Skip to content
#Research
Oct 19Mon
  1. arXiv cs.RO70

    WorldOracle: Benchmarking action-conditioned world models against real-world executions

    WorldOracle is a benchmark for action-conditioned world models (ACWMs) that uses identical initial observations and low-level action sequences to test whether predicted rollouts can reproduce real-world physical consequences and task-state transitions. The evaluation covers four dimensions: physical state correctness, interaction spatial alignment, key interaction area fidelity, and multi-view action coherence, and is paired with long, multi-segment real-world data containing both successful and failed executions. Experiments on seven representative ACWMs reveal different models' strengths and failure modes. The dataset, evaluation code, and leaderboard are publicly available.

  2. arXiv cs.RO78

    Evaluating a Frozen Frontier VLM Directly as a Robot Policy on the RoboMME Memory-Dependent Manipulation Benchmark

    The study uses a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy and tests it on RoboMME, a benchmark of 16 memory-dependent manipulation tasks. The model keeps the entire episode context throughout and directly outputs each end-effector waypoint and gripper command, with no training specific to this benchmark.

    Why it matters: The paper provides complete comparative data on a frozen frontier VLM used directly as a policy on a memory-dependent manipulation benchmark, which can be used to assess how much of the embodied stack a general-purpose model can take over.

  3. arXiv cs.RO47

    Evaluating Sensitivity of World-Action Models to Spatial Instruction Rewriting

    An evaluation conducted 864 rollouts of three world-action models across four RoboLab scenes, holding initial states and task goals fixed, and found that describing spatial relations using the reference object rather than the object to be moved lowered the stable placement success rate by an average of 12.2 percentage points. An independent test of the policies' language understanding identified relation reversals, and adding images disrupted otherwise correct text-only interpretations. Rollout analysis also distinguished spatial placement from instruction following: the stable placement rate fell from 43.2% at any time to 21.8% at episode end.

  4. arXiv cs.RO56

    Analytic Robot Self-Model: Learning Screw-Axis Kinematics for Rendering and Model-Based Control

    The paper proposes an explicit analytic robot self-model that requires neither deformation networks nor URDF/CAD templates. From multi-view images and joint readings, it obtains appearance and rigid link assignments, and independently identifies metric screw axes using sparse end-effector poses, yielding closed-form forward kinematics and an analytic Jacobian that can be extrapolated.

  5. arXiv cs.RO56

    AnyRank: A Reliable Ranking Method for Robot Policies Based on Sequential Testing

    AnyRank proposes a sequential method for multi-policy ranking that adaptively allocates trials to policies that are hard to distinguish, provides a (partial) ranking at any stopping time, and bounds the probability of an incorrect ranking. The method can optionally use prior information (such as expert intuition, a small set of held-out hardware evaluations, or policy rollouts from a simulator or an action-conditioned video world model) to improve hardware evaluation efficiency, and inaccurate priors do not break its statistical guarantees.

  6. arXiv cs.RO67

    RoboHarness: Simple Robot Harness Lets LLM Agents Outperform VLA and World Action Models on BEHAVIOR Challenge 2025

    An arXiv paper presents RoboHarness, a robot harness that gives LLM agents a visual-geometric control panel so they can directly understand and invoke embodied tasks. The authors argue that coding agents have the potential to achieve generalist embodied manipulation without the route of large-scale VLA training. Experiments show that, with RoboHarness, Qwen3.8-Flash-Next outperforms state-of-the-art VLA models on BEHAVIOR Challenge 2025 tasks, and the implementation is open source.

  7. arXiv cs.RO55

    DexBioLab: A dexterous manipulation simulation benchmark for real biological laboratory scenarios

    The research team proposes DexBioLab, a simulation benchmark and framework for dexterous manipulation in real biological laboratory environments, comprising 14 tasks across 4 robot embodiments, covering functional tool use, precision manipulation, language-conditioned visual grounding, and instrument operation.

  9. arXiv cs.RO45

    Reinforcement Learning-Based Tendon-Driven Bionic Jellyfish Robot Achieves Closed-Loop Depth Control

    A tendon-driven bionic jellyfish robot achieves 150° bending through soft actuators that combine a flexible substrate with discrete constraints, with tendon displacement and bending angle approximately linear. Eight actuators driven by four servos enable stable swimming, attitude adjustment, and self-righting. A reinforcement learning controller trained on this linear actuation characteristic achieved closed-loop depth regulation in both simulation and physical experiments.

  10. arXiv cs.RO55

    Benchmarking Service Robots in Public Environments: From the Lab to Real-World Operation

    This study proposes an interdisciplinary process for benchmarking service robots in public everyday environments, addressing the gap between laboratory metrics and real-world operation, with evaluation conducted at technology readiness levels 6-7. Over the three years 2023-2025, seven benchmarking events (one consensus workshop and six on-site evaluations) assessed three robots across three use cases: outdoor park cleaning, pedestrian underpass cleaning, and interactive assistance in a public library.

