Skip to content
Only Research
Oct 19Mon
  1. arXiv cs.RO55

    FLoTS-SLAM: Two-Stage Optimization Using Optical Flow Uncertainty for Dynamic Monocular SLAM

    FLoTS-SLAM proposes deriving motion uncertainty from the residual between optical flow and camera-motion-induced flow, for monocular RGB SLAM in dynamic scenes. The system first estimates camera pose using high-confidence pixels, then reprojects dynamic pixels to jointly optimize pose and depth, reducing the impact of object motion on pose and depth updates. On DAVIS, the average IoU of dynamic masks improves by 35% over advanced baselines; on Bonn and TUM, average ATE is reduced by 59% and 19%, respectively, relative to the SLAM backbone used. The source code will be made public.

  3. arXiv cs.RO70

    No Vision Needed: Touch-Only Dexterous Hand Baoding Ball Manipulation Achieves Zero-Shot Transfer

    The research team achieved Baoding ball rotation on the Shadow Dexterous Hand Lite using only proprioception and binary tactile feedback, enabling zero-shot sim-to-real transfer. In a single continuous trial on the physical hand, it completed 225 180° rotations (112.5 full rotations) at about 0.36 rotations per second, with no vision or object-state information throughout. The authors also compared the roles of touch and pure proprioception, identifying the hand regions where tactile information is most critical.

  4. arXiv cs.RO55

    AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation

    AWAM (Active World-Action Model) introduces a virtual active-perception paradigm that actively plans observation positions and, before execution, imagines what will be seen along the planned trajectory. It treats the predicted task-related virtual camera motion as a structured query into a geometry-conditioned world model, yielding a reusable spatial prior that is compressed into a fixed memory and fused with live observations through cross-attention for diffusion-based action prediction.

  5. arXiv cs.RO68

    ActiveAlign bridges active perception and VLA policies via observation-aligned data adaptation

    The paper proposes ActiveAlign, a data adaptation framework that addresses the mismatch between the initial observation state produced by active camera motion and the manipulation policy's training distribution (first-frame distribution sensitivity): on LIBERO, directly prepending camera repositioning to pi_0.5 reduces the success rate from 46.3% to 11.5%.

  6. arXiv cs.RO60

    Beyond Success Rate: Interventional Evaluation of Memory in Vision-Language-Action Systems

    The paper proposes an Interventional Memory Evaluation Protocol (IMEP) for vision-language-action (VLA) systems, used to determine whether memory truly influences robot decision-making, covering four questions: the net benefit of memory, the conditions under which it takes effect, changes to task outcomes, and whether the effects are specific to task-relevant facts.

  8. arXiv cs.RO52

    Dual-Perspective Survey of Long-Horizon Robot VLA Memory Paradigms: From Sliding Windows to Lifelong Self-Evolving Memory

    arXiv has published a survey that systematically reviews the memory mechanisms of long-horizon robot Vision-Language-Action (VLA) models, dividing them by memory scope and persistence into five representative paradigms and one emerging frontier. The survey compares representative VLA memory systems across memory characteristics, architectural complexity, and open-source maturity, finding a trade-off in which greater architectural complexity is generally accompanied by lower open-source maturity. It also discusses key challenges in building full-lifecycle memory systems, including efficient memory management and lifelong knowledge evolution.

  9. arXiv cs.RO51

    SkyAgent proposes Revisable Target Memory (RTM) to improve continuous aerial search

    SkyAgent proposes Revisable Target Memory (RTM) to address the problem in continuous aerial search where, after evidence becomes contradictory, old candidates still trigger approach or verification actions (which the authors call false candidate persistence, FCP). RTM associates evidence with persistent candidates, suppresses repeated counting of correlated views, and lets candidates be revised among three states: Tentative, Confirmed, and Rejected.

  10. arXiv cs.RO51

    CoEvolve: A Self-Evolving Code Policy Framework for Humanoid Robots

    CoEvolve is a framework that represents team coordination as executable code over fixed robot motor skills. Through verifier-guided co-evolution, multimodal foundation models instantiate coordination strategies, physical verification evaluates each executed transition, and rejected behaviors trigger structured revisions starting from an accepted checkpoint.

