We present RevoSim, a scalable and high-fidelity multimodal tactile simulator for the BrainCo Revo3 hand that jointly models 285 piezoresistive taxels and five visuotactile fingertips. RevoSim efficiently generates synchronized pressure, depth, RGB, and marker-displacement observations; on a single RTX 5090, its depth-conditioned marker-displacement configuration supports up to 4,096 parallel environments. We train in-hand manipulation and grasping policies entirely in simulation, establishing a foundation for future sim-to-real transfer. Project page: this https URL.
https://arxiv.org/abs/2611.08939
Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers simplicity and effectiveness, it fails to distinguish statistically harmful extreme ratio values from large, yet tolerable changes. We study how to adapt the clipping radius to the reliability of the induced importance ratio distribution. Our case study demonstrates that reliable updates require controlling these extreme ratios, rather than merely verifying that individual ratios fall within a fixed interval. Motivated by this observation, we propose Ordered Policy Optimization (\textsc{OPO}). In each minibatch, \textsc{OPO} sorts the importance ratios, selects the extreme ratios that potentially have the largest effect on the update, and assigns them adaptive sample-wise radii instead of using the fixed clipping radius. These radii are derived from a prescribed tail profile, which specifies desired target values for the selected extreme ratios. The resulting objective remains first-order and requires only minibatch sorting and a modified policy loss. Experiments conducted on MuJoCo and Atari benchmarks demonstrate that this simple modification achieves strong performance relative to established baselines.
https://arxiv.org/abs/2611.08936
Dexterous manipulation involves not only moving objects, but also arranging the hand around them to maintain useful contacts and enable subsequent actions. Yet many learning-based systems specify goals primarily through object poses or trajectories, leaving hand-object configurations to emerge implicitly. We introduce DexHOT, which formulates dexterous manipulation as hand-object configuration transfer: moving between feasible configurations that jointly specify hand articulation and object pose relative to the wrist. DexHOT learns a reusable relation-conditioned transfer primitive from synthetic feasible configuration pairs, without human reference motions, and composes long-horizon behaviors through closed-loop tracking of configuration subgoals. On DexHOTBench with 120 objects, a single policy achieves 80.5% transfer success on seen objects and 69.4% on unseen objects; on a real dexterous hand, it achieves 61.5% success over 200 real-robot transfers and 90% task success across six demonstration-guided tasks. These results show that explicit hand-object goals provide an expressive and composable interface for dexterous manipulation. More details and videos are available at this https URL.
https://arxiv.org/abs/2611.05119
This paper introduces the autonomous wellness robot as a distinct category of socially assistive system, defined by its capacity to continuously assess and respond across the seven ICAA dimensions of wellness (see Figure 2). We propose the Care Robot Autonomy Scale (CRAS): a six-level taxonomy (L0-L5) modeled on the automotive automation standard SAE J3016 and evaluated across four wellness-aligned dimensions. We present Ryan, developed initially at the University of Denver and commercialized by DreamFace Technologies, as a case study. NIH/NIA-funded longitudinal evidence (N = 18; 887 hours) shows statistically significant cognitive improvement (SLUMS +2.61, p = 0.015) and a clinically meaningful directional reduction in depressive symptoms (PHQ-9 -2.50, p = 0.073), with no novelty effect. We position Ryan today at CRAS Level 1-2, with emerging Level 3 capabilities in some dimensions, and outline a three-phase roadmap to L5 (full autonomy) by the early 2030s.
