perceived security, indicating that switching or blending agency within one robot measurably shapes human impressions in Human-Robot Interaction (HRI). These findings provide empirical guidance for designing human-in-the-loop mobile manipulation in domestic physical tasks.
comment: Published in Advanced Robotics (2020). v2 updates Abstract/Comments (metadata only); paper content unchanged. Please cite: Advanced Robotics 34(20):1291-1308, 2020. https://doi.org/10.1080/01691864.2020.1780152
♻ ☆ Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion from audio and then retargeting it to robots relies on explicit motion reconstruction, leading to cascaded errors, high latency, and disjointed acoustic-actuation mapping. We propose RoboPerform, the first unified audio-to-locomotion framework that can directly generate music-driven dance and speech-driven co-speech gestures from audio. Guided by the core principle of "motion = content + style", the framework treats audio as implicit style signals and eliminates the need for explicit motion reconstruction. RoboPerform integrates a ResMoE teacher policy for adapting to diverse motion patterns and a diffusion-based student policy for audio style injection. This retargeting-free design ensures low latency and high fidelity. Experimental validation shows that RoboPerform achieves promising results in physical plausibility and audio alignment, successfully transforming robots into responsive performers capable of reacting to audio.
♻ ☆ RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion
Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either curated motion capture trajectories or sparse text commands, leaving a critical gap between visual understanding and control. Text-to-motion methods suffer from semantic sparsity and staged pipeline errors, while video-based approaches only perform mechanical pose mimicry without genuine visual understanding. We propose RoboMirror, the first retargeting-free video-to-locomotion framework embodying "understand before you imitate". Leveraging VLMs, it distills raw egocentric/third-person videos into visual motion intents, which directly condition a diffusion-based policy to generate physically plausible, semantically aligned locomotion without explicit pose reconstruction or retargeting. Extensive experiments validate the effectiveness of RoboMirror, it enables telepresence via egocentric videos, drastically reduces third-person control latency by 80%, and achieves a 3.7% higher task success rate than baselines. By reframing humanoid control around video understanding, we bridge the visual understanding and action gap.
♻ ☆ ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
Embodied agents require robust spatial intelligence to execute precise real-world manipulations. However, this remains a significant challenge, as current methods often struggle to accurately position objects in space. Collecting extensive data can help address this issue by enhancing the agent's spatial understanding. Nonetheless, obtaining such data with real robots is prohibitively expensive, and relying on simulation data frequently leads to visual generalization gaps during real-world deployment. To tackle these challenges, we propose ManiBox, a novel bounding-box-guided framework. By decoupling perception from policy generalization, ManiBox effectively reduces the Sim2Real gap, leverages Internet-scale data, and scales our policy data collection in simulation. Specifically, within ManiBox, the RL teacher policy efficiently generates scalable simulation data. The student policy is distilled from this data and takes bounding boxes as input, which is proven sufficient for determining objects' spatial positions, thus enabling zero-shot transfer to real robots. Comprehensive evaluations in both simulated and real-world environments demonstrate that ManiBox exhibits strong spatial generalization and adaptability across various manipulation tasks and settings. Furthermore, our empirical study provides preliminary verification of spatial scaling laws, i.e., the amount of data required for spatial generalization scales with spatial volume following a power-law relationship. At a given spatial volume level, the success rate of manipulation tasks follows Michaelis-Menten kinetics with respect to data volume, exhibiting a saturation effect as data increases. Our videos and code are available at https://thkkk.github.io/manibox
♻ ☆ LSRE: Latent Semantic Rule Encoding for Real-Time Semantic Risk Detection in Autonomous Driving
Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers' gestures, or stopping for school buses, are intuitive for humans yet difficult to encode explicitly. Although large vision-language models (VLMs) can interpret such semantics, their inference cost makes them impractical for real-time deployment. This work proposes LSRE, a Latent Semantic Rule Encoding framework that converts sparsely sampled VLM judgments into decision boundaries within the latent space of a recurrent world model. By encoding language-defined safety semantics into a lightweight latent classifier, LSRE enables real-time semantic risk assessment at 10 Hz without per-frame VLM queries. Experiments on six semantic-failure scenarios in CARLA demonstrate that LSRE attains semantic risk detection accuracy comparable to a large VLM baseline, while providing substantially earlier hazard anticipation and maintaining low computational latency. LSRE further generalizes to rarely seen semantic-similar test cases, indicating that language-guided latent classification offers an effective and deployable mechanism for semantic safety monitoring in autonomous driving.
Robotics 23
☆ PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS
Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level engines and slower, more accessible Python frameworks. To address this, we introduce PyBatchRender, a Python library for high-throughput, batched 3D rendering that achieves over 1 million FPS on simple scenes. Built on the Panda3D game engine, it utilizes its mature ecosystem while enhancing performance through optimized batched rendering for up to 1000X speedups. Designed as a physics-agnostic renderer for reinforcement learning from pixels, PyBatchRender offers greater flexibility than dedicated libraries, simpler setup than typical game-engine wrappers, and speeds rivaling state-of-the-art C++ engines like Madrona. Users can create custom scenes entirely in Python with tens of lines of code, enabling rapid prototyping for scalable AI training. Open-source and easy to integrate, it serves to democratize high-performance 3D simulation for researchers and developers. The library is available at https://github.com/dolphin-in-a-coma/PyBatchRender.
☆ SAHA: Supervised Autonomous HArvester for selective forest thinning
Forestry plays a vital role in our society, creating significant ecological, economic, and recreational value. Efficient forest management involves labor-intensive and complex operations. One essential task for maintaining forest health and productivity is selective thinning, which requires skilled operators to remove specific trees to create optimal growing conditions for the remaining ones. In this work, we present a solution based on a small-scale robotic harvester (SAHA) designed for executing this task with supervised autonomy. We build on a 4.5-ton harvester platform and implement key hardware modifications for perception and automatic control. We implement learning- and model-based approaches for precise control of hydraulic actuators, accurate navigation through cluttered environments, robust state estimation, and reliable semantic estimation of terrain traversability. Integrating state-of-the-art techniques in perception, planning, and control, our robotic harvester can autonomously navigate forest environments and reach targeted trees for selective thinning. We present experimental results from extensive field trials over kilometer-long autonomous missions in northern European forests, demonstrating the harvester's ability to operate in real forests. We analyze the performance and provide the lessons learned for advancing robotic forest management.
☆ Bridging Language Gaps: Utilizing Interactive Robots to Teach Cantonese in Real-Life Contexts for Newly-Arrived Children
Hong Kong's education system is notably multicultural, including local, non-Chinese-speaking, and newly arrived students (NAS) (Mandarine Chinese-speaking). NAS can guess the meaning of vocabulary but cannot speak out, presenting unique challenges for them, particularly language barriers and cultural differences. These challenges hinder their academic success and social integration, leading to feelings of isolation and demotivation. Current resources often fail to address the emotional well-being of these students and predominantly focus on English language acquisition, leaving a gap in support for learning Cantonese and navigating the local cultural landscape. This study explores the effectiveness of an interactive robot, Boon Boon, in teaching Cantonese through real-life contexts to enhance NAS children learning engagement and motivation. The research questions are: (1) How does interactive robot-empowered scenario learning influence the learning engagement and motivation of NAS in learning Cantonese? and (2) What is the impact of a robot-empowered scenario learning system on the Cantonese language proficiency of NAS? Fourteen children are invited to participate in a four-day learning program with Boon Boon. The preliminary result indicated that Boon Boon drove students' attention to learning and academic achievement. Future research will focus on long-term assessments of robot-empowered learning's effectiveness and explore the scalability of this approach across diverse educational settings and cultural backgrounds.
☆ LiveBo: Empowering Non-Chinese Speaking Students through AI-Driven Real-Life Scenarios in Cantonese
Language learning is a multifaceted process. Insufficient vocabulary can hinder communication and lead to demotivation. For non-Chinese speaking (NCS) students, learning Traditional Chinese (Cantonese) poses distinct challenges, particularly due to the complexity of converting spoken and written forms. To address this issue, this study examines the effectiveness of real-life scenario simulations integrated with interactive social robots in enhancing NCS student engagement and language acquisition. The research employs a quasi-experimental design involving NCS students who interact with an AI-driven, robot-assisted language learning system, LiveBo. The study aims to assess the impact of this innovative approach on active participation and motivation. Data are collected through proficiency tests, questionnaires and semi-structured interviews. Findings indicate that NCS students experience positive improvements in behavioural and emotional engagement, motivation and learning outcomes, highlighting the potential of integrating novel technologies in language education. We plan to compare with the control group in the future. This study highlights the significance of interactive and immersive learning experiences in promoting motivation and enhancing language acquisition among NCS students.