  13. arXiv cs.RO60

    Improving legged locomotion policy health via gait-phase-conditioned effective rank of the network Jacobian

    This study analyzes reinforcement learning policies for legged locomotion using the effective rank of the network Jacobian, finding that conditioning on gait phase exposes representation structures invisible from the global rank. Architectures with observation normalization and residual connections allocate more than one additional effective-rank dimension to swing-dominant states than vanilla MLPs do. Based on this, the proposed diagnostic method reduces joint jitter by up to about 2x in simulation and on a physical Spot, and the paper has been accepted to CoRL 2026.

  14. arXiv cs.RO56

    DriveDegrade: An Image-Degradation Tolerance Benchmark for Camera-Only End-to-End Driving Planning

    The paper proposes DriveDegrade, an image-degradation tolerance benchmark for camera-only end-to-end (E2E) driving. It injects 16 corruption types at 5 severity levels online in the image loader, uses a single operator to cover 15 policies, and evaluates open-loop planning on nuScenes and NAVSIM, with a CARLA closed-loop anchor.

  15. arXiv cs.RO72

    ADEPT: Accelerating Dexterous Manipulation via Reinforcement Learning Pre-Training and Post-Training

    ADEPT is a large-scale reinforcement learning framework that first pre-trains a dexterous policy on a generic object-reposing task, then post-trains downstream policies with this prior, enabling long-horizon tasks to be solved directly from raw visual-tactile perception across high-DoF embodiments. To prevent naive fine-tuning from degrading zero-shot reposing ability, the authors propose a stable post-training scheme combining behavior-cloning distillation, critic warm-up, and conservative on-policy updates, and introduce a joint-space Geometric Fabric that coordinates the policy with the robot.

  16. arXiv cs.RO57

    Cyclops: Synthesizing Sparse LiDAR Intensity into RGB Video for Camera-Free Perception

    Cyclops is a framework that synthesizes sparse Non-Repetitive Scanning LiDAR (NRS-LiDAR) intensity data into RGB video for all-weather perception tasks without a camera. Its method first uses a frozen pre-trained densification module to convert sparse intensity projections into dense representations, then learns a velocity field through Latent Bridge Matching (LBM) to transport intensity latents to the RGB distribution within a few ODE integration steps; it also injects prior-frame context via temporal attention to suppress inter-frame flickering, and models the velocity field as a policy optimized by a differentiable terminal reward.

  17. arXiv cs.RO62

    MANGO-Grasp: A Cross-Embodiment Dexterous Grasping Framework Based on Geometry-Oriented 3D Gaussians and Mahalanobis Fields

    MANGO-Grasp proposes an anisotropic interaction framework that represents objects with geometry-oriented 3D Gaussian primitives to preserve local surface geometry, encodes hands as pretrained descriptors that capture both morphology and kinematics, and models hand-object contact through anisotropic Mahalanobis fields.

  18. arXiv cs.RO64

    FACT post-training method improves VLA success rate in contact-rich manipulation tasks

    The paper investigates why vision-language-action (VLA) models fail in contact-rich manipulation tasks that require precise physical interaction, and proposes two failure modes: precision failures (policies struggle to produce the small, precise corrective actions needed during contact) and force failures (policies fail to respond to contact forces).

  19. arXiv cs.RO55

    Diagnosing Compositional Generalization in Sequential Robot Tasks

    This paper studies compositional generalization in sequential robot manipulation tasks from the perspective of instruction-space coverage, decomposing the generalization gap into three sources: marginal instruction shift, instruction-compositional shift, and context-action shift. Results show that exhaustive instruction-tuple enumeration is unnecessary; a structured subset covering action-relevant dependencies can achieve strong out-of-distribution performance. Sparse-training failures often stem from instruction steering rather than missing low-level skills, and fine-tuning with just one demonstration per task raises out-of-distribution success from 0.4% to 54.7%.

  20. arXiv cs.RO68

    PRISM: Improving Robot Motor Control Policy Learning with Polynomial Representations

    PRISM (Polynomial Representations for Interaction Structured Motor Control) is a physics-inspired policy representation method that learns multiplicative interactions among variables by recursively adding scaled bilinear features. It only requires replacing the first affine layer of a multilayer perceptron (MLP) and can be used for reinforcement learning and imitation learning without changing training objectives, sensing, or controllers.

