Skip to content
Only Research
Oct 22Thu
  1. arXiv cs.RO67

    Let It Be Simple: Research on One-Step Action Generation for Vision-Language-Action Models

    The paper finds that VLA action generation differs from text-to-image generation: merely biasing the training timestep distribution toward the noise endpoint yields strong one-step policies on LIBERO, LIBERO-Plus, LIBERO-Pro, and real-world robot tasks. For open-source VLA models with different architectures, directly replacing iterative decoding with a single forward pass often performs comparably to the original multi-step decoding on LIBERO, CALVIN, and SimplerEnv.

  2. arXiv cs.RO56

    TrackDeform3D: A Markerless 3D Keypoint Tracking and Dataset Collection Framework for Deformable Objects Using RGB-D Cameras

    TrackDeform3D is an affordable and autonomous framework for collecting 3D datasets of deformable objects using only RGB-D cameras. It identifies 3D keypoints and robustly tracks their trajectories with motion consistency constraints, producing temporally smooth and geometrically consistent data.

  3. arXiv cs.RO46

    Verifiable Safe Synthesis Method for Stochastic Neural Control Barrier Functions (SNCBFs)

    This study proposes a verifiable safe synthesis method for stochastic neural control barrier functions (SNCBFs), providing a verification-free synthesis framework and a verification-in-the-loop synthesis framework for the smooth activation function and ReLU cases, respectively. The method was validated on three cases: the inverted pendulum, Darboux, and unicycle models.

  5. arXiv cs.RO60

    SSIO: A Self-Supervised Inertial Odometry Method Without Ground-Truth Trajectories

    The paper proposes a self-supervised inertial odometry training scheme called SSIO, in which a myopic teacher independently integrates the IMU within each short window to supervise the student model, an approach called integration self-supervision. Although the student is supervised only by short-window velocity changes, it learns to predict velocity directly and does so more accurately than its integration teacher. Pose graph distillation is then used to further refine the model with a cross-window consistency objective.

  6. arXiv cs.RO55

    PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

    PaceVLA proposes an adaptive temporal execution framework for VLAs that uses multi-granularity action decoders on a shared action expert, along with quantizability-guided mode selection and context-conditioned routing, to decide at each inference step whether to adopt coarse-grained execution. Experiments cover three multi-task simulation benchmarks and six real-world tasks, improving execution efficiency while maintaining task success rates across multiple embodiments, including long-horizon and dexterous manipulation.

  7. arXiv cs.RO77

    Learning from Fleet Experience: Collective Experience Learning Across 96 Robots

    The paper proposes the Collective Experience Learning (CEL) paradigm, in which deployed robots pool their own execution experience to update a shared policy that is then returned to the fleet for use. It is implemented through failure-guided experience retrieval fine-tuning (FERT), which uses failure contexts to retrieve relevant segments from successful trajectories and prioritizes their recorded actions for supervised updates, without additional expert demonstrations or corrective actions; a supporting fault-tolerant asynchronous training system (FATS) coordinates robot execution, cloud inference, and policy optimization.

    Why it matters: The paper proposes replacing expert corrections with the deployed robots' own execution experience to iterate on the policy, and reports real-world manipulation results at a scale of 96 robots.

  8. arXiv cs.RO60

    VQ-WM: A Latent Feedback Motion Planning Framework for Robot Manipulation

    The paper proposes Vector-Quantized World Model (VQ-WM), a latent feedback motion planning framework that combines discrete long-horizon search with continuous visual feedback control: a discrete latent state predictor models transitions between vector-quantized latent states, allowing the planner to search for the shortest path over long distances, while a continuous learned controller then reaches the planned states step by step through visual feedback to correct deviations and mitigate compounding errors.

  11. arXiv cs.RO51

    FallGown: A Soft Pneumatic Wearable Device for Fall Prevention

    FallGown is a soft wearable support structure made of pressurized air pouches inside a fabric shell; it can support the full weight of a user's body to prevent falls. When stored it measures 6.9 kg and 0.051 cubic meters, with an average donning time of under 2.5 minutes and doffing time of under 0.5 minutes. Single-user fall prevention testing showed a tradeoff between device size and resistance to tipping; a configuration with a base, 12 air pouches, and a skirt-bottom diameter of 1.4 meters prevented all falls except for one mechanical failure. Onboard pressure sensors can sense the user's weight distribution, offering potential for monitored exercise and adaptive support.