  14. arXiv cs.RO54

    ORD-WM: Object-Centric Rigid Dynamics 3D World Model for Robotic Manipulation

    ORD-WM proposes a 3D world model that learns object-centric rigid-body dynamics for robotic manipulation tasks. It uses a vector-neuron variational autoencoder supervised by signed distance fields to encode each object point cloud into a geometry-aware latent representation composed of 3D vector features, and uses an action-conditioned dynamics model to predict per-object SE(3) motion increments. It then analytically applies the predicted rigid-body transformations to the current latent state rather than generating an unconstrained next latent state, thereby separating persistent geometry from pose changes.

  15. arXiv cs.RO55

    SCOPE: A Selective Program Edit Certification Method for Embodied Heuristic Learning

    SCOPE (Selective Certification Of Program Edits) uses failed and successful executions as complementary evidence to guide program revision: frontier-guided program search annotates a shared diagnostic graph with execution evidence to distinguish verified progress from unresolved checks, while selective behavioral certification uses stateful API replay to restore recorded responses and mutations and checks whether edits preserve selected historical successful behaviors.

  17. arXiv cs.RO45

    GRASP: Global-Local Representation Alignment and Spatial-Physical Grounding for Bimanual Robotic Manipulation

    GRASP proposes a training-phase prior injection framework for bimanual robotic manipulation. A physics-grounded flow-matching loss uses differentiable forward kinematics (FK) to supervise tool center point (TCP) poses and inter-arm relative poses, and the framework introduces a global query group distilled from DINOv3 together with local interaction queries supervised by Grounding DINO; the teacher models are removed at inference. Simulation and real-world long-horizon bimanual task experiments show that the two priors are complementary under different deployment conditions: the full model performs better in in-distribution deployment, while the distilled query branch is more suitable under strong visual randomization.

  18. arXiv cs.RO47

    InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration

    InstAgent proposes a recursively self-improving (RSI) agent operating system that uses agentic behavior trees (BTs) to explicitly model capability assignment, inter-robot dependencies, and handoff checks for heterogeneous robots, and updates collaboration programs from execution feedback while preserving successful revisions for reuse in later tasks. Experiments on 20 real-world multi-robot tasks with 3 high-level models show consistent gains in task success rate, first-attempt completion rate, and execution efficiency.

  19. arXiv cs.RO38

    Bio-Inspired Magnetic Navigation via Rao-Blackwellized Particle Filter Gradient Descent

    The paper proposes a gradient descent bio-inspired magnetic navigation (BIMN) method based on local gradient estimation with a Rao-Blackwellized particle filter (RBPF) for navigation in GPS-denied environments. The method does not rely on complex, bulky, and costly magnetic maps; gradient descent naturally draws the system toward the destination, enabling magnetic navigation without magnetic maps as a simple and memory-efficient approach.

  20. arXiv cs.RO47

    A Review of Foundation Models for Autonomous Space Robotics: Architectures, Physical Adaptation, and Validation

    A critical arXiv review systematically examines the architectures, physical adaptation, and validation pathways of foundation models in autonomous space robotics, focusing on orbital manipulation and proximity operations. The article notes that event cameras can provide timely motion observations under strong illumination contrast, that spiking neural networks offer a possible route to sparse local computation, and organizes validation as an iterative "simulation-ground-space" closed loop, using a satellite capture case to connect observation, approach, contact, and recovery. The full text is 23 pages with 7 figures, accompanied by a source list and evidence document.

  21. arXiv cs.RO53

    Connecting VLA and world-action models with a unified model-to-policy formal framework

    The paper proposes an architecture-agnostic probabilistic formal framework based on stochastic kernels for uniformly describing embodied foundation models. The framework has two parts: characterizing models with conditional output distributions and action-realization kernels to induce task-conditioned robot policies, and connecting pretraining, post-training, and policy deployment. The authors instantiate it on OpenVLA and DreamZero, covering both autoregressive action-token prediction and joint video-action generation paradigms.