https://arxiv.org/abs/2611.08930
Human videos contain abundant object-manipulation demonstrations, but they do not directly provide motion cues that a robot can follow. We present HOC2R, a Hand-Object Contact trajectory extractor for Robot motion that combines frozen DINOv3 and SAM 2.1 features with learned heads for hand-object association and contact localization. HOC2R supports two modes: count-aware automation that detects, counts, and localizes visible contacts in untrimmed videos, and fixed-two localization for two-finger grippers when contact frames are known. On a 30-task point-annotated benchmark, count-aware automation improves contact-count accuracy from 58.1% to 71.4% and reduces mean localization distance from 19.81 to 10.46 pixels relative to an adapted VRB2 baseline. On seven unseen RGB-D rollouts, a five-task fixed-two checkpoint reduces mean localization distance from 67.67 to 27.02 pixels. Across six robot evaluation sequences, the 30-task fixed-two checkpoint produces four feasible trajectories and succeeds on three tasks, compared with two feasible trajectories and one successful task for each adapted baseline. HOC2R is competitive in the evaluated single-hand scenes, robust to the hand-color shift, and strongest in the evaluated multi-hand scenes. These results support HOC2R as a practical pseudo-labeling method for extracting robot-usable contact trajectories from human demonstrations.
https://arxiv.org/abs/2611.08920
Vision-Language-Action (VLA) models promise a single language-conditioned policy adaptable to many manipulation behaviors, yet deployment additionally requires skill retention and long-horizon composition: a policy must retain previously acquired skills and reuse them inside composite tasks whose behavior changes across phases. The standard recipe absorbs every new task into one shared update, which provides neither a parameter-level locus for reusable skills nor a mechanism for invoking each skill along the trajectory. We observe that this missing structure is latent rather than absent: per-skill low-rank updates of a pretrained VLA occupy a robustly distinguishable, low-dimensional subspace, and a single composite-task LoRA concentrates roughly half of its Frobenius energy in this subspace, against a near-zero matched random-rotation control. Building on this geometry, we introduce PRISM, which represents reusable skills as parameter-level primitives: each skill family is stored as a dedicated low-rank action-expert adapter in a primitive bank, primitives are augmented with skill-specific low-rank residuals and composed at inference by a per-chunk VLM-conditioned router that reads the prefix representation to track task progress, and the router is supervised by per-chunk labels from a deterministic, task-conditioned, action-derived oracle. During composite training, the vision encoder, the language LoRA, the skill residuals, the router, and the shared action projections and time MLP are updated; every primitive is held frozen, so the base per-skill action-expert adapters are preserved by construction. On RoboCasa365, PRISM achieves 56.43% atomic-skill success and reaches 20.00% on long-horizon composite tasks, while a standard $\pi_{0.5}$-LoRA two-stage fine-tune reaches 17.86% atomic and 17.50% composite success. We additionally validate PRISM on an AgileX PIPER real-robot setup.
https://arxiv.org/abs/2611.08917
Recent progress in embodied robotics is bringing robots closer to deployment in homes, as vision-language models (VLMs) are demonstrating significant advances in reasoning, making VLM-driven robots promising home assistant agents. These agents will often be introduced into homes that already have cameras, Internet of Things (IoT) devices, and residents with wearables. To fulfill their potential, they need to integrate with existing smart infrastructure and reason through ambiguous scenarios: a smoke alarm may come from a pan about to ignite, a pan already on fire, a resident cooking or a faulty sensor, and each calls for a different response. To that end, we introduce HomeLoop, a simulation framework and benchmark built on Isaac Sim that combines robot bodies, networked devices and wearables, simulated residents and visitors, faulty sensors, and hazards that evolve over time. Our benchmark is composed of 20 tasks across five families grounded in real-world household hazards and needs, and designed so that the same alert can have different causes. A runtime monitor scores each episode with temporal-logic checks on the final outcome and the actions along the way, and every action carries a predefined cost. We evaluate six open-weight and proprietary VLMs. The best achieves a family-balanced score of 61.9%, and across models we see a pattern of over-reaction: failed episodes involving prohibited interventions outnumber those involving missed required interventions by more than two to one, with models often shutting off the stove before investigating the alarm's cause. HomeLoop is an extensible foundation intended for use in research on robot-IoT coordination, long-term memory, proactive assistance, and privacy-safety trade-offs. HomeLoop will be released with 2,100 home layouts that can be automatically furnished in diverse configurations, five robot bodies and 20 networked device types.