☆ MotiBo: The Impact of Interactive Digital Storytelling Robots on Student Motivation through Self-Determination Theory
Creativity is increasingly recognized as an important skill in education, and storytelling can enhance motivation and engagement among students. However, conventional storytelling methods often lack the interactive elements necessary to engage students. To this end, this study examines the impact of an interactive digital storytelling system incorporating a human-like robot on student engagement and creativity. The study aims to compare engagement levels across three modalities: paper-based, PowerPoint, and robot-assisted storytelling, MotiBo. Utilizing a quasi-experimental design, this work involves three groups of students who interact with the storytelling system over a five-day learning. Findings reveal that students using MotiBo exhibit statistically significant improvement in behavioural and cognitive engagement compared to those using traditional methods. These results suggest that the integration of novel technologies can effectively enhance the learning experience, ultimately promoting creativity and self-learning ability in educational settings. Future research will investigate the long-term effects of these technologies on learning outcomes and explore their potential for broader applications in diverse educational contexts.
☆ Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission
To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. LiDAR sensors capture 3D in real time, but produce sparce point clouds. Therefore, this paper presents a high-speed LiDAR point cloud densification method to generate dense 3D scene with minimal latency, addressing the need for on-the-fly depth completion while maintaining real-time performance. Our approach combines multiple LiDAR inputs with high-resolution color images and applies a joint bilateral filtering strategy implemented through a convolutional neural network architecture. Experiments demonstrate that the proposed method produces dense depth maps at full HD resolution in real time (30 fps), which is over 15x faster than a recent training-based depth completion approach. The resulting dense point clouds exhibit accurate geometry without multiview inconsistencies or ghosting artifacts.
☆ EduSim-LLM: An Educational Platform Integrating Large Language Models and Robotic Simulation for Beginners
In recent years, the rapid development of Large Language Models (LLMs) has significantly enhanced natural language understanding and human-computer interaction, creating new opportunities in the field of robotics. However, the integration of natural language understanding into robotic control is an important challenge in the rapid development of human-robot interaction and intelligent automation industries. This challenge hinders intuitive human control over complex robotic systems, limiting their educational and practical accessibility. To address this, we present the EduSim-LLM, an educational platform that integrates LLMs with robot simulation and constructs a language-drive control model that translates natural language instructions into executable robot behavior sequences in CoppeliaSim. We design two human-robot interaction models: direct control and autonomous control, conduct systematic simulations based on multiple language models, and evaluate multi-robot collaboration, motion planning, and manipulation capabilities. Experiential results show that LLMs can reliably convert natural language into structured robot actions; after applying prompt-engineering templates instruction-parsing accuracy improves significantly; as task complexity increases, overall accuracy rate exceeds 88.9% in the highest complexity tests.
☆ DST-Calib: A Dual-Path, Self-Supervised, Target-Free LiDAR-Camera Extrinsic Calibration Network
LiDAR-camera extrinsic calibration is essential for multi-modal data fusion in robotic perception systems. However, existing approaches typically rely on handcrafted calibration targets (e.g., checkerboards) or specific, static scene types, limiting their adaptability and deployment in real-world autonomous and robotic applications. This article presents the first self-supervised LiDAR-camera extrinsic calibration network that operates in an online fashion and eliminates the need for specific calibration targets. We first identify a significant generalization degradation problem in prior methods, caused by the conventional single-sided data augmentation strategy. To overcome this limitation, we propose a novel double-sided data augmentation technique that generates multi-perspective camera views using estimated depth maps, thereby enhancing robustness and diversity during training. Built upon this augmentation strategy, we design a dual-path, self-supervised calibration framework that reduces the dependence on high-precision ground truth labels and supports fully adaptive online calibration. Furthermore, to improve cross-modal feature association, we replace the traditional dual-branch feature extraction design with a difference map construction process that explicitly correlates LiDAR and camera features. This not only enhances calibration accuracy but also reduces model complexity. Extensive experiments conducted on five public benchmark datasets, as well as our own recorded dataset, demonstrate that the proposed method significantly outperforms existing approaches in terms of generalizability.
☆ ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation
Existing methods for multi-agent navigation typically assume fully known environments, offering limited support for partially known scenarios such as warehouses or factory floors. There, agents may need to plan trajectories that balance their own path optimality with their ability to collect and share information about the environment that can help their teammates reach their own goals. To these ends, we propose ORION, a novel deep reinforcement learning framework for cooperative multi-agent online navigation in partially known environments. Starting from an imperfect prior map, ORION trains agents to make decentralized decisions, coordinate to reach their individual targets, and actively reduce map uncertainty by sharing online observations in a closed perception-action loop. We first design a shared graph encoder that fuses prior map with online perception into a unified representation, providing robust state embeddings under dynamic map discrepancies. At the core of ORION is an option-critic framework that learns to reason about a set of high-level cooperative modes that translate into sequences of low-level actions, allowing agents to switch between individual navigation and team-level exploration adaptively. We further introduce a dual-stage cooperation strategy that enables agents to assist teammates under map uncertainty, thereby reducing the overall makespan. Across extensive maze-like maps and large-scale warehouse environments, our simulation results show that ORION achieves high-quality, real-time decentralized cooperation over varying team sizes, outperforming state-of-the-art classical and learning-based baselines. Finally, we validate ORION on physical robot teams, demonstrating its robustness and practicality for real-world cooperative navigation.
☆ VISO: Robust Underwater Visual-Inertial-Sonar SLAM with Photometric Rendering for Dense 3D Reconstruction
Visual challenges in underwater environments significantly hinder the accuracy of vision-based localisation and the high-fidelity dense reconstruction. In this paper, we propose VISO, a robust underwater SLAM system that fuses a stereo camera, an inertial measurement unit (IMU), and a 3D sonar to achieve accurate 6-DoF localisation and enable efficient dense 3D reconstruction with high photometric fidelity. We introduce a coarse-to-fine online calibration approach for extrinsic parameters estimation between the 3D sonar and the camera. Additionally, a photometric rendering strategy is proposed for the 3D sonar point cloud to enrich the sonar map with visual information. Extensive experiments in a laboratory tank and an open lake demonstrate that VISO surpasses current state-of-the-art underwater and visual-based SLAM algorithms in terms of localisation robustness and accuracy, while also exhibiting real-time dense 3D reconstruction performance comparable to the offline dense mapping method.
☆ Latent Space Reinforcement Learning for Multi-Robot Exploration
Autonomous mapping of unknown environments is a critical challenge, particularly in scenarios where time is limited. Multi-agent systems can enhance efficiency through collaboration, but the scalability of motion-planning algorithms remains a key limitation. Reinforcement learning has been explored as a solution, but existing approaches are constrained by the limited input size required for effective learning, restricting their applicability to discrete environments. This work addresses that limitation by leveraging autoencoders to perform dimensionality reduction, compressing high-fidelity occupancy maps into latent state vectors while preserving essential spatial information. Additionally, we introduce a novel procedural generation algorithm based on Perlin noise, designed to generate topologically complex training environments that simulate asteroid fields, caves and forests. These environments are used for training the autoencoder and the navigation algorithm using a hierarchical deep reinforcement learning framework for decentralized coordination. We introduce a weighted consensus mechanism that modulates reliance on shared data via a tuneable trust parameter, ensuring robustness to accumulation of errors. Experimental results demonstrate that the proposed system scales effectively with number of agents and generalizes well to unfamiliar, structurally distinct environments and is resilient in communication-constrained settings.
☆ Towards reliable subsea object recovery: a simulation study of an auv with a suction-actuated end effector
Autonomous object recovery in the hadal zone is challenging due to extreme hydrostatic pressure, limited visibility and currents, and the need for precise manipulation at full ocean depth. Field experimentation in such environments is costly, high-risk, and constrained by limited vehicle availability, making early validation of autonomous behaviors difficult. This paper presents a simulation-based study of a complete autonomous subsea object recovery mission using a Hadal Small Vehicle (HSV) equipped with a three-degree-of-freedom robotic arm and a suction-actuated end effector. The Stonefish simulator is used to model realistic vehicle dynamics, hydrodynamic disturbances, sensing, and interaction with a target object under hadal-like conditions. The control framework combines a world-frame PID controller for vehicle navigation and stabilization with an inverse-kinematics-based manipulator controller augmented by acceleration feed-forward, enabling coordinated vehicle - manipulator operation. In simulation, the HSV autonomously descends from the sea surface to 6,000 m, performs structured seafloor coverage, detects a target object, and executes a suction-based recovery. The results demonstrate that high-fidelity simulation provides an effective and low-risk means of evaluating autonomous deep-sea intervention behaviors prior to field deployment.