  21. arXiv cs.RO55

    FELT: Generating Tactile Signals from Vision for Visuo-Tactile Manipulation

    FELT is a framework that uses existing paired visuo-tactile data to learn contact-aware representations from RGB observations, providing them to downstream policies through two interfaces: generated tactile images and contact-aware features. It combines a frozen visual encoder with separate query decoders for the left and right fingers, and the two branches exchange information through gated connections, with a convolutional readout producing spatial contact representations. On four contact-intensive real-robot tasks, both interfaces achieved higher success rates than vision-only policies, and directly integrating contact-aware features into policies raised success rates by 15-22.5 percentage points.

  22. arXiv cs.RO62

    OptCar: Specializing a Generalist FKD Model into a High-Speed MPC-Specific Model with Limited Real-Vehicle Data

    The paper proposes OptCar, a method that specializes a generalist forward kinodynamic (FKD) model into a vehicle-specific model while preserving cross-terrain generalization. At its core, a FiLM mechanism summarizes recent state-action history into a single dynamics context token that conditions multi-step predictions in a Transformer FKD architecture; specialization then combines limited real-vehicle data with targeted synthetic trajectories generated by system identification.

  23. arXiv cs.RO48

    EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation

    EDAR (Environment-Dependent Action Representation) anchors action tokens in both executable control structure and expected visual consequences. By coupling motor commands with their environment-conditioned effects, it enables the learned action space to capture interaction semantics rather than merely command-level patterns.

  24. arXiv cs.RO62

    NativeMEM: A Native Memory Compression Method for Long-Horizon Robotic Manipulation

    NativeMEM is a vision-language-action (VLA) policy with long-horizon, real-time updated memory. Its core is the Native Memory Compression encoding scheme, which reuses the VLA's own vision encoder to compress each historical frame from each camera view into a single token. Appended to the input sequence, these tokens let the pretrained VLA attend to long-term history with negligible latency overhead, requiring neither an external planner nor a newly initialized memory module.

  25. arXiv cs.RO55

    SPACE: Adaptive Collision-Aware Swarm Exploration Based on Pheromone Fields

    SPACE is a swarm exploration method inspired by ant foraging. On a synchronized shared map, it maintains an attractive frontier pheromone, a repellent exploration pheromone, and a fast robot-density field, providing local field guidance for robots. The authors evaluated it on sixteen home layouts from HouseExpo and eight campus floors from KTH, using up to two hundred fifty-six robots. At congested swarm sizes, SPACE achieved the lowest inter-robot contact rate on HouseExpo and lay on the empirical Pareto frontier on KTH.

  26. arXiv cs.RO40

    PinNet: Keypoint-Aware Local Descriptors with Geometric Embedding for LiDAR SLAM Loop Closure Detection

    PinNet generates point cloud keypoints and their descriptors, and uses a plane-based geometric self-attention module to model spatial relationships between keypoints, thereby improving descriptor discriminability for loop closure detection and point cloud registration. The method was evaluated on datasets collected with various different LiDAR sensors; experimental results show strong place recognition performance, precise relative pose estimation, and successful single-shot localization in different environments.

  27. arXiv cs.RO55

    Research on Asynchronous Upper-Body Task-Space Trajectory Tracking Strategies for Humanoid Robots

    The paper proposes an asynchronous upper-body task-space trajectory tracking framework for humanoid robots, addressing the temporal asynchrony between sparse, low-frequency trajectories output by high-level planners and the high-frequency operation of whole-body controllers. The student policy is initialized through teacher-student distillation, conditioned on the fully cached future trajectory and an execution-time index, and trained with a sliding-window global reward to reduce frame drift; in the task post-training stage, an MPC module completes sparse references into floating-base and upper-body guidance.

  28. arXiv cs.RO59

    WireCraft: A Simulation Benchmark for Industrial Deformable Linear Object Manipulation

    WireCraft is a simulation benchmark for industrial deformable linear object (DLO) manipulation, covering three task families: connector insertion, clip routing, and channel seating. It supports two physics models, articulated and deformable, and the released trajectories come from both simulation and a real UR5 robotic arm.

  29. arXiv cs.RO55

    SidewalkBench: A benchmark for visual navigation on urban sidewalks

    SidewalkBench is a benchmark for visual navigation on urban sidewalks built on NVIDIA Isaac Sim. It provides GPU-accelerated, high-fidelity sidewalk environments, including procedurally generated and real-world scanned scenes, and adds event-driven pedestrian reactive behaviors. The authors evaluated 9 visual navigation models on 330 unit-test scenarios, 800 pedestrian-reactive scenarios, and 105 long-horizon scenarios. They found that pedestrian interaction and long-horizon robustness remain key bottlenecks for existing models, and that scaling up sidewalk training with synthetic data is a viable direction.