https://arxiv.org/abs/2611.08914
Skylight polarization provides directional cues for robotic navigation, but fisheye lens effects and analyzer imperfections can degrade polarization measurements across the field of view. We present a joint lens-analyzer calibration method that explicitly models incidence-dependent lens transmission together with analyzer gains and angular offsets in a unified eight-parameter formulation. Given known geometric calibration, rotations between camera frames can be estimated using visual features and cross-frame directional polarized light consistency can be used for polarization calibration. Therefore, our calibration approach requires only a short handheld outdoor sequence under natural skylight, without dedicated polarization calibration equipment or a predefined sky polarization model. On real-world outdoor sequences, the proposed method achieves a weighted cross-frame angle-of-linear-polarization (AoLP) mean absolute error below 0.5° across all incidence angles, with a 73.4% reduction in the 80°-90° incidence angle region, and generalizes to an independent sequence with an overall mean absolute error of 0.466° without refitting. Preliminary solar-azimuth experiments using a camera mounted on a quadruped robot further show improved alignment with the visible solar center, supporting the potential of calibrated AoLP measurements for relative-heading estimation and future polarization--inertial navigation. The calibration software tool will be released upon acceptance of this paper.
https://arxiv.org/abs/2611.08911
Reliable relative tracking is fundamental to cooperative autonomous underwater vehicles (AUVs), yet remains challenging under nonlinear vehicle dynamics and degraded underwater visual conditions. Active light markers improve robustness to appearance variation, but provide deliberately sparse observations that can become incomplete or corrupted by occlusion, reflections, and detection noise during dynamic motion. To address the resulting partial-observation control problem, this paper proposes FATHOM, a world-model-guided diffusion action-trajectory selection framework for sparse-marker AUV tracking. FATHOM first integrates structured marker observations, inertial measurements, action history, and temporal dynamics into a predictive tracking belief using a multimodal task-supervised recurrent state-space model. A diffusion action prior then generates multiple expert-like multi-thruster trajectories, whose future tracking consequences are predicted through the learned latent dynamics. Rather than directly executing a generated trajectory, FATHOM selects the most favorable candidate under an explicit receding-horizon objective and continually updates the decision from onboard observations. Extensive offline analyses verify the learned predictive belief, multi-step world-model prediction, diffusion trajectory generation, and predictive selection. More importantly, comprehensive real-AUV experiments, including strong pose-based comparisons and component ablations, demonstrate robust autonomous tracking across nominal and challenging motions with naturally occurring partial marker visibility, while maintaining real-time onboard operation without motion-capture feedback.
https://arxiv.org/abs/2611.08898
Operators can state safety constraints for robots as prohibitions such as "do not put the bowl on the stove". We study whether OpenVLA follows such prohibitions and where it represents the goal it executes. The 10 tasks of LIBEROGoal share one scene, so we can label the goal that each rollout executes. We combine closed-loop rollouts with activation patching, linear probes, activation steering and runtime monitors. On LIBERO-Goal, negation had no detectable effect on which task OpenVLA executed. The model executed the forbidden task in 79% of negated rollouts and completed 78% of plain tasks. A goal probe gives similar read-outs under "not X" and "X". Activation patching shows that the first action depends mostly on the instruction tokens before layer 12 and on the last prompt token from layer 16 onward. A fixed steering vector at the instruction tokens at layer 8 redirected 12 of 18 rollouts. Fixed vectors and prefill patches at layers 12 to 20 redirected none of 158. From layer 16, only patches at every decoded action token redirected the robot (15 of 18 rollouts at layer 24). When the instruction changes during a rollout, the layer-32 goal read-out detects non-compliance better than failure detectors, and an external probe on image and instruction features performs comparably. These results support enforcing prohibitions outside the instruction and monitoring goal read-outs against the specification. Goal edits in OpenVLA should act before layer 12 or patch every action token.