☆ Scalable Data-Driven Reachability Analysis and Control via Koopman Operators with Conformal Coverage Guarantees
We propose a scalable reachability-based framework for probabilistic, data-driven safety verification of unknown nonlinear dynamics. We use Koopman theory with a neural network (NN) lifting function to learn an approximate linear representation of the dynamics and design linear controllers in this space to enable closed-loop tracking of a reference trajectory distribution. Closed-loop reachable sets are efficiently computed in the lifted space and mapped back to the original state space via NN verification tools. To capture model mismatch between the Koopman dynamics and the true system, we apply conformal prediction to produce statistically-valid error bounds that inflate the reachable sets to ensure the true trajectories are contained with a user-specified probability. These bounds generalize across references, enabling reuse without recomputation. Results on high-dimensional MuJoCo tasks (11D Hopper, 28D Swimmer) and 12D quadcopters show improved reachable set coverage rate, computational efficiency, and conservativeness over existing methods.
comment: Under review, 28 pages, 12 figures
☆ Topological Mapping and Navigation using a Monocular Camera based on AnyLoc
This paper proposes a method for topological mapping and navigation using a monocular camera. Based on AnyLoc, keyframes are converted into descriptors to construct topological relationships, enabling loop detection and map building. Unlike metric maps, topological maps simplify path planning and navigation by representing environments with key nodes instead of precise coordinates. Actions for visual navigation are determined by comparing segmented images with the image associated with target nodes. The system relies solely on a monocular camera, ensuring fast map building and navigation using key nodes. Experiments show effective loop detection and navigation in real and simulation environments without pre-training. Compared to a ResNet-based method, this approach improves success rates by 60.2% on average while reducing time and space costs, offering a lightweight solution for robot and human navigation in various scenarios.
comment: Published in Proc. IEEE CASE 2025. 7 pages, 11 figures
♻ ☆ No Minima, No Collisions: Combining Modulation and Control Barrier Function Strategies for Feasible Dynamic Collision Avoidance
Control Barrier Function Quadratic Programs (CBF-QPs) have become a central tool for real-time safety-critical control due to their applicability to general control-affine systems and their ability to enforce constraints through optimization. Yet, they often generate trajectories with undesirable local minima that prevent convergence to goals. On the other hand, Modulation of Dynamical Systems (Mod-DS) methods (including normal, reference, and on-manifold variants) reshape nominal vector fields geometrically and achieve obstacle avoidance with few or even no local minima. However, Mod-DS provides no straightforward mechanism for handling input constraints and remains largely restricted to fully actuated systems. In this paper, we revisit the theoretical foundations of both approaches and show that, despite their seemingly different constructions, the normal Mod-DS is a special case of the CBF-QP, and the reference Mod-DS is linked to the CBF-QP through a single shared equation. These connections motivate our Modulated CBF-QP (MCBF-QP) framework, which introduces reference and on-manifold modulation variants that reduce or fully eliminate the spurious equilibria inherent to CBF-QPs for general control-affine systems operating in dynamic, cluttered environments. We validate the proposed controllers in simulated hospital settings and in real-world experiments on fully actuated Ridgeback robots and underactuated Fetch platforms. Across all evaluations, Modulated CBF-QPs consistently outperform standard CBF-QPs on every performance metric.
♻ ☆ Nonlinear Oscillatory Response of Automated Vehicle Car-following: Theoretical Analysis with Traffic State and Control Input Limits
This paper presents a framework grounded in the theory of describing function (DF) and incremental-input DF to theoretically analyze the nonlinear oscillatory response of automated vehicles (AVs) car-following (CF) amidst traffic oscillations, considering the limits of traffic state and control input. While prevailing approaches largely ignore these limits (i.e., saturation of acceleration/deceleration and speed) and focus on linear string stability analysis, this framework establishes a basis for theoretically analyzing the frequency response of AV systems with nonlinearities imposed by these limits. To this end, trajectories of CF pairs are decomposed into nominal and oscillatory trajectories, subsequently, the controlled AV system is repositioned within the oscillatory trajectory coordinates. Built on this base, DFs are employed to approximate the frequency responses of nonlinear saturation components by using their first harmonic output, thereby capturing the associated amplification ratio and phase shift. Considering the closed-loop nature of AV control systems, where system states and control input mutually influence each other, amplification ratios and phase shifts are balanced within the loop to ensure consistency. This balancing process may render multiple solutions, hence the incremental-input DF is further applied to identify the reasonable ones. The proposed method is validated by estimations from Simulink, and further comparisons with prevailing methods are conducted. Results confirm the alignment of our framework with Simulink results and exhibit its superior accuracy in analysis compared to the prevailing methods. Furthermore, the framework proves valuable in string stability analysis, especially when conventional linear methods offer misleading insights.
♻ ☆ Stochastic Online Optimization for Cyber-Physical and Robotic Systems
We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. Our problem formulation accommodates constraints that model the evolution of a cyber-physical system, which has, in general, a continuous state and action space, is nonlinear, and where the state is only partially observed. We also incorporate an approximate model of the dynamics as prior knowledge into the learning process and show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms. Our online optimization framework encompasses both gradient descent and quasi-Newton methods, and we provide a unified convergence analysis of our algorithms in a non-convex setting. We also characterize the impact of modeling errors in the system dynamics on the convergence rate of the algorithms. Finally, we evaluate our algorithms in simulations of a flexible beam, a four-legged walking robot, and in real-world experiments with a ping-pong playing robot.
comment: 46 pages, 16 figures
♻ ☆ SPARC: Spine with Prismatic and Revolute Compliance for Quadruped Robots
We present SPARC, a compact, open-source 3-DoF sagittal-plane spine module that combines revolute (pitch) and prismatic (axial) motion with programmable task-space impedance for quadruped robots. The system integrates three torque-controlled actuators, a 1~kHz control board, and protected power electronics in a 1.26~kg package. A floating-base impedance controller with dynamics compensation renders tunable spring-damper behavior along horizontal, vertical, and rotational axes. Benchtop experiments validate the approach: quasi-static tests demonstrate linear force-displacement characteristics with commanded horizontal stiffness spanning 300--700~N/m ($\leq 1.5\%$ error, $R^2 \geq 0.992$), while dynamic trials confirm predictable damping behavior across multiple settings. Furthermore, simulation studies reveal that adapting spine stiffness based on terrain slope and stride length significantly reduces the cost of transport. SPARC provides an open-source platform for systematic studies of spine compliance in legged locomotion, with complete hardware and firmware resources available for community use. Github repository: https://github.com/YueWang996/sparc.git
♻ ☆ RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics NeurIPS 2025
Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), recent approaches are still not qualified to accurately understand the complex 3D scenes and dynamically reason about the instruction-indicated locations for interaction. To this end, we propose RoboRefer, a 3D-aware VLM that can first achieve precise spatial understanding by integrating a disentangled but dedicated depth encoder via supervised fine-tuning (SFT). Moreover, RoboRefer advances generalized multi-step spatial reasoning via reinforcement fine-tuning (RFT), with metric-sensitive process reward functions tailored for spatial referring tasks. To support SFT and RFT training, we introduce RefSpatial, a large-scale dataset of 20M QA pairs (2x prior), covering 31 spatial relations (vs. 15 prior) and supporting complex reasoning processes (up to 5 steps). In addition, we introduce RefSpatial-Bench, a challenging benchmark filling the gap in evaluating spatial referring with multi-step reasoning. Experiments show that SFT-trained RoboRefer achieves state-of-the-art spatial understanding, with an average success rate of 89.6%. RFT-trained RoboRefer further outperforms all other baselines by a large margin, even surpassing Gemini-2.5-Pro by 17.4% in average accuracy on RefSpatial-Bench. Notably, RoboRefer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (e,g., UR5, G1 humanoid) in cluttered real-world scenes.
comment: Accepted by NeurIPS 2025. Project page: https://zhoues.github.io/RoboRefer/
♻ ☆ P2U-SLAM: A Monocular Wide-FoV SLAM System Based on Point Uncertainty and Pose Uncertainty
This paper presents P2U-SLAM, a visual Simultaneous Localization And Mapping (SLAM) system with a wide Field of View (FoV) camera, which utilizes pose uncertainty and point uncertainty. While the wide FoV enables considerable repetitive observations of historical map points for matching cross-view features, the data properties of the historical map points and the poses of historical keyframes have changed during the optimization process. The neglect of data property changes results in the lack of partial information matrices in optimization, increasing the risk of long-term positioning performance degradation. The purpose of our research is to mitigate the risks posed by wide-FoV visual input to the SLAM system. Based on the conditional probability model, this work reveals the definite impacts of the above data properties changes on the optimization process, concretizes these impacts as point uncertainty and pose uncertainty, and gives their specific mathematical form. P2U-SLAM embeds point uncertainty into the tracking module and pose uncertainty into the local mapping module respectively, and updates these uncertainties after each optimization operation including local mapping, map merging, and loop closing. We present an exhaustive evaluation on 27 sequences from two popular public datasets with wide-FoV visual input. P2U-SLAM shows excellent performance compared with other state-of-the-art methods. The source code will be made publicly available at https://github.com/BambValley/P2U-SLAM.
comment: Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS). The source code will be made publicly available at https://github.com/BambValley/P2U-SLAM
♻ ☆ Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration
Deployable service and delivery robots struggle to navigate multi-floor buildings to reach object goals, as existing systems fail due to single-floor assumptions and requirements for offline, globally consistent maps. Multi-floor environments pose unique challenges including cross-floor transitions and vertical spatial reasoning, especially navigating unknown buildings. Object-Goal Navigation benchmarks like HM3D and MP3D also capture this multi-floor reality, yet current methods lack support for online, floor-aware navigation. To bridge this gap, we propose \textbf{\textit{ASCENT}}, an online framework for Zero-Shot Object-Goal Navigation that enables robots to operate without pre-built maps or retraining on new object categories. It introduces: (1) a \textbf{Multi-Floor Abstraction} module that dynamically constructs hierarchical representations with stair-aware obstacle mapping and cross-floor topology modeling, and (2) a \textbf{Coarse-to-Fine Reasoning} module that combines frontier ranking with LLM-driven contextual analysis for multi-floor navigation decisions. We evaluate on HM3D and MP3D benchmarks, outperforming state-of-the-art zero-shot approaches, and demonstrate real-world deployment on a quadruped robot.
comment: Accepted to IEEE Robotics and Automation Letters (RAL). Project Page at https://zeying-gong.github.io/projects/ascent
♻ ☆ Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
Unmanned aerial vehicles (UAVs) have emerged as powerful embodied agents. One of the core abilities is autonomous navigation in large-scale three-dimensional environments. Existing navigation policies, however, are typically optimized for low-level objectives such as obstacle avoidance and trajectory smoothness, lacking the ability to incorporate high-level semantics into planning. To bridge this gap, we propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions, thereby enabling agents to rank candidate trajectories by their semantic plausibility and navigational utility. ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection (FFP), which projects past frames into future viewpoints to provide coarse geometric priors. This module mitigates representational uncertainty in long-distance visual generation and captures the mapping between 3D trajectories and egocentric observations. Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments.