  12. arXiv cs.RO58

    RoboCap: A six-camera head-mounted platform and Grounded API for egocentric robot learning

    The research team introduces RoboCap, a 250-gram head-mounted device with six cameras and dual IMUs for in-the-wild egocentric data collection, along with the Grounded API, a device-agnostic suite of 3D algorithms. The report shows how the hardware, calibration, and 3D algorithms work together to achieve state-of-the-art performance on public benchmarks, covering SLAM across diverse settings and rigs, egocentric depth estimation, and hand tracking when adapted to third-party devices.

  13. arXiv cs.RO60

    Robot Learning with Visual Predicted Force: Achieving Force-Aware Manipulation Through Visual Force Prediction

    The paper proposes achieving force-aware manipulation by visually predicting the deformation of a compliant Fin Ray gripper, without requiring force or tactile sensors at deployment. The method trains two models: first, a visual force estimator is trained on calibration data to annotate demonstrations with force estimates; second, an action-force proposal policy is trained to jointly generate candidate actions and their corresponding forces. At test time, candidate actions are sampled and the action whose predicted force is closest to a target from the demonstrations is executed. The method was evaluated on four tasks: berry picking, empty-can grasping, in-hand reorientation, and plug insertion.

  14. arXiv cs.RO62

    PolyUMI: A visual-tactile-audio multimodal data collection platform for object inference and manipulation

    PolyUMI is an open-source visual-tactile-audio demonstration collection and robot deployment platform. Its lightweight wireless handheld gripper synchronously records wrist-camera, optical tactile, contact-audio, and proprioceptive observations without requiring a tethered workstation. The same sensing finger can be transferred to the robot end effector to keep the sensing geometry consistent between data collection and policy execution.

  15. arXiv cs.RO57

    HarnessPAI: An Evolvable Harness Framework for Physical AI

    HarnessPAI proposes a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable, evolvable interface organizing underlying action primitives. The framework separates two timescales: within a single rollout, it executes open-loop at the program level with a fixed program guiding and checking execution; across rollouts, it evolves closed-loop, using execution feedback to revise the program and distill failures into reusable skills.

  16. arXiv cs.RO55

    BAS-VLA: A Task-Semantic Action Calibration Framework for VLA Models

    The paper proposes BAS-VLA, a task-semantic action calibration framework built on top of a frozen base VLA, designed to address two types of failure: policies producing unnecessary action drift when task semantics are unchanged but appearance varies, and policies continuing along the original trajectory when key semantics such as the target object or constraints are altered.

  17. arXiv cs.RO54

    rMuscle: A Real-Time Framework That Uses Robotic Task Similarity to Accelerate VLA Model Inference

    The paper proposes rMuscle, a real-time vision-language-action (VLA) model inference framework inspired by human muscle memory. The authors first analyze embodied workloads and find that when robots repeatedly perform tasks, there is significant similarity in observations, action trajectories, and even internal model states.

  18. arXiv cs.RO51

    Action-Conditioned World Model for Robotic Neck Ultrasound Target Plane Guidance

    This study proposes a local action-conditioned world model framework for probe guidance toward target planes in robotic ultrasound, using a two-stage model-based learning pipeline: first, a latent conditional diffusion world model predicts future ultrasound observations from recent context frames, probe motion, and temporal offset; second, a goal-conditioned temporal Transformer predicts ordered probe actions and is fine-tuned using rewards from the frozen world model.

  19. arXiv cs.RO55

    Hilti-Trimble-Oxford dataset released: a benchmark for 360-degree visual-inertial SLAM and floor plan localization

    The paper releases the Hilti-Trimble-Oxford dataset, collected at an active construction site. It contains 30 visual-inertial sequences covering 10 floors over an eight-month span, and captures real-world challenges such as changing lighting, moving workers, fast motion, and repetitive structures. Ground-truth trajectories were collected with a high-precision LiDAR-inertial SLAM system rigidly attached to the 360 camera. The authors also report results from the accompanying open research challenge: 62 teams entered the SLAM track, while only 22 entered floor plan localization, indicating less attention to the latter.

