Skip to content
#Data and simulation
Nov 2Mon
  1. Robotics & Automation News50

    Interview with TorqueAGI founder: Most robot AI is just a language or vision model with robot data added

    TorqueAGI is providing a "world reasoning model" intelligence layer for industrial robots and heavy machinery rather than developing its own hardware. The model represents objects, machines, and workflows as spatiotemporal graphs and incorporates physics and geometry into its reasoning. The company says new tasks typically require only dozens of examples rather than tens of thousands, and must be validated in simulation and in supervised operation at customer sites before unattended operation is possible. The same model has already run on single-arm and dual-arm robots, mobile platforms, scissor lifts, humanoid robots, and tractors, while details specific to each machine body still need to be described per machine.

  2. OFweek Robotics62

    CAS Institute of Automation and PaXini collaborative research: tactile reinforcement learning achieves sub-millimeter precision assembly

    A team led by Cheng Long at the Institute of Automation, Chinese Academy of Sciences, published research at IROS 2026 using tactile-enhanced reinforcement learning to complete sub-millimeter precision insertion, raising the success rate from 52% for a tactile-free approach to 67% under a 0.05 mm clearance.

  3. OFweek Robotics70

    Critical Point rolls out its 15,000th dexterous hand, launches OmniGlove Pro data-collection glove

    At its AI DAY on October 29, Critical Point announced that cumulative production of its dexterous hands has surpassed 15,000 units, and launched its self-developed data-collection glove, OmniGlove Pro. The glove uses a fusion of EMF magnetic field positioning and IMU, achieves fingertip positioning accuracy of 0.1 mm, is equipped with 746 tactile sensing points, and has a tactile spatial resolution of 3 mm. The company also introduced the "real-machine Ready" concept, spanning from data collection to real-machine replay.

  4. arXiv cs.RO62

    GenSight: A Unified Embodied World Model for Video Generation and 4D Perception

    GenSight is a unified embodied world model that integrates future video generation and dense perception into a single pretrained video diffusion Transformer. It uses a unified spatiotemporal representation covering video, depth, embodiment segmentation, and 2D optical flow relative to the first frame; built on a shared DiT backbone, it predicts each modality within the same architecture via lightweight task modulation, and jointly optimizes them in a unified velocity prediction space. At inference, it supports multi-step future video generation with aligned dense prediction, as well as single-step dense perception from an observed video. Training data covers a variety of robot embodiments and human hand interaction.

  5. arXiv cs.RO62

    MUSBRIC: LEGO-Compatible Pneumatic Muscle Modules for Reconfigurable Musculoskeletal Robots

    The authors present MUSBRIC, a modular hardware platform and accompanying MuJoCo simulator for reconfigurable musculoskeletal robots, which uses LEGO-compatible endcaps to turn fiber-reinforced extensile pneumatic artificial muscles into reusable, plug-and-play muscle modules. An elbow-joint prototype validated load-dependent flexion and extension, with pulley-guided routing enabling reversible motion and a mechanical stop stabilizing the straight posture; a robotic hand demonstrated compliant grasping and multi-joint construction, 15 leg configurations completed matched sweeps in hardware and simulation, and a quadruped assembled from four legs achieved walking. The hardware design and simulation code will be open-sourced.

  6. arXiv cs.RO72

    OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation

    OpenFlyV2 is a unified onboard vision-language-action architecture that uses a shared vision-language representation to support semantic understanding, language-grounded perception, spatial reasoning, and continuous flight control within a single model. The authors built a simulation dataset of approximately 70,000 navigation trajectories and 60,000 vision-language instruction-response pairs. On an NVIDIA Jetson Orin NX, the model runs fully onboard and generates action chunks of 12 waypoints each at 10 Hz.

  8. arXiv cs.RO80

    TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation

    The research team released TacClaw-Infinity, a large-scale structured Vision-Tactile-Language-Action (VTLA) dataset for contact-rich manipulation, spanning over 10,000 hours, 1 million episodes, and 1 billion frames across more than 1,000 task types.

    Why it matters: This dataset provides a collection interface and quality control pipeline for ten-thousand-hour-scale tactile manipulation data, and its cross-embodiment transfer validation approach can serve as a reference.