♻ ☆ Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation AAAI 2026
In open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to proximity-based regions without considering affordances, resulting in frequent manipulation failures. We propose Affordance-Guided Coarse-to-Fine Exploration, a zero-shot framework for base placement that integrates semantic understanding from vision-language models (VLMs) with geometric feasibility through an iterative optimization process. Our method constructs cross-modal representations, namely Affordance RGB and Obstacle Map+, to align semantics with spatial context. This enables reasoning that extends beyond the egocentric limitations of RGB perception. To ensure interaction is guided by task-relevant affordances, we leverage coarse semantic priors from VLMs to guide the search toward task-relevant regions and refine placements with geometric constraints, thereby reducing the risk of convergence to local optima. Evaluated on five diverse open-vocabulary mobile manipulation tasks, our system achieves an 85% success rate, significantly outperforming classical geometric planners and VLM-based methods. This demonstrates the promise of affordance-aware and multimodal reasoning for generalizable, instruction-conditioned planning in OVMM.
comment: Accepted to AAAI 2026
Robotics 23
☆ Calling for Backup: How Children Navigate Successive Robot Communication Failures
How do children respond to repeated robot errors? While prior research has examined adult reactions to successive robot errors, children's responses remain largely unexplored. In this study, we explore children's reactions to robot social errors and performance errors. For the latter, this study reproduces the successive robot failure paradigm of Liu et al. with child participants (N=59, ages 8-10) to examine how young users respond to repeated robot conversational errors. Participants interacted with a robot that failed to understand their prompts three times in succession, with their behavioral responses video-recorded and analyzed. We found both similarities and differences compared to adult responses from the original study. Like adults, children adjusted their prompts, modified their verbal tone, and exhibited increasingly emotional non-verbal responses throughout successive errors. However, children demonstrated more disengagement behaviors, including temporarily ignoring the robot or actively seeking an adult. Errors did not affect participants' perception of the robot, suggesting more flexible conversational expectations in children. These findings inform the design of more effective and developmentally appropriate human-robot interaction systems for young users.
☆ DefVINS: Visual-Inertial Odometry for Deformable Scenes
Deformable scenes violate the rigidity assumptions underpinning classical visual-inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or severe drift when deformation dominates visual parallax. We introduce DefVINS, a visual-inertial odometry framework that explicitly separates a rigid, IMU-anchored state from a non--rigid warp represented by an embedded deformation graph. The system is initialized using a standard VIO procedure that fixes gravity, velocity, and IMU biases, after which non-rigid degrees of freedom are activated progressively as the estimation becomes well conditioned. An observability analysis is included to characterize how inertial measurements constrain the rigid motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and informs a conditioning-based activation strategy that prevents ill-posed updates under poor excitation. Ablation studies demonstrate the benefits of combining inertial constraints with observability-aware deformation activation, resulting in improved robustness under non-rigid environments.
comment: 4 figures, 3 tables. Submitted to RA-L
☆ Bayesian Inverse Games with High-Dimensional Multi-Modal Observations
Many multi-agent interaction scenarios can be naturally modeled as noncooperative games, where each agent's decisions depend on others' future actions. However, deploying game-theoretic planners for autonomous decision-making requires a specification of all agents' objectives. To circumvent this practical difficulty, recent work develops maximum likelihood techniques for solving inverse games that can identify unknown agent objectives from interaction data. Unfortunately, these methods only infer point estimates and do not quantify estimator uncertainty; correspondingly, downstream planning decisions can overconfidently commit to unsafe actions. We present an approximate Bayesian inference approach for solving the inverse game problem, which can incorporate observation data from multiple modalities and be used to generate samples from the Bayesian posterior over the hidden agent objectives given limited sensor observations in real time. Concretely, the proposed Bayesian inverse game framework trains a structured variational autoencoder with an embedded differentiable Nash game solver on interaction datasets and does not require labels of agents' true objectives. Extensive experiments show that our framework successfully learns prior and posterior distributions, improves inference quality over maximum likelihood estimation-based inverse game approaches, and enables safer downstream decision-making without sacrificing efficiency. When trajectory information is uninformative or unavailable, multimodal inference further reduces uncertainty by exploiting additional observation modalities.
☆ RoboReward: General-Purpose Vision-Language Reward Models for Robotics
A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotic domains, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives. Vision-language models (VLMs) have shown promise as automatic reward models, yet their effectiveness on real robot tasks is poorly understood. In this work, we aim to close this gap by introducing (1) \textbf{RoboReward}, a robotics reward dataset and benchmark built on large-scale real-robot corpora from Open X-Embodiment (OXE) and RoboArena, and (2) vision-language reward models trained on this dataset (RoboReward 4B/8B). Because OXE is success-heavy and lacks failure examples, we propose a \emph{negative examples data augmentation} pipeline that generates calibrated \emph{negatives} and \emph{near-misses} via counterfactual relabeling of successful episodes and temporal clipping to create partial-progress outcomes from the same videos. Using this framework, we produce an extensive training and evaluation dataset that spans diverse tasks and embodiments and enables systematic evaluation of whether state-of-the-art VLMs can reliably provide rewards for robotics. Our evaluation of leading open-weight and proprietary VLMs reveals that no model excels across all tasks, underscoring substantial room for improvement. We then train general-purpose 4B- and 8B-parameter models that outperform much larger VLMs in assigning rewards for short-horizon robotic tasks. Finally, we deploy the 8B-parameter reward VLM in real-robot reinforcement learning and find that it improves policy learning over Gemini Robotics-ER 1.5, a frontier physical reasoning VLM trained on robotics data, by a large margin, while substantially narrowing the gap to RL training with human-provided rewards.
☆ From 2D to 3D terrain-following area coverage path planning
An algorithm for 3D terrain-following area coverage path planning is presented. Multiple adjacent paths are generated that are (i) locally apart from each other by a distance equal to the working width of a machinery, while (ii) simultaneously floating at a projection distance equal to a specific working height above the terrain. The complexities of the algorithm in comparison to its 2D equivalent are highlighted. These include uniformly spaced elevation data generation using an Inverse Distance Weighting-approach and a local search. Area coverage path planning results for real-world 3D data within an agricultural context are presented to validate the algorithm.
comment: 6 pages, 10 figures, 1 table
☆ Vision-based Goal-Reaching Control for Mobile Robots Using a Hierarchical Learning Framework
Reinforcement learning (RL) is effective in many robotic applications, but it requires extensive exploration of the state-action space, during which behaviors can be unsafe. This significantly limits its applicability to large robots with complex actuators operating on unstable terrain. Hence, to design a safe goal-reaching control framework for large-scale robots, this paper decomposes the whole system into a set of tightly coupled functional modules. 1) A real-time visual pose estimation approach is employed to provide accurate robot states to 2) an RL motion planner for goal-reaching tasks that explicitly respects robot specifications. The RL module generates real-time smooth motion commands for the actuator system, independent of its underlying dynamic complexity. 3) In the actuation mechanism, a supervised deep learning model is trained to capture the complex dynamics of the robot and provide this model to 4) a model-based robust adaptive controller that guarantees the wheels track the RL motion commands even on slip-prone terrain. 5) Finally, to reduce human intervention, a mathematical safety supervisor monitors the robot, stops it on unsafe faults, and autonomously guides it back to a safe inspection area. The proposed framework guarantees uniform exponential stability of the actuation system and safety of the whole operation. Experiments on a 6,000 kg robot in different scenarios confirm the effectiveness of the proposed framework.