  21. arXiv cs.RO67

    ReStruct: Guiding Robot Behavior at Inference Time via Physically-Aware Reconfiguration of Task Structure

    ReStruct proposes a method to steer learned robot policies at inference time, enabling them to satisfy user preferences not specified during training without retraining. The method decomposes a visuomotor policy into a high-level state-machine skeleton and a low-level residual controller, and incorporates preferences into the skeleton via a synchronous product to reconfigure the task structure, while the controller remains frozen. Simulation and real-world experiments show that ReStruct can handle a variety of preferences, from object-level specifications to temporal-logic constraints, and after steering it outperforms existing methods in task success rate and preference adherence, leading VLA models by up to 25%.

  22. arXiv cs.RO60

    SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Models

    SafeDojo proposes a model-based safe reinforcement learning framework that improves vision-language-action (VLA) policies through world-model imagination, avoiding costly real-world exploration or reliance on hand-crafted safety functions. The method performs online reinforcement learning on top of an interactive video world model, using a ResNet success classifier to score predicted future frames, paired with a lightweight safety head that predicts per-step contact probabilities from the current latent context and candidate action chunks, then balances task execution and trajectory safety signals through Lagrangian-constrained GRPO.

  24. arXiv cs.RO44

    UGV-Conditioned Multi-UAV Informative Planning on a Shared Exposure Belief

    Simulation results show that the method reduces cumulative UGV exposure by 38% compared with terrain-semantic replanning, and the multi-UAV coordination scheme cuts redundant aerial coverage from 38.8% to 3.7%. The method guides UGV path planning through a risk-averse shared exposure belief and uses mission-conditioned rewards to drive UAVs to focus sensing on exposure-relevant uncertain regions; UAV observations update the belief online, and the UGV uses this to route around newly discovered threats. In multi-UAV scenarios, region-conditioned spatial assignment is used to reduce redundant sensing.

  25. arXiv cs.RO55

    MiTaS multi-resolution tactile imitation learning framework for contact-rich manipulation tasks

    MiTaS is a multi-resolution tactile representation framework that uses modality-specific convolutional stems and a Transformer-based fusion structure to integrate information from an RGB camera, a GelSight Mini vision-based tactile sensor, and a high-frequency event-based Evetac sensor, then conditions a flow-matching policy to perform downstream tasks.

  26. arXiv cs.RO51

    OSCAR: An Adaptive Robot Navigation Framework Based on Obstacle Survival Curves

    OSCAR proposes an adaptive survival-modeling framework for temporary blockages in graph-structured navigation. The robot learns residual clearance-time distributions by obstacle class from online experience and integrates them into a time-dependent graph planner with obstacle memory, computing at each blocked edge a patience threshold for how long to wait before rerouting.

  27. arXiv cs.RO57

    Research on Resource Allocation for Heterogeneous Multi-Team Robot Collaboration Based on Hamilton's Rule

    This paper studies the dynamic robot allocation problem in heterogeneous multi-team collaboration, treating robots as transferable resources, drawing on Hamilton's rule from ecology to design an altruistic decision-making mechanism, and proving that the generalized heterogeneous resource allocation problem is combinatorial optimization and NP-hard.

  28. arXiv cs.RO60

    Feedback World Model Enables Precise Guidance of Diffusion Policy (NeurIPS 2026)

    This paper proposes a feedback world model that uses the true states observed after robot execution to perform online closed-loop correction of predictions at inference time, without additional training data or parameter updates. The method can be interpreted as a latent-space observer and provides convergence guarantees under bounded, asymptotically convergent dynamics residuals and a stable feedback gain; it also introduces action-aware guidance to better translate corrected predictions into control.

  30. arXiv cs.RO62

    WARPED: Synthesizing wrist-view observations from first-person human demonstrations to train robot visuomotor policies

    WARPED is a framework that synthesizes realistic wrist-view observations and actions from human demonstration videos, enabling visuomotor policy training with only monocular RGB data. The system uses vision foundation models to initialize the interactive scene, employs a hand-object interaction pipeline to track the hand and manipulated object and retarget trajectories to a robotic end-effector, and finally uses Gaussian Splatting to synthesize photorealistic wrist-view observations for directly training policies.

  31. arXiv cs.RO60

    Safe-Night VLA: Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

    Safe-Night VLA is a multimodal manipulation framework that integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling robots to perform semantic reasoning based on thermodynamic properties and to enforce deterministic workspace constraints during policy execution through a control barrier functions safety filter.