https://arxiv.org/abs/2611.08895
In recent years, massively parallelized rigid-body simulation has played a central role in robotics research, enabling rapid progress in areas such as reinforcement learning, stochastic optimal control, and randomized smoothing-based trajectory optimization. Particularly in contact-rich settings, the scalability of such simulations in large part depends on well-optimized representations of collision geometry, often requiring a coarse approximation of the underlying surfaces using primitives such as spheres, capsules, cylinders, and boxes. Whenever the complexity of the surfaces or the precision demands of the application render such approximations insufficient, it is instead necessary to employ mesh-mesh collisions, which impose a significant reduction in throughput. This paper proposes a simulation framework designed from scratch to address this bottleneck, with novel routines for broadphase and narrowphase collision detection as well as the subsequent contact dynamics computation. As experimentally validated, the framework matches existing well-established simulators in terms of physical faithfulness, and can achieve approximately an order of magnitude higher throughput in the detailed mesh-mesh collision setting that it specializes in. The source code is available at this https URL.
https://arxiv.org/abs/2611.08872
Lodos-v2 is a GPU-based simulation framework for massively parallel rigid-body dynamics with contact. It is specifically designed to achieve high throughput in scenes involving collisions among large numbers of detailed meshes. Its predecessor, Lodos-v1, had two main limitations. First, it solved the standard convex relaxation of cone-complementarity-based contact dynamics, thereby inheriting well-known physical artifacts, including lift-off and artificial compliance in the normal direction, as well as creep in the tangential direction. Second, its contact-group reparameterization scheme, which rescales spring-damper forces using a single factor per collision pair, could not be integrated with other constraints required by a full-fledged simulator, such as joint limits and welds. Lodos-v2 addresses both limitations through two main contributions. First, it introduces an efficient algorithm for solving the exact frictional contact problem by sequentially solving a cascade of convex relaxations in primal form within an outer proximal minimization loop. Second, it extends the contact-group reparameterization scheme of Lodos-v1 to the primal formulation of cone-complementarity-based contact dynamics, enabling its integration with the other constraints of a full-fledged simulator. Experiments demonstrate that these contributions result in throughput improvements over established rigid-body simulation frameworks. The source code is available at this https URL.
https://arxiv.org/abs/2611.08868
Assistive robots and search-and-rescue platforms require reliable human state sensing in smoke, darkness, and privacy-sensitive environments, where cameras and LiDAR may be unreliable Millimeter-wave radar offers an alternative that works without ambient light, penetrates smoke, and does not capture visual appearance. However, the compact arrays that fit robot size, power, and cost budgets have limited apertures, producing joint-localization errors on the order of decimeters at a few meters, large enough to compromise the safety margins and tracking accuracy a robot depends on. Existing pipelines reduce pose error through frame fusion, multiple viewpoints, return selection, or stronger estimators, but examine one technique at a time, without relating its effect to a shared measurement limit or separating gains from added information from gains from estimator completion. We address this gap with a framework that models the human and environment as one time-varying scattering field and states a Cramer-Rao type error floor for joint localization as a function of bandwidth, aperture, signal-to-noise ratio, fused frame count, phase coherence, and visibility of retained returns. We then use existing frame fusion, multi viewpoint, return selection, and pose estimation methods as matched probes of this floor rather than as competing pipelines. Under the evaluated conditions, experiments on three datasets and a live deployment show these strategies move joint localization error in the predicted directions, for example lowering mean per-joint position error from about 97 to 65 mm with a second viewpoint, while a stronger estimator mainly lowers overall error by completing joints the measurement cannot resolve. These results give the robotics community a principled basis for deciding whether to prioritize observation design or estimator capacity when deploying reliable mmWave human sensing.