☆ NMPC-Augmented Visual Navigation and Safe Learning Control for Large-Scale Mobile Robots
A large-scale mobile robot (LSMR) is a high-order multibody system that often operates on loose, unconsolidated terrain, which reduces traction. This paper presents a comprehensive navigation and control framework for an LSMR that ensures stability and safety-defined performance, delivering robust operation on slip-prone terrain by jointly leveraging high-performance techniques. The proposed architecture comprises four main modules: (1) a visual pose-estimation module that fuses onboard sensors and stereo cameras to provide an accurate, low-latency robot pose, (2) a high-level nonlinear model predictive control that updates the wheel motion commands to correct robot drift from the robot reference pose on slip-prone terrain, (3) a low-level deep neural network control policy that approximates the complex behavior of the wheel-driven actuation mechanism in LSMRs, augmented with robust adaptive control to handle out-of-distribution disturbances, ensuring that the wheels accurately track the updated commands issued by high-level control module, and (4) a logarithmic safety module to monitor the entire robot stack and guarantees safe operation. The proposed low-level control framework guarantees uniform exponential stability of the actuation subsystem, while the safety module ensures the whole system-level safety during operation. Comparative experiments on a 6,000 kg LSMR actuated by two complex electro-hydrostatic drives, while synchronizing modules operating at different frequencies.
☆ Priority-Aware Multi-Robot Coverage Path Planning
Multi-robot systems are widely used for coverage tasks that require efficient coordination across large environments. In Multi-Robot Coverage Path Planning (MCPP), the objective is typically to minimize the makespan by generating non-overlapping paths for full-area coverage. However, most existing methods assume uniform importance across regions, limiting their effectiveness in scenarios where some zones require faster attention. We introduce the Priority-Aware MCPP (PA-MCPP) problem, where a subset of the environment is designated as prioritized zones with associated weights. The goal is to minimize, in lexicographic order, the total priority-weighted latency of zone coverage and the overall makespan. To address this, we propose a scalable two-phase framework combining (1) greedy zone assignment with local search, spanning-tree-based path planning, and (2) Steiner-tree-guided residual coverage. Experiments across diverse scenarios demonstrate that our method significantly reduces priority-weighted latency compared to standard MCPP baselines, while maintaining competitive makespan. Sensitivity analyses further show that the method scales well with the number of robots and that zone coverage behavior can be effectively controlled by adjusting priority weights.
comment: IEEE Robotics and Automation Letters, 8 pages, 10 figures
☆ LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill Orchestration
This paper presents an end-to-end LLM-based agentic exploration system for an indoor shopping task, evaluated in both Gazebo simulation and a corresponding real-world corridor layout. The robot incrementally builds a lightweight semantic map by detecting signboards at junctions and storing direction-to-POI relations together with estimated junction poses, while AprilTags provide repeatable anchors for approach and alignment. Given a natural-language shopping request, an LLM produces a constrained discrete action at each junction (direction and whether to enter a store), and a ROS finite-state main controller executes the decision by gating modular motion primitives, including local-costmap-based obstacle avoidance, AprilTag approaching, store entry, and grasping. Qualitative results show that the integrated stack can perform end-to-end task execution from user instruction to multi-store navigation and object retrieval, while remaining modular and debuggable through its text-based map and logged decision history.
☆ Optimal Transport-Based Decentralized Multi-Agent Distribution Matching
This paper presents a decentralized control framework for distribution matching in multi-agent systems (MAS), where agents collectively achieve a prescribed terminal spatial distribution. The problem is formulated using optimal transport (Wasserstein distance), which provides a principled measure of distributional discrepancy and serves as the basis for the control design. To avoid solving the global optimal transport problem directly, the distribution-matching objective is reformulated into a tractable per-agent decision process, enabling each agent to identify its desired terminal locations using only locally available information. A sequential weight-update rule is introduced to construct feasible local transport plans, and a memory-based correction mechanism is incorporated to maintain reliable operation under intermittent and range-limited communication. Convergence guarantees are established, showing cycle-wise improvement of a surrogate transport cost under both linear and nonlinear agent dynamics. Simulation results demonstrate that the proposed framework achieves effective and scalable distribution matching while operating fully in a decentralized manner.
☆ Variable Elimination in Hybrid Factor Graphs for Discrete-Continuous Inference & Estimation
Many hybrid problems in robotics involve both continuous and discrete components, and modeling them together for estimation tasks has been a long standing and difficult problem. Hybrid Factor Graphs give us a mathematical framework to model these types of problems, however existing approaches for solving them are based on approximations. In this work, we propose an efficient Hybrid Factor Graph framework alongwith a variable elimination algorithm to produce a hybrid Bayes network, which can then be used for exact Maximum A Posteriori estimation and marginalization over both sets of variables. Our approach first develops a novel hybrid Gaussian factor which can connect to both discrete and continuous variables, and a hybrid conditional which can represent multiple continuous hypotheses conditioned on the discrete variables. Using these representations, we derive the process of hybrid variable elimination under the Conditional Linear Gaussian scheme, giving us exact posteriors as hybrid Bayes network. To bound the number of discrete hypotheses, we use a tree-structured representation of the factors coupled with a simple pruning and probabilistic assignment scheme, which allows for tractable inference. We demonstrate the applicability of our framework on a SLAM dataset with ambiguous measurements, where discrete choices for the most likely measurement have to be made. Our demonstrated results showcase the accuracy, generality, and simplicity of our hybrid factor graph framework.
☆ Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations ICLR 2026
Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a Stochastic Differential Equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce Contractive Diffusion Policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.
comment: Under review at ICLR 2026
☆ Simulations of MRI Guided and Powered Ferric Applicators for Tetherless Delivery of Therapeutic Interventions
Magnetic Resonance Imaging (MRI) is a well-established modality for pre-operative planning and is also explored for intra-operative guidance of procedures such as intravascular interventions. Among the experimental robot-assisted technologies, the magnetic field gradients of the MRI scanner are used to power and maneuver ferromagnetic applicators for accessing sites in the patient's body via the vascular network. In this work, we propose a computational platform for preoperative planning and modeling of MRI-powered applicators inside blood vessels. This platform was implemented as a two-way data and command pipeline that links the MRI scanner, the computational core, and the operator. The platform first processes multi-slice MR data to extract the vascular bed and then fits a virtual corridor inside the vessel. This corridor serves as a virtual fixture (VF), a forbidden region for the applicators to avoid vessel perforation or collision. The geometric features of the vessel centerline, the VF, and MRI safety compliance (dB/dt, max available gradient) are then used to generate magnetic field gradient waveforms. Different blood flow profiles can be user-selected, and those parameters are used for modeling the applicator's maneuvering. The modeling module further generates cues about whether the selected vascular path can be safely maneuvered. Given future experimental studies that require a real-time operation, the platform was implemented on the Qt framework (C/C++) with software modules performing specific tasks running on dedicated threads: PID controller, generation of VF, generation of MR gradient waveforms.
comment: 9 pages, 8 figures, published in ICBBB 2022
☆ From Perception to Symbolic Task Planning: Vision-Language Guided Human-Robot Collaborative Structured Assembly
Human-robot collaboration (HRC) in structured assembly requires reliable state estimation and adaptive task planning under noisy perception and human interventions. To address these challenges, we introduce a design-grounded human-aware planning framework for human-robot collaborative structured assembly. The framework comprises two coupled modules. Module I, Perception-to-Symbolic State (PSS), employs vision-language models (VLMs) based agents to align RGB-D observations with design specifications and domain knowledge, synthesizing verifiable symbolic assembly states. It outputs validated installed and uninstalled component sets for online state tracking. Module II, Human-Aware Planning and Replanning (HPR), performs task-level multi-robot assignment and updates the plan only when the observed state deviates from the expected execution outcome. It applies a minimal-change replanning rule to selectively revise task assignments and preserve plan stability even under human interventions. We validate the framework on a 27-component timber-frame assembly. The PSS module achieves 97% state synthesis accuracy, and the HPR module maintains feasible task progression across diverse HRC scenarios. Results indicate that integrating VLM-based perception with knowledge-driven planning improves robustness of state estimation and task planning under dynamic conditions.
☆ Value Vision-Language-Action Planning & Search
Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic manipulation, yet they remain fundamentally limited by their reliance on behavior cloning, leading to brittleness under distribution shift. While augmenting pretrained models with test-time search algorithms like Monte Carlo Tree Search (MCTS) can mitigate these failures, existing formulations rely solely on the VLA prior for guidance, lacking a grounded estimate of expected future return. Consequently, when the prior is inaccurate, the planner can only correct action selection via the exploration term, which requires extensive simulation to become effective. To address this limitation, we introduce Value Vision-Language-Action Planning and Search (V-VLAPS), a framework that augments MCTS with a lightweight, learnable value function. By training a simple multilayer perceptron (MLP) on the latent representations of a fixed VLA backbone (Octo), we provide the search with an explicit success signal that biases action selection toward high-value regions. We evaluate V-VLAPS on the LIBERO robotic manipulation suite, demonstrating that our value-guided search improves success rates by over 5 percentage points while reducing the average number of MCTS simulations by 5-15 percent compared to baselines that rely only on the VLA prior.
comment: 10 pages, 3 figures
☆ Analyzing the Shopping Journey: Computing Shelf Browsing Visits in a Physical Retail Store
Motivated by recent challenges in the deployment of robots into customer-facing roles within retail, this work introduces a study of customer activity in physical stores as a step toward autonomous understanding of shopper intent. We introduce an algorithm that computes shoppers' ``shelf visits'' -- capturing their browsing behavior in the store. Shelf visits are extracted from trajectories obtained via machine vision-based 3D tracking and overhead cameras. We perform two independent calibrations of the shelf visit algorithm, using distinct sets of trajectories (consisting of 8138 and 15129 trajectories), collected in different stores and labeled by human reviewers. The calibrated models are then evaluated on trajectories held out of the calibration process both from the same store on which calibration was performed and from the other store. An analysis of the results shows that the algorithm can recognize customers' browsing activity when evaluated in an environment different from the one on which calibration was performed. We then use the model to analyze the customers' ``browsing patterns'' on a large set of trajectories and their relation to actual purchases in the stores. Finally, we discuss how shelf browsing information could be used for retail planning and in the domain of human-robot interaction scenarios.