  32. arXiv cs.RO65

    ExtremControl: 50ms humanoid robot teleoperation with scaled velocity feedforward

    ExtremControl proposes a low-latency whole-body control framework for humanoid robots that reduces end-to-end teleoperation latency from about 200ms to as low as 50ms. Its core is adding scaled velocity feedforward in low-level control, which cuts tracking delay by about 70ms, and operating directly on the SE(3) poses of selected rigid links to avoid joint-space retargeting; the paper also derives a closed-form Cartesian-space mapping that needs only a single anthropomorphic calibration to adapt to operators of different body proportions.

  34. arXiv cs.RO47

    HEHA: Bounded Suboptimal Constrained Path Planning for Heterogeneous Multi-Robot Exploration of Unknown Environments

    HEHA (Hierarchical Exploration with Heterogeneous Agents) proposes a hierarchical framework that uses a new routing algorithm, RCH (Routing with Constraints and Heterogeneity), to quickly solve large-scale multiple Hamiltonian path problems (mHPP) with traversability constraints, assigning areas to be explored to drones, wheeled robots, and legged robots and determining the order in which those areas are visited.

  35. arXiv cs.RO55

    AFFORD2ACT studies the capability ceiling of robot manipulation policies with sparse 2D keypoint input

    AFFORD2ACT (Affordance-Guided Keypoints to Act) studies how much manipulation capability can be retained when only sparse 2D keypoints are used as input: an off-the-shelf language-conditioned affordance model locates task-relevant regions, selects up to 15 object keypoints plus 4 end-effector keypoints, compresses the policy input to 19 2D keypoints (38 coordinates), and then uses lightweight gating to decide which keypoints to focus on during execution.

  36. arXiv cs.RO51

    AgriVLN: A Vision-and-Language Navigation Benchmark and Method for Agricultural Robots

    This work proposes A2A, a vision-and-language navigation benchmark for agricultural robots, comprising 1,560 episodes across 6 classes of agricultural scenes, using step-by-step instructions and a continuous-action environment. Evaluation found that existing VLN methods perform well on short instructions but poorly on long instructions; to address this, the authors propose an STL module that decomposes complex instructions into lists of simple subtasks and integrates it into the NavGPT backbone, raising SR from 0.33 to 0.47 while NE slightly increases from 2.76 m to 2.91 m. Ablation studies and case analyses are also included.

  37. arXiv cs.RO73

    AgiBot World Colosseo releases large-scale manipulation data platform and GO-1 generalist policy

    AgiBot World Colosseo introduces the AgiBot World large-scale manipulation platform, containing over 1 million trajectories covering 217 tasks across 5 deployment scenarios, an order-of-magnitude increase in data scale over existing datasets, and uses a standardized collection pipeline with human-in-the-loop verification.

  38. arXiv cs.RO36

    Implementation of Dynamic Microsegmentation in Multi-Robot Networks

    A laboratory study used a commercial software-defined microsegmentation tool to implement dynamic microsegmentation in an Internet-of-Things multi-robot network, with policies adaptively adjusted and automatically deployed based on asset functional and health tags. The demonstration showed that the approach can automatically isolate a designated threat in real time while maintaining normal operation of unaffected nodes, validating the feasibility of microsegmentation for addressing threats and disruptions in IoT networks.

  39. arXiv cs.RO38

    Extending graspable-part segmentation to multi-object images

    A study proposes introducing a laser pointer into a vision-based portable pipeline for target disambiguation in multi-object scenes, to support grasp selection and preshaping in upper-limb prostheses. The method uses a mixed reality strategy to reuse existing high-quality segmentation masks to generate training images and retrains a deep convolutional neural network. Experimental results show target disambiguation accuracy improves by up to 9% over existing solutions while computational cost remains unchanged.

  40. arXiv cs.RO55

    AOV-GS: Active Open-Vocabulary Semantic Mapping with 3D Gaussian Splatting

    AOV-GS is an active 3D Gaussian Splatting mapping system that uses frozen foundation models to guide exploration, without requiring manually annotated segmentation masks or closed semantic categories. In its coarse exploration stage, it re-ranks geometric candidate views by the novelty of CLIP mask embeddings computed from SAM instance segmentation, biasing exploration toward semantically informative regions; a lightweight scene language field fitted offline directly aligns the collected CLIP embeddings, enabling open-vocabulary text-query segmentation.