Skip to content
#Robot models and learning
Nov 9Mon
  1. arXiv cs.RO62

    Autoregressive policies achieve real-time execution via tokenization horizon adjustment and constrained decoding

    The paper proposes that autoregressive policies can achieve real-time execution by adjusting the tokenization horizon and applying constrained decoding, thereby guaranteeing strict latency bounds and enabling multi-trajectory decoding. In simulated and real-world environments, the autoregressive policy significantly improves task completion speed over synchronous inference and consistently outperforms equivalent-level flow-matching policies. The authors note that autoregressive policies also have inherent advantages of faster convergence and better generalization in instruction following. The work was published at CoRL 2026.

  2. arXiv cs.RO62

    MosaicIMU: A Generalizable Neural Inertial Odometry Framework for Multiple Carriers

    MosaicIMU is a carrier-conditioned Mixture-of-Experts (MoE) pretraining and adaptation framework for generalizable neural inertial odometry. It composes carrier-specific expert features through a prototype-based router, decodes local velocity and uncertainty constraints, and integrates them with a history-aware EKF. For unseen domains, it freezes the pretrained base model and learns a lightweight expert residual branch; for edge deployment, it reuses the router to select online samples for incremental updates.

  3. arXiv cs.RO67

    CLAW: Learning continuous latent action world models from action-free video via adversarial regularization

    CLAW is a fully end-to-end self-supervised framework that jointly learns a world model and continuous latent action representations directly from videos without action annotations. It uses adversarial latent regularization to prevent the latent variables from encoding future observations, so that they capture action structure, and a diffusion model models environment dynamics as a distribution over future observations rather than a single deterministic rollout. The authors say this latent action world model supports imitation learning from observation and goal-directed planning, and outperforms existing methods in multi-task, multi-embodiment experiments.

  4. arXiv cs.RO80

    Learning-augmented robotic automation achieves cable insertion and soldering on motor production line

    The study proposes Learning-Augmented Robotic Automation, a hybrid system that integrates learned task controllers and a neural 3D safety monitor into conventional industrial workflows to automatically perform flexible cable insertion and soldering on a motor production line. Using less than 20 minutes of real-world data per task, the system ran continuously for 5 hours 10 minutes without physical fencing, producing 108 motors with a 99.4% pass rate on product-level quality inspection, a takt time close to that of human workers with smaller cycle-time variation, and solder-joint quality comparable to that of skilled operators.

    Why it matters: The paper reports data from continuous operation of learning-augmented industrial automation on a real production line for 5 hours 10 minutes, with 108 motors and a 99.4% pass rate, serving as a practical reference for learned control entering manufacturing.

  5. arXiv cs.RO62

    VLD: Visual Learned Distance as an Interface for Reinforcement Learning Navigation

    The authors propose the Visual Learned Distance (VLD) framework, which decouples perception learning from policy learning for image-goal navigation: first, a distance-to-goal predictor is trained self-supervised on about 3,000 hours of internet and simulated video; then, in simulation, a reinforcement learning policy is trained using privileged geometric distances perturbed by GeoNoise; at deployment, VLD predictions are used zero-shot.

  9. arXiv cs.RO60

    Flex-RSI: Benchmarking recursive self-improvement of frontier agents on vision and robotics tasks

    Flex-RSI is a benchmark for evaluating agents' recursive self-improvement capability under a fixed budget, covering perception, reasoning, robot action, 3D reconstruction, visual creation, and infrastructure tasks. In each round, an executor improves the task solution, which is kept only if it scores higher on held-out validation data; an improver then revises the harness, including the executor and itself. Final solutions are scored on hidden test data.

  10. arXiv cs.RO50

    Ordered Policy Optimization (OPO): A reinforcement learning policy optimization method with adaptive clipping ordered by importance ratios

    Addressing the problem that PPO uses a fixed clipping interval for all samples and cannot distinguish extreme importance ratios from tolerable large changes, the authors propose Ordered Policy Optimization (OPO): within each minibatch, it sorts the importance ratios, selects the extreme ratios that have the greatest effect on the update, and assigns them adaptive per-sample clipping radii according to a preset tail profile. The objective remains first-order and requires only minibatch sorting and a modified policy loss.