  10. arXiv cs.RO75

    D4orm diffusion-denoising framework extended into a family of multi-robot trajectory planners

    Based on the dynamics-aware diffusion-denoising framework D4orm, this paper builds a family of multi-robot trajectory planners for different operational requirements, including a decoupled planner, an online receding-horizon planner with feedback control, and a distributed planner. Evaluations with differential-drive and holonomic robots in 2D and 3D environments show that D4orm-based methods find high-quality solutions faster and more reliably than sampling-based optimization methods such as MPPI and a learning-based diffusion model method.

  11. arXiv cs.RO58

    CDIP: Compressed Delayed-Information Projection for Underwater Navigation Under Acoustic Measurement Latency

    The paper proposes compressed delayed-information projection (CDIP), which handles delayed-arrival acoustic position measurements in a 15-dimensional error-state Kalman filter (ESKF), retaining source-associated IMU snapshots and the current-to-snapshot cross-covariances, so delayed corrections can be projected without repeating the filter from the start.

  12. arXiv cs.RO60

    Study: Learning and Transferring Closed-Loop Robot Software

    The research treats complete closed-loop robot policy implementations as reusable execution experience: a coding agent generates policy code from a few successful demonstrations and iteratively improves it using simulation feedback. Across four source tasks in RoboCasa, iterative optimization raised the success rate from 28.3% with initially generated code to 64.2% with validation-selected code, and the learning approach was validated on a physical Unitree G1.

  13. arXiv cs.RO67

    DR-LfD: Decomposing and Reorganizing Demonstrations with Atomic Skills and Visuomotor Policies for Bimanual Manipulation Planning

    The authors propose DR-LfD, a framework that integrates visuomotor policies into a TAMP-gated decision-making system, decomposes human demonstrations into atomic skills based on contact relationships, and then reproduces and reorganizes them using visuomotor policies or object-centric primitives. This method shifts the demonstration data requirement from growing exponentially with the skill sequence to growing with the number of skill types, and on two DexMimicGen tasks it outperforms a diffusion imitation policy trained on 1,000 demonstrations while using only 100 demonstrations. The paper has been accepted by T-RO.

  14. arXiv cs.RO58

    Using a Robotic Arm as an Attitude Actuator: Propellant-Free Attitude Maneuver Planning for Free-Floating Spacecraft

    This research uses manipulator motion for propellant-free attitude control of free-floating spacecraft, modeling it as a trajectory optimization problem with joint and collision-avoidance constraints and solving it with an interior-point method. Across a range of spacecraft-manipulator systems, the method computed rest-to-rest slew trajectories of up to 90° and detumble trajectories with a 40% reduction in angular velocity. The authors also directly compare the manipulator's control authority with that of reaction wheel arrays via momentum and torque envelopes, noting that manipulators could serve as a redundant or even primary attitude control system, with particular promise for in-space assembly and manufacturing involving the capture of high relative-mass payloads.

  15. arXiv cs.RO72

    VEGA: Training Navigation VLAs with In-the-Wild Egocentric Video and Geometric Trajectory Supervision

    VEGA proposes a method for training navigation Vision-Language-Action (VLA) models from unlabeled egocentric navigation videos. It reconstructs local scene geometry from monocular video, samples text, image, and spatial waypoint goals, and generates obstacle-avoidance trajectories, then uses these trajectories to train a flow-matching VLA navigation policy; geometry is used only during training.

  16. arXiv cs.RO69

    TacO: A Benchmark Evaluation of Tactile Sensors for Object Manipulation

    The authors propose the TacO framework to systematically evaluate tactile sensors based on manipulation policy performance, covering four modalities: visual, acoustic, magnetic, and resistive. They train separate policies for three tasks—pick-and-place with unknown mass, object reorientation, and plug insertion—and analyze how sensor properties such as spatial resolution, shear sensing, tactile representation, and material friction affect task performance. The results show that the value of tactile information depends on the sensor modality, material properties, and specific manipulation task, rather than being universally beneficial; the sensors, code, data, and hardware designs will be made public on the project website.