  22. arXiv cs.RO47

    PASS: A Trustworthy Precision Approach Simulation System for CAT III Integrity Algorithm Development

    PASS is a trustworthy precision approach simulation system for fixed-wing aircraft CAT III integrity algorithm development. Within a unified spatiotemporal geometric framework, it integrates configurable airport environments, prescribed trajectories, inertial simulation, calibrated stereo images, and continuous runway-relative ground truth, supporting navigation and integrity research under controllable sensor errors and environmental variations.

  23. arXiv cs.RO58

    VLA-Fabric: Learning Composable Interaction Mechanisms for Multi-Arm VLA Agents

    VLA-Fabric assigns a complete vision-language-action (VLA) model to each robotic arm, preserving each arm's local perception and action ownership, and achieves coordination through explicitly learned interaction across policy boundaries. The paper systematically studies where interaction should occur, how peer information should be aggregated, and how interaction should be learned, finding that shared context, peer-specific latent variables, and action-stage interaction play complementary coordination roles, and reproduces this principle on structurally different VLA architectures.

  24. arXiv cs.RO56

    What Makes a Good Symbol for Hybrid Discrete-Continuous Planning?

    The paper proposes defining symbol usefulness from the perspective of the solving algorithm: a good symbol should expose the discrete decisions that simplify solving the original planning problem. The authors first introduce the concept of solver-sufficient symbolization for finite-horizon piecewise-affine systems and design a counterexample-guided symbol invention algorithm, then extend it to optimization objectives whose energy functions are general neural networks. Experiments on simulated and real-robot tasks show that the resulting symbols reduce solving cost while maintaining solution quality, and improve interpretability and controllability.

  25. arXiv cs.RO60

    Robotic Spatiotemporal Editing: A Unified and Controllable Action Generation Interface via Masked Action Reconstruction

    The paper proposes the MAP (Masked Action Space) interface, which unifies spatiotemporal references such as keypoints, flows, orientations, and key poses as partial constraints in the same temporal Cartesian action space, and models controllable manipulation as an action inpainting problem.

  26. arXiv cs.RO45

    GR-VIP: Geometric representation-conditioned visuomotor policy for precise docking

    The study proposes GR-VIP, a goal-conditioned visuomotor policy that uses a visual encoder pretrained for relative camera pose estimation, conditioning action prediction on dense relational features before pose regression to preserve fine-grained cross-view information for learning corrective actions from demonstrations. In real-world docking tasks, GR-VIP achieves high docking success rates and millimeter-level terminal accuracy in both the training environment and unseen environments, with transfer requiring no additional training. Supplementary experiments show the policy can align with non-docking targets and complete docking under the low-light conditions tested.

  27. arXiv cs.RO57

    Hardware-as-Regularization: Improving Imitation Learning Data Consistency with an Adjustable Passive Compliant Leader Arm

    An arXiv paper proposes the Hardware-as-Regularization method, which uses a low-cost passive joint module (an adjustable mechanical clutch plus a 3D-printed spiral spring) to pull each joint toward a user-defined neutral posture, so that the passive restoring force acts as a physical prior for joint-space L2 regularization.

  29. arXiv cs.RO57

    Ego2Contact: Predicting Touch from Egocentric Human Video for Contact-Rich Robot Manipulation

    Ego2Contact learns visual-tactile priors from human interactions and transfers them to robot hands. Its predictor fuses temporal scene context with hand-local visual features to infer bimanual tactile fields from RGB video, and anatomical region correspondences align varying robot tactile layouts with the predictor's canonical grid.

  32. arXiv cs.RO57

    AnchorQ uses flow-reversed action anchors to improve RL sample efficiency for robot policies

    An arXiv paper proposes AnchorQ, which uses flow reversal to map reference policy behaviors into state-conditioned latent anchors, samples particles near the anchors, and applies value-guided sampling to achieve coarse-to-fine policy improvement. The analysis shows that anchors reduce identification complexity but introduce support bias; particle refinement trades this bias against action-class complexity, and critic accuracy determines the reliability of KL-regularized value-guided selection.