  11. arXiv cs.RO80

    Paper analyzes agentic manipulation policies: AMP1 achieves 85.6% zero-shot success rate

    The paper proposes agentic manipulation policies (AMP), in which a generalist AI model directly controls a robotic arm and adjusts its actions as the task progresses. The authors' reference implementation, AMP1, runs unchanged across single-arm, bimanual, and mobile manipulation.

    Why it matters: The paper reports zero-shot success rates and real-world trial data for a generalist AI model directly controlling a robotic arm, which can be compared with specialist policies such as VLA and WAM.

  12. arXiv cs.RO65

    Seeing What Matters: A Benchmark for Task-Conditioned Actionable Spatial Belief for Manipulation

    The authors propose the Seeing What Matters benchmark to evaluate task-conditioned actionable spatial belief in simulated tabletop manipulation, covering 860 frozen evaluation cases across three scenarios—coffee workstation, drawer/cabinet, and microwave—which expand to more than 115,000 evaluation episodes.

  13. arXiv cs.RO60

    SURE: Spatiotemporal Uncertainty Representation for Efficient Vision-Language-Action Learning

    SURE is a data-efficient vision-language-action (VLA) training framework that models spatial uncertainty with a lightweight transposed-convolutional probabilistic action decoder and uses Soft-DTW alignment supervision to accommodate temporal variation across demonstrations. On LIBERO, RoboTwin 2.0, and real manipulation tasks, SURE matches or exceeds baseline VLA manipulation success rates using only 10% of demonstration data or 20% of training steps.

  14. arXiv cs.RO60

    ODEAction proposes chunk-free action generation paradigm using ODE evolution instead of action-chunk prediction

    ODEAction proposes a chunk-free action generation paradigm that replaces the action-chunk prediction common in VLA models with continuous action evolution. It characterizes the rate of change of the current action over evolution time using a transition field over action space; during execution, it takes the current action as the initial condition and recursively generates subsequent actions via ODE integration. The method is implemented as an action head and does not depend on a specific vision-language backbone architecture. Experiments on LIBERO, EBench, RoboTwin, and real robots show better task performance and trajectory quality than matched action-chunking baselines, with particularly notable gains on fine manipulation tasks.

  16. arXiv cs.RO67

    DKWBC: A Humanoid Whole-Body Control Framework Decoupling Motion Tracking and Balancing

    DKWBC proposes a dynamics-informed whole-body control framework that uses inverse-dynamics feedforward and joint PD feedback to supply tracking torques, while a residual policy learns the joint-torque corrections needed for balance. The authors state that this structure explicitly separates motion-related torque demands, simplifying the policy learning task, and that they validated in simulation and on real hardware that a single balancing policy can generalize across multiple motion datasets, maintaining tracking and balance under ground support, added payload, and physical interaction. The project homepage has been made public.

  18. arXiv cs.RO60

    Horizon-Coupled Obstacle Guidance: inference-time obstacle avoidance guidance for relative-action diffusion policies

    This research proposes an inference-time obstacle-guidance framework for pretrained relative-action diffusion policies. It rolls out cumulative relative actions into a workspace trajectory, evaluates obstacle interactions along the trajectory with an SDF-based obstacle model, and during denoising propagates each obstacle response to all contributing action increments. In real-robot experiments across seven obstacle-constrained scenarios spanning four manipulation tasks, the method achieved 105/140 (75.0%) collision-free task successes, compared with 8/140 (5.7%) for absolute-action pointwise guidance. Ablations show that the temporally coupled form of relative actions yields larger gains under both obstacle models.