  17. arXiv cs.RO62

    FlowTouch: A View-Invariant Visuo-Tactile Prediction Model

    FlowTouch is a view-invariant visuo-tactile prediction model that uses an object's local 3D mesh to encode information for predicting tactile patterns, enabling tactile feedback even before the object is touched. The method combines scene reconstruction with a Flow Matching-based image generation model. Results show that it narrows the sim-to-real gap and generalizes to new sensor instances, and the generated tactile images can also be used for downstream grasp stability prediction. Code, dataset, and videos are publicly available.

  18. arXiv cs.RO62

    CausalWAM: Learning the Causal Sources of Actions in World Action Models

    The authors propose CWAM (Causal WAM), which adds sparse routing paths to the action head of a world action model to separate the latent variables that truly drive actions from the nuisance variables that scene prediction depends on, while keeping the world modeling objective unchanged. The paper proves that under a sparsity constraint, the latent variables used to generate actions are an invertible function of the action-relevant latent variables alone, and the true structure is identifiable up to a permutation of the latent variables, without requiring sufficient temporal dependence or assumptions about how unobserved states evolve. Synthetic data and real-robot experiments validate the theory and show improved closed-loop success rate efficiency.

  19. arXiv cs.RO60

    Sensorium: An open-source multimodal data collection and curation library for embodied surgical AI

    The authors released Sensorium, an open-source Python library built on ROS and ROS2 middleware that records, processes, annotates, and curates multimodal surgical data from configurable robot and sensor streams, covering operator-side acquisition, configurable processing, semantic annotation, and episodic dataset generation. The library was evaluated on 1516 recordings of phantom, ex vivo, and in vivo porcine experiments involving multiple surgical tasks and sensing configurations, with preliminary usability feedback reported.

  20. arXiv cs.RO60

    DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction

    DrawSplat proposes an Atlanta World-guided implicit Gaussian SLAM framework for indoor reconstruction. The method first estimates camera poses, sparse geometry, and gravity direction through joint point-line tracking, then infers structural planes from tracked lines using the shared gravity component of the Atlanta World prior and converts them into differentiable regularization terms on Gaussian centers and normals. The framework also combines an anchor-based implicit neural Gaussian representation with adaptive structural sampling, achieving robust tracking, high-fidelity rendering, and geometrically consistent reconstruction across multiple datasets.

  21. arXiv cs.RO61

    FOCUS: A First-Order Control Method for Observation-Only Imitation Learning Supervised by Optimal Transport

    FOCUS combines local optimal transport alignment with short-horizon differentiable actor-critic learning for observation-only imitation learning, requiring neither temporally aligned expert trajectories nor expert-aligned initialization. The method matches agent rollout windows to multiple sampled expert segments using a soft best-of-K objective, with the transport cost providing a differentiable imitation reward and a learned critic bootstrapping value beyond the rollout horizon.

  22. arXiv cs.RO67

    MotorSense releases first large-scale paired egocentric video and EMG dataset

    MotorSense is the first large-scale paired egocentric video and surface electromyography (EMG) dataset, containing synchronized video, bimanual EMG, IMU, and audio across 100 hours of unscripted manipulation. The research uses this data for cross-modal pre-training between video and EMG to learn an action organization shared across visual and motor spaces, and transfers it to tasks including action recognition, 3D hand reconstruction, and 3D contact reconstruction. Across four action-related visual tasks and eight video datasets, this sensorimotor-aligned representation outperforms conventional video self-supervised methods.

  23. arXiv cs.RO62

    Nexus-VLA: Connecting Human and Robot Experience with a Shared Hierarchical Semantic Latent Space

    The authors propose Nexus-VLA, a hybrid policy learning framework that enables cross-embodiment knowledge transfer through end-to-end human-robot joint training, allowing human manipulation experience to directly contribute to robot policy learning. The framework first establishes hierarchical cross-embodiment semantic alignment from task intent to fine-grained interactions, then encodes multi-level shared knowledge into a shared manipulation latent representation used directly for continuous action generation. In RoboCasa-GR1, OOD settings, and real-robot experiments, Nexus-VLA achieved an 80.5% task success rate on RoboCasa-GR1.

  24. arXiv cs.RO58

    Suspended fabric robotic manipulation surfaces: modeling, design space, and multimodule extension

    This paper proposes a separable catenary model for suspended-fabric Robotic Manipulation Surfaces (RMS) that can quickly compute the surface shape for given actuator heights, as well as the actuator heights needed to achieve a desired local slope. The closed-form inverse solution lets a simple PID controller position objects on the fabric surface, and the model relates fabric length, module span, and actuator stroke to the reachable workspace, yielding a lower bound on minimum fabric length and design charts.