♻ ☆ Flattening Hierarchies with Policy Bootstrapping NeurIPS 2025
Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language processing. However, scaling GCRL to longer horizons remains challenging due to the combination of sparse rewards and discounting, which obscures the comparative advantages of primitive actions with respect to distant goals. Hierarchical RL methods achieve strong empirical results on long-horizon goal-reaching tasks, but their reliance on modular, timescale-specific policies and subgoal generation introduces significant additional complexity and hinders scaling to high-dimensional goal spaces. In this work, we introduce an algorithm to train a flat (non-hierarchical) goal-conditioned policy by bootstrapping on subgoal-conditioned policies with advantage-weighted importance sampling. Our approach eliminates the need for a generative model over the (sub)goal space, which we find is key for scaling to high-dimensional control in large state spaces. We further show that existing hierarchical and bootstrapping-based approaches correspond to specific design choices within our derivation. Across a comprehensive suite of state- and pixel-based locomotion and manipulation benchmarks, our method matches or surpasses state-of-the-art offline GCRL algorithms and scales to complex, long-horizon tasks where prior approaches fail. Project page: https://johnlyzhou.github.io/saw/
comment: NeurIPS 2025 (Spotlight, top 3.2%)
♻ ☆ Iterative Tuning of Nonlinear Model Predictive Control for Robotic Manufacturing Tasks
Manufacturing processes are often perturbed by drifts in the environment and wear in the system, requiring control re-tuning even in the presence of repetitive operations. This paper presents an iterative learning framework for automatic tuning of Nonlinear Model Predictive Control (NMPC) weighting matrices based on task-level performance feedback. Inspired by norm-optimal Iterative Learning Control (ILC), the proposed method adaptively adjusts NMPC weights Q and R across task repetitions to minimize key performance indicators (KPIs) related to tracking accuracy, control effort, and saturation. Unlike gradient-based approaches that require differentiating through the NMPC solver, we construct an empirical sensitivity matrix, enabling structured weight updates without analytic derivatives. The framework is validated through simulation on a UR10e robot performing carbon fiber winding on a tetrahedral core. Results demonstrate that the proposed approach converges to near-optimal tracking performance (RMSE within 0.3% of offline Bayesian Optimization (BO)) in just 4 online repetitions, compared to 100 offline evaluations required by BO algorithm. The method offers a practical solution for adaptive NMPC tuning in repetitive robotic tasks, combining the precision of carefully optimized controllers with the flexibility of online adaptation.
♻ ☆ Digital Twin based Automatic Reconfiguration of Robotic Systems in Smart Environments SC2
Robotic systems have become integral to smart environments, enabling applications ranging from urban surveillance and automated agriculture to industrial automation. However, their effective operation in dynamic settings - such as smart cities and precision farming - is challenged by continuously evolving topographies and environmental conditions. Traditional control systems often struggle to adapt quickly, leading to inefficiencies or operational failures. To address this limitation, we propose a novel framework for autonomous and dynamic reconfiguration of robotic controllers using Digital Twin technology. Our approach leverages a virtual replica of the robot's operational environment to simulate and optimize movement trajectories in response to real-world changes. By recalculating paths and control parameters in the Digital Twin and deploying the updated code to the physical robot, our method ensures rapid and reliable adaptation without manual intervention. This work advances the integration of Digital Twins in robotics, offering a scalable solution for enhancing autonomy in smart, dynamic environments.
comment: Accepted for presentation to 11th IEEE International Smart Cities Conference (ISC2 2025)
♻ ☆ Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
This paper addresses the Kidnapped Robot Problem (KRP), a core localization challenge of relocalizing a robot in a known map without prior pose estimate when localization loss or at SLAM initialization. For this purpose, a passive 2-D global relocalization framework is proposed. It estimates the global pose efficiently and reliably from a single LiDAR scan and an occupancy grid map while the robot remains stationary, thereby enhancing the long-term autonomy of mobile robots. The proposed framework casts global relocalization as a non-convex problem and solves it via the multi-hypothesis scheme with batched multi-stage inference and early termination, balancing completeness and efficiency. The Rapidly-exploring Random Tree (RRT), under traversability constraints, asymptotically covers the reachable space to generate sparse, uniformly distributed feasible positional hypotheses, fundamentally reducing the sampling space. The hypotheses are preliminarily ordered by the proposed Scan Mean Absolute Difference (SMAD), a coarse beam-error level metric that facilitates the early termination by prioritizing high-likelihood candidates. The SMAD computation is optimized for non-panoramic scans. The Translation-Affinity Scan-to-Map Alignment Metric (TAM) is proposed for reliable orientation selection at hypothesized positions and accurate final pose evaluation to mitigate degradation in conventional likelihood-field metrics under translational uncertainty induced by sparse hypotheses, as well as non-panoramic LiDAR scan and environmental changes. Real-world experiments on a resource-constrained mobile robot with non-panoramic LiDAR scans show that the proposed framework achieves competitive performance in both global relocalization success rate and computational efficiency.
comment: 10 pages, 8 figures. This work has been submitted to the IEEE for possible publication
♻ ☆ NeRF-VIO: Map-Based Visual-Inertial Odometry with Initialization Leveraging Neural Radiance Fields
A prior map serves as a foundational reference for localization in context-aware applications such as augmented reality (AR). Providing valuable contextual information about the environment, the prior map is a vital tool for mitigating drift. In this paper, we propose a map-based visual-inertial localization algorithm (NeRF-VIO) with initialization using neural radiance fields (NeRF). Our algorithm utilizes a multilayer perceptron model and redefines the loss function as the geodesic distance on \(SE(3)\), ensuring the invariance of the initialization model under a frame change within \(\mathfrak{se}(3)\). The evaluation demonstrates that our model outperforms existing NeRF-based initialization solution in both accuracy and efficiency. By integrating a two-stage update mechanism within a multi-state constraint Kalman filter (MSCKF) framework, the state of NeRF-VIO is constrained by both captured images from an onboard camera and rendered images from a pre-trained NeRF model. The proposed algorithm is validated using a real-world AR dataset, the results indicate that our two-stage update pipeline outperforms MSCKF across all data sequences.
♻ ☆ PLK-Calib: Single-shot and Target-less LiDAR-Camera Extrinsic Calibration using Plücker Lines
Accurate LiDAR-Camera (LC) calibration is challenging but crucial for autonomous systems and robotics. In this paper, we propose two single-shot and target-less algorithms to estimate the calibration parameters between LiDAR and camera using line features. The first algorithm constructs line-to-line constraints by defining points-to-line projection errors and minimizes the projection error. The second algorithm (PLK-Calib) utilizes the co-perpendicular and co-parallel geometric properties of lines in Plücker (PLK) coordinate, and decouples the rotation and translation into two constraints, enabling more accurate estimates. Our degenerate analysis and Monte Carlo simulation indicate that three nonparallel line pairs are the minimal requirements to estimate the extrinsic parameters. Furthermore, we collect an LC calibration dataset with varying extrinsic under three different scenarios and use it to evaluate the performance of our proposed algorithms.
♻ ☆ Towards Balanced Behavior Cloning from Imbalanced Datasets
Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art methods default to treating each element of the human's dataset as equally important. So if -- for instance -- the majority of the human's data focuses on reaching a goal, and only a few state-action pairs move to avoid an obstacle, the learning algorithm will place greater emphasis on goal reaching. More generally, misalignment between the relative amounts of data and the importance of that data causes fundamental problems for imitation learning approaches. In this paper we analyze and develop learning methods that automatically account for mixed datasets. We formally prove that imbalanced data leads to imbalanced policies when each state-action pair is weighted equally; these policies emulate the most represented behaviors, and not the human's complex, multi-task demonstrations. We next explore algorithms that rebalance offline datasets (i.e., reweight the importance of different state-action pairs) without human oversight. Reweighting the dataset can enhance the overall policy performance. However, there is no free lunch: each method for autonomously rebalancing brings its own pros and cons. We formulate these advantages and disadvantages, helping other researchers identify when each type of approach is most appropriate. We conclude by introducing a novel meta-gradient rebalancing algorithm that addresses the primary limitations behind existing approaches. Our experiments show that dataset rebalancing leads to better downstream learning, improving the performance of general imitation learning algorithms without requiring additional data collection. See our project website: https://collab.me.vt.edu/data_curation/.