https://arxiv.org/abs/2611.08863
Learning locomotion directly on a humanoid robot is a promising direction to avoid the sim-to-real gap. However, locomotion rewards in Reinforcement Learning (RL) typically track the base velocity, which cannot be measured onboard without an external motion capture system or well-calibrated state estimator. This is why we introduce \method{}, which learns humanoid locomotion from minutes of samples with a reward that only requires the onboard Inertial Measurement Unit (IMU). Instead of tracking the base velocity, STRIDE rewards the robot for following a commanded acceleration profile. To learn efficiently from this reward, we use the off-policy RL algorithm XQC and combine a high gain setting for the joint position controllers with left-right symmetry augmentation. In simulation, STRIDE learns to walk on the Unitree G1 and Booster T1 humanoids within 14 minutes of samples. Compared to learning without these two components, it reduces the falls during training by 81%, while without them the robot learns only in over an hour.
https://arxiv.org/abs/2611.08857
Vision-language-action (VLA) models perform versatile manipulation tasks from language instructions, but their inference cost limits how fast a robot can respond in closed-loop control. Visual token pruning reduces this cost; however, prior methods estimate token redundancy from encoded visual embeddings or attention, only after the visual encoder has processed the entire observation. We propose \ours, a training-free token pruning method that moves the pruning decision ahead of the vision encoder by grounding it in a geometric prior derived from the robot's own action. The action chunk predicted at the previous control step is already available before the current observation is encoded, and it specifies the end-effector and camera motion between consecutive observations. The same action affects the two standard camera views asymmetrically: in the fixed third-person view, \ours retains patches along the projected end-effector trajectory together with semantic anchors, while in the wrist view, it prunes patches that remain unchanged after compensating for the action-induced camera motion. Extensive experiments on two simulation environments (LIBERO and VLABench) and four real-robot tasks demonstrate that \ours achieves up to 1.61 $\times$ speedup and 59.5\% FLOPs reduction with negligible degradation in success rates.
https://arxiv.org/abs/2611.08827
Geometric assembly requires fine spatiotemporal coordination to place parts without causing collisions or deadlocks under tight clearances. To address this, we present 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 pieces, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component. Per-agent proximal policy optimization with a centralized graph critic directly learns motion and temporal coordination within a single feedback policy. We study this formulation through planar Tangram assembly, where pieces must slide and rotate into a given configuration while remaining on the assembly surface. Procedural generation of target configurations and randomized initial arrangements support training and evaluation across diverse assembly problems. Our experiments isolate the roles of relational structure and multi-agent optimization, and compare learned control with sampling-based planning. We demonstrate concurrent assembly in simulation and transfer the policy to sequential execution on a real robot, as our object-centric formulation decouples learned assembly coordination from low-level physical control. Project page: this https URL
https://arxiv.org/abs/2611.08814
Recent advances in robot foundation models have highlighted the potential of in-context learning (ICL) for adapting robot behavior from demonstrations without further fine-tuning. Previous work has used retrieval-based post-training to equip pretrained vision-language-action (VLA) models with the capability for ICL by teaching them to condition action predictions on retrieved visually-relevant demonstration chunks. However, the effectiveness of retrieval hinges on selecting context relevant to the current execution stage, which visual similarity alone may not capture. We introduce VICTR, a framework enabling in-context learning in VLAs via progress-informed context retrieval built around an In-Context Value Function Estimator (IC-VFE). IC-VFE conditions on a reference demonstration video, a language instruction and the current observation to estimate task-relative progress. By conditioning progress estimation on a reference demonstration, IC-VFE can align the current state with a demonstrated execution even for tasks unseen during training. VICTR uses the estimated progress to select demonstration chunks at corresponding stages of execution and supplies them to a $\pi_{0.5}$ policy post-trained for in-context action generation. On unseen out-of-domain real-world manipulation tasks, VICTR raises the success rate from 6.2% for a fine-tuned $\pi_{0.5}$ baseline to 23.8% and more than doubles the task progress rate, from 28.9% to 55.5%. Project page with code, data and videos: this https URL