  25. arXiv cs.RO62

    Open-Source Knee Exoskeleton: Generating Biological Torque Control with Musculoskeletal Simulation

    A research team has released an open-source knee exoskeleton built from off-the-shelf components, whose biological torque controller is generated entirely by simulation, requiring no training data collected on the target device. The method uses a muscle-driven imitation policy to reproduce squatting motions from a public biomechanics dataset, then distills the knee joint torque into an estimator that relies only on onboard sensors.

  26. arXiv cs.RO80

    Movens-Zero: Scaling humanoid motion foundation models with large-scale human videos

    The research team proposes Movens-Zero, a scalable understanding-generation-execution architecture that supports real-time closed-loop humanoid motion generation under text, speech, music, and video inputs. Its accompanying dataset, Movens-5M, is built from Internet videos through clip generation, quality filtering, semantic annotation, motion recovery, and physical refinement with humanoid retargeting. It contains 15 million human motion sequences and 5 million physically executable humanoid motion sequences, totaling over 10,000 hours.

    Why it matters: This technical report presents a complete path for building a humanoid motion dataset from Internet videos and training a unified understanding-generation-execution model, offering a reference for data scale and architecture design.

  27. arXiv cs.RO80

    SimuGuard: Auditing Contact Artifacts in Simulation Benchmarks Such as LIBERO and RoboTwin

    The authors propose SimuGuard, an auditing plugin for LIBERO, RoboTwin, RoboCasa, and RoboDojo that identifies failures caused by the simulator rather than the policy. On RoboTwin, the authors trace these failures to the physics engine's collision detection: when geometry is 1 to 2 centimeters apart, the engine reports a penetration of about 2 centimeters, and the solver ejects the object at several meters per second because the distance algorithm discards triangles below a fixed area threshold.

    Why it matters: The original traces failures in simulation benchmarks to a physics engine collision detection constant and provides a before-and-after success rate comparison, which can serve as a reference for teams doing simulation evaluation.

  28. arXiv cs.RO67

    SketchMate: Building Sketch Models with VLMs for Zero-Shot Precision Insertion

    SketchMate has a vision-language model build a sketch model for insertion tasks, consisting of a few geometric primitives and two mating coordinate frames, which a planner and compliant controller then execute. In a strict kinematic test of 69 simulated insertion episodes, the method inserted 88% of parts at the assembled pose, while ReKep and MOKA using the same VLM achieved no successful insertions.

  29. arXiv cs.RO38

    Integrating Low-Thrust Transfer Dynamics into POMDP Planning for On-Orbit Servicing Missions

    This research models low-thrust (LT) orbital transfers within a partially observable Markov decision process (POMDP) for on-orbit servicing (OOS) mission planning, adding the servicing spacecraft's remaining propellant to the state space to support mass updates. High-thrust transfers are modeled with a precomputed transfer matrix, while low-thrust transfers are represented by an analytical GEO phase model, with propellant consumption and maneuver feasibility computed for given transfer-duration alternatives. In a simplified OOS scenario, SARSOP is used to solve and compare high-thrust and low-thrust policies, quantitatively assessing the feasibility and operational impact of the low-thrust option.

  30. arXiv cs.RO58

    Visual-Inertial-Encoder RGB-D SLAM for Differential Wheeled Robots

    The study proposes a generative measurement model for encoders and derives the maximum a posteriori estimation expression and the Jacobians required for optimization, building a tightly coupled visual-inertial-encoder RGB-D SLAM system. On a self-built dataset, the system's real-time state estimation achieves a root mean square error of about 2-7 cm, used to compensate for the failure of pure vision solutions during temporary feature point loss and fast motion. The source code and the dataset containing encoder information have been made public.