Robotics 16
☆ Space Debris Removal using Nano-Satellites controlled by Low-Power Autonomous Agents
Space debris is an ever-increasing problem in space travel. There are already many old, no longer functional spacecraft and debris orbiting the earth, which endanger both the safe operation of satellites and space travel. Small nano-satellite swarms can address this problem by autonomously de-orbiting debris safely into the Earth's atmosphere. This work builds on the recent advances of autonomous agents deployed in resource-constrained platforms and shows a first simplified approach how such intelligent and autonomous nano-satellite swarms can be realized. We implement our autonomous agent software on wireless microcontrollers and perform experiments on a specialized test-bed to show the feasibility and overall energy efficiency of our approach.
comment: This is an open-access, author-archived version of a manuscript published in European Conference on Multi-Agent Systems 2024
☆ Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers IROS 2025
In domestic environments, robots require a comprehensive understanding of their surroundings to interact effectively and intuitively with untrained humans. In this paper, we propose DVEFormer - an efficient RGB-D Transformer-based approach that predicts dense text-aligned visual embeddings (DVE) via knowledge distillation. Instead of directly performing classical semantic segmentation with fixed predefined classes, our method uses teacher embeddings from Alpha-CLIP to guide our efficient student model DVEFormer in learning fine-grained pixel-wise embeddings. While this approach still enables classical semantic segmentation, e.g., via linear probing, it further enables flexible text-based querying and other applications, such as creating comprehensive 3D maps. Evaluations on common indoor datasets demonstrate that our approach achieves competitive performance while meeting real-time requirements, operating at 26.3 FPS for the full model and 77.0 FPS for a smaller variant on an NVIDIA Jetson AGX Orin. Additionally, we show qualitative results that highlight the effectiveness and possible use cases in real-world applications. Overall, our method serves as a drop-in replacement for traditional segmentation approaches while enabling flexible natural-language querying and seamless integration into 3D mapping pipelines for mobile robotics.
comment: Published in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
☆ Replaceable Bit-based Gripper for Picking Cluttered Food Items
The food packaging industry goes through changes in food items and their weights quite rapidly. These items range from easy-to-pick, single-piece food items to flexible, long and cluttered ones. We propose a replaceable bit-based gripper system to tackle the challenge of weight-based handling of cluttered food items. The gripper features specialized food attachments(bits) that enhance its grasping capabilities, and a belt replacement system allows switching between different food items during packaging operations. It offers a wide range of control options, enabling it to grasp and drop specific weights of granular, cluttered, and entangled foods. We specifically designed bits for two flexible food items that differ in shape: ikura(salmon roe) and spaghetti. They represent the challenging categories of sticky, granular food and long, sticky, cluttered food, respectively. The gripper successfully picked up both spaghetti and ikura and demonstrated weight-specific dropping of these items with an accuracy over 80% and 95% respectively. The gripper system also exhibited quick switching between different bits, leading to the handling of a large range of food items.
☆ Pure Inertial Navigation in Challenging Environments with Wheeled and Chassis Mounted Inertial Sensors
Autonomous vehicles and wheeled robots are widely used in many applications in both indoor and outdoor settings. In practical situations with limited GNSS signals or degraded lighting conditions, the navigation solution may rely only on inertial sensors and as result drift in time due to errors in the inertial measurement. In this work, we propose WiCHINS, a wheeled and chassis inertial navigation system by combining wheel-mounted-inertial sensors with a chassis-mounted inertial sensor for accurate pure inertial navigation. To that end, we derive a three-stage framework, each with a dedicated extended Kalman filter. This framework utilizes the benefits of each location (wheel/body) during the estimation process. To evaluate our proposed approach, we employed a dataset with five inertial measurement units with a total recording time of 228.6 minutes. We compare our approach with four other inertial baselines and demonstrate an average position error of 11.4m, which is $2.4\%$ of the average traveled distance, using two wheels and one body inertial measurement units. As a consequence, our proposed method enables robust navigation in challenging environments and helps bridge the pure-inertial performance gap.
☆ Vehicle Painting Robot Path Planning Using Hierarchical Optimization
In vehicle production factories, the vehicle painting process employs multiple robotic arms to simultaneously apply paint to car bodies advancing along a conveyor line. Designing paint paths for these robotic arms, which involves assigning car body areas to arms and determining paint sequences for each arm, remains a time-consuming manual task for engineers, indicating the demand for automation and design time reduction. The unique constraints of the painting process hinder the direct application of conventional robotic path planning techniques, such as those used in welding. Therefore, this paper formulates the design of paint paths as a hierarchical optimization problem, where the upper-layer subproblem resembles a vehicle routing problem (VRP), and the lower-layer subproblem involves detailed path planning. This approach allows the use of different optimization algorithms at each layer, and permits flexible handling of constraints specific to the vehicle painting process through the design of variable representation, constraints, repair operators, and an initialization process at the upper and lower layers. Experiments with three commercially available vehicle models demonstrated that the proposed method can automatically design paths that satisfy all constraints for vehicle painting with quality comparable to those created manually by engineers.
☆ SLAP: Slapband-based Autonomous Perching Drone with Failure Recovery for Vertical Tree Trunks
Perching allows unmanned aerial vehicles (UAVs) to reduce energy consumption, remain anchored for surface sampling operations, or stably survey their surroundings. Previous efforts for perching on vertical surfaces have predominantly focused on lightweight mechanical design solutions with relatively scant system-level integration. Furthermore, perching strategies for vertical surfaces commonly require high-speed, aggressive landing operations that are dangerous for a surveyor drone with sensitive electronics onboard. This work presents the preliminary investigation of a perching approach suitable for larger drones that both gently perches on vertical tree trunks and reacts and recovers from perch failures. The system in this work, called SLAP, consists of vision-based perch site detector, an IMU (inertial-measurement-unit)-based perch failure detector, an attitude controller for soft perching, an optical close-range detection system, and a fast active elastic gripper with microspines made from commercially-available slapbands. We validated this approach on a modified 1.2 kg commercial quadrotor with component and system analysis. Initial human-in-the-loop autonomous indoor flight experiments achieved a 75% perch success rate on a real oak tree segment across 20 flights, and 100% perch failure recovery across 2 flights with induced failures.
comment: Paper accepted to IEEE Aerospace Conference 2026. This is a pre-print
☆ Application Research of a Deep Learning Model Integrating CycleGAN and YOLO in PCB Infrared Defect Detection
This paper addresses the critical bottleneck of infrared (IR) data scarcity in Printed Circuit Board (PCB) defect detection by proposing a cross-modal data augmentation framework integrating CycleGAN and YOLOv8. Unlike conventional methods relying on paired supervision, we leverage CycleGAN to perform unpaired image-to-image translation, mapping abundant visible-light PCB images into the infrared domain. This generative process synthesizes high-fidelity pseudo-IR samples that preserve the structural semantics of defects while accurately simulating thermal distribution patterns. Subsequently, we construct a heterogeneous training strategy that fuses generated pseudo-IR data with limited real IR samples to train a lightweight YOLOv8 detector. Experimental results demonstrate that this method effectively enhances feature learning under low-data conditions. The augmented detector significantly outperforms models trained on limited real data alone and approaches the performance benchmarks of fully supervised training, proving the efficacy of pseudo-IR synthesis as a robust augmentation strategy for industrial inspection.
comment: 8 pages,8 figures
☆ CropNeRF: A Neural Radiance Field-Based Framework for Crop Counting
Rigorous crop counting is crucial for effective agricultural management and informed intervention strategies. However, in outdoor field environments, partial occlusions combined with inherent ambiguity in distinguishing clustered crops from individual viewpoints poses an immense challenge for image-based segmentation methods. To address these problems, we introduce a novel crop counting framework designed for exact enumeration via 3D instance segmentation. Our approach utilizes 2D images captured from multiple viewpoints and associates independent instance masks for neural radiance field (NeRF) view synthesis. We introduce crop visibility and mask consistency scores, which are incorporated alongside 3D information from a NeRF model. This results in an effective segmentation of crop instances in 3D and highly-accurate crop counts. Furthermore, our method eliminates the dependence on crop-specific parameter tuning. We validate our framework on three agricultural datasets consisting of cotton bolls, apples, and pears, and demonstrate consistent counting performance despite major variations in crop color, shape, and size. A comparative analysis against the state of the art highlights superior performance on crop counting tasks. Lastly, we contribute a cotton plant dataset to advance further research on this topic.
comment: 8 pages, 10 figures, and 2 tables
☆ SLEI3D: Simultaneous Exploration and Inspection via Heterogeneous Fleets under Limited Communication
Robotic fleets such as unmanned aerial and ground vehicles have been widely used for routine inspections of static environments, where the areas of interest are known and planned in advance. However, in many applications, such areas of interest are unknown and should be identified online during exploration. Thus, this paper considers the problem of simultaneous exploration, inspection of unknown environments and then real-time communication to a mobile ground control station to report the findings. The heterogeneous robots are equipped with different sensors, e.g., long-range lidars for fast exploration and close-range cameras for detailed inspection. Furthermore, global communication is often unavailable in such environments, where the robots can only communicate with each other via ad-hoc wireless networks when they are in close proximity and free of obstruction. This work proposes a novel planning and coordination framework (SLEI3D) that integrates the online strategies for collaborative 3D exploration, adaptive inspection and timely communication (via the intermit-tent or proactive protocols). To account for uncertainties w.r.t. the number and location of features, a multi-layer and multi-rate planning mechanism is developed for inter-and-intra robot subgroups, to actively meet and coordinate their local plans. The proposed framework is validated extensively via high-fidelity simulations of numerous large-scale missions with up to 48 robots and 384 thousand cubic meters. Hardware experiments of 7 robots are also conducted. Project website is available at https://junfengchen-robotics.github.io/SLEI3D/.