https://arxiv.org/abs/2611.08698
Automated vehicle (AV) deployment in the United States is expanding without a unified federal certification framework, leading to substantial variation in how states authorize and oversee AV testing and deployment. This paper examines how U.S. states regulate Society of Automotive Engineers (SAE) Level 4-5 automated driving systems (ADS), identifies common certification approaches, compares them with international practices, and evaluates the implications for North Carolina's future regulatory strategy. Publicly available state statutes, administrative regulations, agency guidance, and federal policy documents were reviewed. Ten states, selected to capture the range of regulatory approaches, were analyzed using a structured framework covering operational scope, governance and oversight, federal interaction, and implementation outcomes. Certification practices in the European Union, China, Japan, and Australia were reviewed for comparative context. Three state certification models were identified, reflecting increasing regulatory involvement: baseline legal compliance, administrative self-certification with ongoing oversight, and permit-based authorization requiring formal agency review before deployment. North Carolina currently aligns with the baseline compliance model. International frameworks are converging toward scenario-based testing, operational-design-domain-specific approval, safety-case documentation, cybersecurity assurance, and lifecycle oversight, although direct transferability to the U.S. is limited. The paper develops a three-model typology for comparing state AV certification approaches and integrates state practices with international frameworks, providing a consistent basis for evaluating differences in regulatory involvement, governance complexity, and institutional responsibilities across jurisdictions.
https://arxiv.org/abs/2611.08681
Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based approaches impose infrastructure requirements; simulator and world-model evaluators additionally face prediction errors that can compound over the evaluation horizon. In this paper, we study off-policy evaluation as an alternative to rollout-based robot-policy evaluation methods. Specifically, we introduce RoboFQE, an evaluator that estimates the discounted expected return of a target policy from offline robot trajectories without estimating a behavior-policy density, combining fitted Q-evaluation with a pretrained vision foundation model and learned terminal success annotation to bridge the gap between standard OPE benchmarks and continuous-control visual manipulation. Controlled experiments across simulated and real-world manipulation tasks show that RoboFQE produces accurate discounted-return estimates and preserves policy rankings even on long-horizon manipulation tasks where video world-model evaluators are degraded by autoregressive prediction errors. Ablation experiments show that pretrained vision encoders substantially outperform from-scratch alternatives, particularly on long-horizon tasks, and that learned terminal success annotation enables evaluation without ground-truth reward labels with only slight reduction of accuracy.
https://arxiv.org/abs/2610.18699
Humanoid robots are expected to take over strenuous material handling in manufacturing, logistics, and healthcare, where operating existing wheeled carts would let them move heavy loads without modifying the workplace. However, humanoid cart pushing remains challenging because the bimanual grasp closes a force-coupled loop in which the contact wrenches that drive the cart also disturb the robot's balance, and payload changes alter the coupled dynamics. We propose ForPC, a force-aware whole-body control framework that regulates cart velocity through two-stage reinforcement learning. A locomotion prior is first trained under varied hand loads and upper-body postures to provide balance support. A force latent and a state latent are then inferred from onboard observations, without external force sensors, and fed to a residual policy that coordinates bounded arm, waist, and leg adjustments with base-velocity commands. Multi-objective rewards penalize bimanual internal opposition, grasp slip, and actuator saturation, encouraging the policy to apply contact force on demand without human demonstrations. Sim-to-sim experiments show that ForPC reduces cart-velocity RMSE by up to 68.2% relative to a locomotion-only baseline (Loco-only) and cross-track RMSE by up to 74.2% on the multi-bend route. Trained solely in simulation, the policy also transfers to a physical Unitree G1 without real-world training or fine-tuning and, with no payload-specific adjustment, pushes a cart carrying up to 30 kg at 0.5 m/s. These results suggest that humanoid robots could eventually replace humans for efficient material handling in daily life.
https://arxiv.org/abs/2611.08664