  31. arXiv cs.RO60

    Interaction-Aware Sampling-Based Motion Planning for Autonomous Surface Vessels in Urban Waterways

    The authors propose a decentralized motion planner based on model predictive path integral control that jointly computes the ego vessel's trajectory and predictions of other vessels' trajectories, encoding traffic rules as discontinuous costs without requiring smooth approximations. In maps taken from real sections of Amsterdam's canals, 780 randomized runs all reached their goals without collisions or deadlocks, outperforming an optimization-based planner designed for the same domain as well as a version of the proposed planner that does not account for interaction. Two scaled vessel prototypes completed head-on and crossing encounters without rule violations, planning and localizing onboard at 10 Hz in an outdoor environment.

  32. arXiv cs.RO78

    ∇Mimic: Efficient Whole-Body Control for Humanoid Robots with Differentiable Simulation

    The authors propose ∇Mimic, which uses exact gradients from a differentiable simulator to train whole-body motion-tracking policies for humanoid robots, reaching a score of 0.82 in 20 minutes and 0.874 in 1.8 hours on a single GPU, whereas the world-model method takes 1.2 hours to reach 0.82.

    Why it matters: The paper presents a complete scheme for training humanoid policies with exact gradients under differentiable simulation and open-sources the engine and code, making it easy to compare the efficiency of first-order and zeroth-order methods.

  34. arXiv cs.RO56

    TaSP-KKT: Geometry-Aware Humanoid Motion Retargeting Based on Manifold ODEs

    The study proposes TaSP-KKT, which models the continuous-time limit of OmniRetarget's per-frame KKT conditions as an ODE on the robot configuration manifold and implements motion retargeting through forward discretization. The method requires only one weighted tangent-cone projection and a closed-form manifold update per step, avoiding repeated inner SQP iterations. In numerical experiments, retargeting quality is comparable to OmniRetarget but slightly lower, while running speed is about twice as fast.

  35. arXiv cs.RO62

    HandMimicX: Learning Object-Centric Dexterous Manipulation Policies from Egocentric Videos

    HandMimicX proposes an object-centric framework for learning dexterous manipulation skills from egocentric human RGB-D videos. The method defines the reinforcement learning objective in terms of object motion, decoupling skills from specific hand trajectories, and imposes constraints on hand-object interaction states during grasping and manipulation to obtain more anatomically plausible hand configurations. Simulation and real-robot experiments show that the method learns efficiently from human videos and transfers skills to novel spatial configurations.

  36. arXiv cs.RO67

    Hourglass: Cross-Embodiment Motion Planning by Coupling a Body-Agnostic World Model with Differentiable Ego-Dynamics

    The paper proposes the Hourglass architecture, which decomposes cross-embodiment motion planning into a body-agnostic world model and each robot's differentiable ego-dynamics template, coupled only through a camera ego-motion interface. On seven simulated robots across five motion types, this generalist policy achieves success rates 3.8–10.6 percentage points higher than imitation learning and diffusion policy baselines on the same world model, matches each robot's specialized policy without dedicated training, and comes within 1.4–2.8 percentage points of a parameter-conditioned MPPI teacher.

  37. arXiv cs.RO60

    CONSORT: Multi-Robot Cooperative Localization Planning with Uncertainty Constraints in GPS-Denied Environments

    The authors propose CONSORT, a multi-robot planning method for cooperative localization in GPS-denied environments. By optimizing only over mean-state trajectories and propagating covariance only for terminal constraint evaluation, it turns the belief-space problem into a solvable form.

  38. arXiv cs.RO72

    TinyAstral: Transferring a self-evolving harness to small generalist manipulation agents

    TinyAstral proposes a two-stage method: first freeze an open-weight teacher model and optimize its harness through recursive self-improvement (RSI), then distill a 4B student model to replace the teacher within the same harness. On RoboTwin, harness evolution raised the teacher's success rate from 33.4% to 63.6%, and the final 4B student reached 62.8%; in measured deployment episodes, the student used about one-fifth of the teacher's accelerator time.

  40. arXiv cs.RO75

    CaPtain: A pipeline for post-training small open VLMs into code-as-policy robot agents

    CaPtain proposes an open post-training pipeline that trains small open vision-language models (VLMs) into code-as-policy (CaP) robot agents, without relying on VLAs, frontier models, or privileged state at test time. The pipeline first performs supervised fine-tuning on synthetic trajectories generated by GPT-6 Astra, then applies multi-turn reinforcement learning, introducing a physics critic that reads simulator privileged state to assign credit to each request.