  19. arXiv cs.RO64

    MDF++: A Visuo-Tactile World Action Model with End-to-End Representation Learning

    MDF++ is a visuo-tactile world action model that uses a diffusion backbone to learn latent representations of multisensory observations end-to-end, addressing the problem that existing world action models rely on frozen pretrained encoders whose representations are not well suited for control. The authors propose a multi-task learning strategy that leverages cross-modal correlations to learn task-relevant representations, avoiding the feature collapse caused by naive joint training. On contact-rich manipulation tasks including real-world bolt screwing and nut mating, it outperforms world action models built on frozen pretrained representations by up to 50%.

  20. arXiv cs.RO65

    SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

    SUGARv2 proposes a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. The method adapts reusable task templates to different spatial configurations to synthesize coordinated robot and object motion references at low cost, and uses reference-based imitation as a common learning objective across tasks, first training privileged teachers and then training visual policies through teacher distillation and reinforcement learning.

  21. arXiv cs.RO71

    Auditing Grasp Feasibility Predictors with Planner-Verified Counterfactual Tests

    The study proposes a planner-verified counterfactual (CF) test: holding the grasp pose fixed, a solid obstacle is inserted into the approach corridor and its points are added to the model input, after which the planner re-derives the label, flipping it from feasible to infeasible. Across eight predictors spanning point clouds, voxels, depth, and object tokens, CF-pair AUROC falls from 0.920-0.996 in natural scenes to near chance (0.470-0.504), and this flip holds across four planners, two robotic arms, and a real-object obstacle.

  22. arXiv cs.RO79

    A2-MEAS: An Embodied Multi-Agent Framework with Code as a Scaling Interface

    The authors propose A2-MEAS, an embodied multi-agent framework that uses code as a scaling interface, combining corrective language, spatial evidence, execution history, and action proposals into correction codes; during training, MetaBrain provides supervision and runtime guidance.

    Why it matters: The framework uses code as a scaling interface, injects corrective language and execution history into the policy, and provides quantitative comparisons across benchmarks and real-robot tasks.

  24. arXiv cs.RO62

    RevoSim: A Scalable Multimodal Tactile Simulator for Dexterous Manipulation

    The authors present RevoSim, a multimodal tactile simulator for the BrainCo Revo3 dexterous hand that jointly models 285 piezoresistive taxels and 5 visuotactile fingertips. The simulator can synchronously generate pressure, depth, RGB, and marker-displacement observations; on a single RTX 5090, its depth-conditioned marker-displacement configuration supports up to 4096 parallel environments. The authors trained in-hand manipulation and grasping policies entirely in simulation, laying a foundation for future sim-to-real transfer.

  26. arXiv cs.RO65

    PRISM: Retentive VLA adaptation via in-context skill mixing routing

    PRISM represents reusable skills as parameter-level primitives, storing each skill family as a dedicated low-rank action-expert adapter, and combines and invokes them at inference via a block-wise VLM-conditioned router. On RoboCasa365, PRISM achieves a 56.43% atomic skill success rate and a 20.00% success rate on long-horizon composite tasks, compared with 17.86% and 17.50% for standard two-stage π0.5-LoRA fine-tuning.

  27. arXiv cs.RO65

    HomeLoop: A Robot-IoT Collaborative Simulation Framework and Benchmark for Home Assistance and Safety

    The authors propose HomeLoop, a simulation framework and benchmark built on Isaac Sim that integrates robot bodies, networked devices and wearables, simulated residents, faulty sensors, and hazards that evolve over time within a single environment. The benchmark contains 20 tasks across 5 categories, where the same alert can have different causes. A runtime monitor uses temporal logic to score both the final outcome and process actions, and each action has a preset cost.

  28. arXiv cs.RO63

    FATHOM: World-model-guided diffusion action-trajectory selection for sparse-marker AUV tracking

    FATHOM proposes a world-model-guided diffusion action-trajectory selection framework for relative tracking of autonomous underwater vehicles (AUVs) under sparse active light markers. The method first fuses marker observations, inertial measurements, action history, and temporal dynamics using a multimodal task-supervised recurrent state-space model to form a predictive tracking belief; a diffusion action prior then generates multiple multi-thruster trajectories, and the best candidate is selected under a receding-horizon objective and continuously updated based on onboard observations.