♻ ☆ Symphony: A Heuristic Normalized Calibrated Advantage Actor and Critic Algorithm in application for Humanoid Robots
In our work we not explicitly hint that it is a misconception to think that humans learn fast. Learning process takes time. Babies start learning to move in the restricted liquid area called placenta. Children often are limited by underdeveloped body. Even adults are not allowed to participate in complex competitions right away. However, with robots, when learning from scratch, we often don't have the privilege of waiting for dozen millions of steps. "Swaddling" regularization is responsible for restraining an agent in rapid but unstable development penalizing action strength in a specific way not affecting actions directly. The Symphony, Transitional-policy Deterministic Actor and Critic algorithm, is a concise combination of different ideas for possibility of training humanoid robots from scratch with Sample Efficiency, Sample Proximity and Safety of Actions in mind. It is no secret that continuous increase in Gaussian noise without appropriate smoothing is harmful for motors and gearboxes. Compared to Stochastic algorithms, we set a limited parametric noise and promote a reduced strength of actions, safely increasing entropy, since the actions are kind of immersed in weaker noise. When actions require more extreme values, actions rise above the weak noise. Training becomes empirically much safer for both the environment around and the robot's mechanisms. We use Fading Replay Buffer: using a fixed formula containing the hyperbolic tangent, we adjust the batch sampling probability: the memory contains a recent memory and a long-term memory trail. Fading Replay Buffer allows us to use Temporal Advantage when we improve the current Critic Network prediction compared to the exponential moving average. Temporal Advantage allows us to update Actor and Critic in one pass, as well as combine Actor and Critic in one Object and implement their Losses in one line.
comment: https://github.com/SuspensionRailway/symphony
♻ ☆ Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models. While large Vision-Language Models (VLMs) improve semantic generalization, insufficient embodied reasoning leads to brittle behavior, and conversely, strong reasoning alone is inadequate without precise control. To provide a decoupled and quantitative assessment of this bottleneck, we introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodied reasoning benchmark in robotic manipulation, comprising 6K+ question-answer pairs across four reasoning dimensions. By decoupling reasoning from execution, ERIQ enables systematic evaluation and reveals a strong positive correlation between embodied reasoning capability and end-to-end VLA generalization. To bridge the gap from reasoning to precise execution, we propose FACT, a flow-matching-based action tokenizer that converts continuous control into discrete sequences while preserving high-fidelity trajectory reconstruction. The resulting GenieReasoner jointly optimizes reasoning and action in a unified space, outperforming both continuous-action and prior discrete-action baselines in real-world tasks. Together, ERIQ and FACT provide a principled framework for diagnosing and overcoming the reasoning-precision trade-off, advancing robust, general-purpose robotic manipulation. Project page: https://geniereasoner.github.io/GenieReasoner/
♻ ☆ MDE-AgriVLN: Agricultural Vision-and-Language Navigation with Monocular Depth Estimation
Agricultural robots are serving as powerful assistants across a wide range of agricultural tasks, nevertheless, still heavily relying on manual operations or railway systems for movement. The AgriVLN method and the A2A benchmark pioneeringly extended Vision-and-Language Navigation (VLN) to the agricultural domain, enabling a robot to navigate to a target position following a natural language instruction. Unlike human binocular vision, most agricultural robots are only given a single camera for monocular vision, which results in limited spatial perception. To bridge this gap, we present the method of Agricultural Vision-and-Language Navigation with Monocular Depth Estimation (MDE-AgriVLN), in which we propose the MDE module generating depth features from RGB images, to assist the decision-maker on multimodal reasoning. When evaluated on the A2A benchmark, our MDE-AgriVLN method successfully increases Success Rate from 0.23 to 0.32 and decreases Navigation Error from 4.43m to 4.08m, demonstrating the state-of-the-art performance in the agricultural VLN domain. Code: https://github.com/AlexTraveling/MDE-AgriVLN.
♻ ☆ Efficient Multi-Task Scene Analysis with RGB-D Transformers IJCNN 2023
Scene analysis is essential for enabling autonomous systems, such as mobile robots, to operate in real-world environments. However, obtaining a comprehensive understanding of the scene requires solving multiple tasks, such as panoptic segmentation, instance orientation estimation, and scene classification. Solving these tasks given limited computing and battery capabilities on mobile platforms is challenging. To address this challenge, we introduce an efficient multi-task scene analysis approach, called EMSAFormer, that uses an RGB-D Transformer-based encoder to simultaneously perform the aforementioned tasks. Our approach builds upon the previously published EMSANet. However, we show that the dual CNN-based encoder of EMSANet can be replaced with a single Transformer-based encoder. To achieve this, we investigate how information from both RGB and depth data can be effectively incorporated in a single encoder. To accelerate inference on robotic hardware, we provide a custom NVIDIA TensorRT extension enabling highly optimization for our EMSAFormer approach. Through extensive experiments on the commonly used indoor datasets NYUv2, SUNRGB-D, and ScanNet, we show that our approach achieves state-of-the-art performance while still enabling inference with up to 39.1 FPS on an NVIDIA Jetson AGX Orin 32 GB.
comment: Published in Proc. International Joint Conference on Neural Networks (IJCNN 2023)
♻ ☆ Video-Based Detection and Analysis of Errors in Robotic Surgical Training
Robot-assisted minimally invasive surgeries offer many advantages but require complex motor tasks that take surgeons years to master. There is currently a lack of knowledge on how surgeons acquire these robotic surgical skills. Toward bridging this gap, a previous study followed surgical residents learning complex surgical dry lab tasks on a surgical robot over six months. Errors are an important measure for training and skill evaluation, but unlike in virtual simulations, in dry lab training, errors are difficult to monitor automatically. Here, we analyzed errors in the ring tower transfer task, in which surgical residents moved a ring along a curved wire as quickly and accurately as possible. We developed an image-processing algorithm using color and size thresholds, optical flow and short time Fourier transforms to detect collision errors and achieved a detection accuracy of approximately 95%. Using the detected errors and task completion time, we found that the residents reduced their completion time and number of errors over the six months, while the percentage of task time spent making errors remained relatively constant on average. This analysis sheds light on the learning process of the residents and can serve as a step towards providing error-related feedback to robotic surgeons.
comment: Title change; 9 pages, 4 figures, 1 table. Alex Geftler and Ilana Nisky contributed equally to this work
♻ ☆ World In Your Hands: A Large-Scale and Open-source Ecosystem for Learning Human-centric Manipulation in the Wild
Large-scale pre-training is fundamental for generalization in language and vision models, but data for dexterous hand manipulation remains limited in scale and diversity, hindering policy generalization. Limited scenario diversity, misaligned modalities, and insufficient benchmarking constrain current human manipulation datasets. To address these gaps, we introduce World In Your Hands (WiYH), a large-scale open-source ecosystem for human-centric manipulation learning. WiYH includes (1) the Oracle Suite, a wearable data collection kit with an auto-labeling pipeline for accurate motion capture; (2) the WiYH Dataset, featuring over 1,000 hours of multi-modal manipulation data across hundreds of skills in diverse real-world scenarios; and (3) extensive annotations and benchmarks supporting tasks from perception to action. Furthermore, experiments based on the WiYH ecosystem show that integrating WiYH's human-centric data significantly enhances the generalization and robustness of dexterous hand policies in tabletop manipulation tasks. We believe that World In Your Hands will bring new insights into human-centric data collection and policy learning to the community.
comment: This dataset represents the first large-scale collection of real-world, human-centric multimodal data integrating vision, language, tactile sensing, and action (VLTA)
♻ ☆ AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeniable candidates for end-to-end driving systems. However, limited work exists on studying the trustworthiness of DriveVLMs -- a critical factor that directly impacts public transportation safety. In this paper, we introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs), considering diverse perspectives -- including trustfulness, safety, robustness, privacy, and fairness. We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios, comprising over 10k unique scenes and 18k queries. We evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models. Our exhaustive evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats. Specifically, we found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness. DriveVLMs like DriveLM-Agent are particularly vulnerable to disclosing sensitive information. Additionally, both generalist and specialist VLMs remain susceptible to adversarial attacks and struggle to ensure unbiased decision-making across diverse environments and populations. Our findings call for immediate and decisive action to address the trustworthiness of DriveVLMs -- an issue of critical importance to public safety and the welfare of all citizens relying on autonomous transportation systems. We release all the codes and datasets in https://github.com/taco-group/AutoTrust.
comment: Published at TMLR 2025