  30. arXiv cs.RO56

    CoRL 2026 paper proposes language feedback policy that can steer frozen VLAs harmlessly

    The paper proposes a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills them into a test-time language feedback policy (LFP), and trains an improvement head to predict when language steering will be effective, then applies conformal calibration to the improvement head to prevent harmful interventions.

  31. arXiv cs.RO55

    Perceptive BFM: A Perception Control Framework for Adapting Human Motion Priors to Robot Terrain

    The paper proposes Perceptive Behavior Foundation Model (Perceptive BFM), a terrain-aware whole-body control framework for humanoid robots that uses local terrain observations from the robot's perspective to adapt contact, posture, and timing while retaining the original kinematic reference as the behavioral interface.

  33. arXiv cs.RO58

    OrbiSim: Recasting World Models as a Differentiable Physics Engine for Embodied Intelligence

    OrbiSim proposes a robot simulation paradigm that recasts world models as a fully differentiable physics engine, connecting structured scene assets, neural dynamics, and downstream reinforcement learning. The entire simulation loop, from explicit state transitions to visual observation generation, supports end-to-end differentiability, enabling tasks such as differentiable contact modeling, gradient-based policy optimization under sparse rewards, and physical reasoning. Experiments show that OrbiSim significantly outperforms existing world models in prediction fidelity and control performance, and responds consistently to asset configurations and physical parameters.

  34. arXiv cs.RO46

    Learning Cross-Coupled and Regime-Dependent Dynamics for Aerial Manipulation

    A study proposes a structured encoder-decoder framework in which a nonlinear history encoder captures the temporal and cross-coupled residual dynamics of an aerial manipulation platform and its robotic arm, while a linear latent-space decoder supports rapid adaptation at deployment time. The framework's linear-in-parameters structure enables closed-form Bayesian updates and integration with real-time model predictive control (MPC). Experiments on a real aerial manipulation platform showed improved residual prediction accuracy, rapid adaptation after dynamics changes, and reduced MPC tracking error under changing payload conditions.

  36. arXiv cs.RO62

    PanoAir: A Panoramic Visual-Inertial SLAM Framework for UAVs with a Cross-Time Real-World Dataset

    PanoAir proposes a panoramic visual-inertial SLAM (VI-SLAM) framework and builds a real-world panoramic dataset covering different illumination, altitudes, trajectory lengths, and motion dynamics. The method uses panoramic feature extraction and panoramic loop closure to strengthen feature constraints and global consistency. On its own dataset and public benchmarks, it completed all 17 sequences without tracking failure and reduced ATE by up to 47.1% compared with the best baseline. Deployment on an embedded platform verified computational efficiency comparable to the PC implementation. The source code and dataset are publicly available.

  37. arXiv cs.RO62

    OxyGen: Unified KV Cache Management for Multi-Task Parallel VLA Inference

    OxyGen proposes an inference design for unified KV cache management that treats the KV cache as a shared resource across tasks and control cycles, eliminating redundant prefill of shared observations through cross-task KV sharing and advancing unfinished language requests within each frame's decoding budget via cross-frame continuous batching.

  38. arXiv cs.RO44

    Gaussian Process-Based Robot Skill Learning and Adaptation Framework

    A study published in IEEE RA-L 2026 and presented at IROS 2026 proposes a robot skill adaptation framework based on Gaussian processes (GPs) and sparse via-points, which preserves the kinematic characteristics of skills by using first- and second-order analytical derivatives of trajectory poses. The framework includes three adaptation methods: an optimization agent, a behavior cloning agent, and a reinforcement learning (RL) agent. In simulation and real-world evaluations on three tasks—opening a drawer, pushing a cube, and manipulating a horizontal bar—it outperformed all baseline methods in success rate and demonstrated high cosine similarity and low velocity magnitude error.

  39. arXiv cs.RO62

    HydroShear: Fluid-elastic shear simulation for tactile sim-to-real reinforcement learning

    HydroShear is a non-holonomic fluid-elastic tactile simulator accepted to RSS 2026, addressing tactile sim-to-real policy transfer for contact-intensive tasks. It models stick-slip transitions, path-dependent force and shear accumulation, and full SE(3) object-sensor interaction, and uses signed distance functions (SDFs) to track the displacement of indenter surface points as they interact with the sensor membrane, generating physically grounded and computationally efficient force fields from arbitrary watertight geometries.

  40. arXiv cs.RO50

    TRAIN: A reinforcement learning framework for terrain-aware interactive navigation for quadruped robots

    TRAIN proposes a two-stage deep reinforcement learning framework that, through the TRAIN-Loco and TRAIN-Nav pipelines, enables quadruped robots to achieve terrain-aware navigation in unstructured terrain and human-populated environments. Benchmarks compared quadruped locomotion and robot navigation baselines, and hardware experiments verified its sim-to-real transfer potential.