  33. arXiv cs.RO55

    DefFlow: A Goal-Conditioned Framework for Deformable Object Manipulation Based on 3D Point Flows

    DefFlow is a goal-conditioned manipulation framework for deformable objects. By jointly predicting the goal-conditioned 3D point flows of the robot and the deformable object from demonstrations, it captures manipulation decisions such as grasping, releasing, and re-grasping, as well as the continuous fine motions required to reach the goal. Across rope, granular media, and cloth settings with diverse initial and target configurations, DefFlow clearly outperforms goal-conditioned action prediction and robot-flow-only baselines on success rate and goal-distance metrics, and it was deployed on a real robot using real point cloud observations and unseen target configurations.

  34. arXiv cs.RO43

    Simultaneous Force and Motion Control of Robot Manipulators in Generalized Coordinates

    An arXiv paper proposes using Gauss's principle of least constraint to formulate simultaneous force and motion control of a robot manipulator as a quadratic programming (QP) problem in generalized coordinates (joint space), so that inequality constraints such as joint limits, collision avoidance, and singularity avoidance can be incorporated directly into the solution. Simulations were run in MuJoCo and compared with an operational-space (task-space) method; the results show that the method can simultaneously maintain the desired contact force, reduce trajectory tracking error, and satisfy the inequality constraints. The paper is 8 pages with 5 figures and has been submitted to IEEE ICRA 2027.

  35. arXiv cs.RO55

    PASS-VLN: A Passability-Aware Benchmark and Model for Local-Command Vision-and-Language Navigation

    PASS-VLN is a passability-aware benchmark and model for local-command vision-and-language navigation (VLN). It holds the scene, instruction, start pose, and reference route fixed while varying only the robot body width, requiring the robot to reach the target when the passage is feasible and to stop early when it is blocked.

  36. arXiv cs.RO57

    Research on Pedicel-Targeted Strawberry Harvesting via Imitation Learning on a Low-Cost Teleoperated Robotic Arm

    This work proposes a visuomotor imitation learning pipeline for pedicel-targeted strawberry harvesting that unifies perception, motion planning, and contact manipulation: data is collected from human teleoperation demonstrations, an Action Chunking with Transformers (ACT) policy with a ResNet-50 visual backbone is trained, and the policy is deployed autonomously on a Jetson AGX Orin edge platform at 15 Hz.

  37. arXiv cs.RO48

    Shape-Aware Neural Time Fields: Physics-Informed Neural Time Fields for Rigid-Body Motion and Manipulation Planning

    We propose Shape-Aware Neural Time Fields, a physics-informed neural motion planning framework that learns a reusable travel-time (cost-to-go) representation for rigid-body motion, explicitly distinguishing the different geometric constraints on translation and rotation, and pairs it with a sampling-based planner.

  38. arXiv cs.RO55

    Study on Coding Agents Automatically Designing Robot Spatial Memory: Codex / GPT-6 Astra Five-Track Average Improves 50.9% Over ReMEmbR

    The arXiv paper "Spatial Memory by Agents, for Agents" investigates letting coding agents automatically design robot spatial memory: under a fixed development budget, a Designer Agent writes and iteratively revises memory construction and retrieval code, with feedback from a fixed Query Agent; the resulting implementations are frozen and then used to build memory from held-out observation histories for evaluation.

  39. arXiv cs.RO41

    Task Structure and Scalability in Multi-Robot Drawing: A Simulation Comparison of Single-Token and Shared-Token Allocation

    A simulation study compared the speedup effects of two pipelines for multi-robot drawing: single-token (component-level) allocation and shared-token (decomposed) allocation, covering 385 drawings and team sizes of 1 to 8 robots. The results show diminishing speedup gains under single-token allocation; the shared-token pipeline achieved higher mean speedups and lower idle-time shares at larger team sizes, but it did not shorten completion time for every drawing.

  40. arXiv cs.RO58

    FCTS: Failure-Guided Curriculum Tree Search for Generating Terrain to Improve Quadruped Parkour Policies

    FCTS is a failure-conditioned terrain curriculum framework that uses localized traversal failures to automatically generate the terrain a policy should train on next. Each failure's location, termination mode, robot state, and surrounding terrain geometry jointly condition the generation process, and Monte Carlo Tree Search explores alternative curriculum trajectories under a fixed training budget.