  29. arXiv cs.RO62

    ActPrune: Action-Grounded Visual Token Pruning for Efficient Vision-Language-Action Models

    ActPrune proposes a training-free visual token pruning method that moves the pruning decision ahead of the vision encoder and uses the action chunk predicted at the previous control step as a geometric prior. In the fixed third-person view, the method retains image patches near the projected end-effector trajectory along with semantic anchors; in the wrist view, it prunes patches that remain unchanged after compensating for action-induced camera motion.

  30. arXiv cs.RO58

    It Takes Two to Tangram: Multi-Agent Object-Centric Reinforcement Learning for Assembly

    The authors propose an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for continuous assembly control. A graph neural network represents the parts, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component; per-agent PPO with a centralized graph critic learns motion and temporal coordination within a single feedback policy. The study validates the approach on planar Tangram assembly, using procedurally generated target configurations and randomized initial layouts to support training and evaluation, and demonstrates parallel assembly in simulation and transfer to sequential execution on a real robot.

  31. arXiv cs.RO67

    ForPC: Force-Aware Whole-Body Control Framework for Humanoid Cart Pushing

    ForPC is a force-aware whole-body control framework that regulates a humanoid robot's cart-pushing speed through two-stage reinforcement learning. The method first infers force latent variables and state latent variables from onboard observations without external force sensors, then uses a residual policy to coordinate arm, waist, and leg movements; in simulation, cart-pushing speed RMSE is reduced by up to 68.2% compared with a locomotion-only control baseline, and lateral error on multi-curve routes is reduced by up to 74.2%.

  32. arXiv cs.RO69

    CS-Pi: Constraint-Satisfying Flow Policy Sampling at Inference Time

    CS-Pi proposes a "sample-project-renoise" flow-matching policy sampler that satisfies constraints absent from demonstrations at inference time while keeping actions plausible under the policy. The method projects each sample onto the nearest safe action, then adds noise back according to the size of the projection displacement and reruns the original policy until the sample is safe. On a 7-DoF shelf grasping task it achieves an 81% safe success rate, and 55% in zero-shot deployment on Franka, versus 55% and 40% for projection alone. The paper has been accepted to CoRL 2026.

  34. OFweek Robotics77

    Apple unveils HALO humanoid robot control system; Unitree G1 achieves 91% task success rate in unfamiliar environments

    Apple's research team published the paper "Perceptive Humanoid Motion from Simulation" on arXiv, unveiling HALO, an autonomous humanoid robot control system, and validating it on the Unitree G1.

    Why it matters: Apple's HALO splits task orchestration, motion generation, and tracking into three layers, and reports comparative results of 91% in unfamiliar environments and 70% on composite tasks, offering a look at its layered design and data synthesis pipeline.

Nov 8Sun
  1. Guyuehome58

    How Robots Recognize Objects Through Touch: From Material Classification to Contact State Judgment

    The article reviews the core issues in robotic tactile classification, pointing out that robots need to judge material, attributes, and state from contact signals rather than simply categorizing them. It emphasizes that task definitions must distinguish between material, attributes, and state to avoid label confusion, and notes that tactile readings are affected by action conditions and must be modeled in temporal and conditional contexts.

  3. Guyuehome58

    SuperMimic explained: how a differentiable world model moves humanoid whole-body control training onto a single GPU

    SuperMimic proposes a humanoid robot motion-tracking framework that uses a differentiable world model with 32-step backpropagation rollouts to reduce training compute demands when the motion library is large. The framework models physical laws with a deterministic incremental model and uses real states as the starting point for imagined rollouts. The original is an in-depth analysis; the body provides only a summary.

  4. Guyuehome62

    Long-WAM explained: using autoregressive video pretraining for long-horizon robot decision-making

    Long-WAM learns visual dynamics through autoregressive video pretraining and uses asymmetric causal attention to connect video and action experts, enabling long-horizon decision-making based on historical information. Its approach predicts future frames in latent space, combines historical information to generate action chunks, and supports streaming encoding and asynchronous execution.