Intent-driven exoskeleton control needs a continuous, causal estimate of the wearer's joint kinematics and an answer to a second question: whose data should train the estimator for a new user? Borrowing the user's recordings of other activities, or other users' recordings of the same activity, is usually evaluated as "more data" versus "less data," which confounds the information a source carries with the optimizer updates it adds and hides negative transfer behind averages. We separate these effects for hip, knee, and ankle angle estimation from high-density sEMG and an IMU across six locomotion activities on all ten participants of a public dataset. A compact residual causal TCN-GRU decoder is frozen, and an update-matched replay control prices every added source against the same number of updates on the user's own data. A user's own other activities raise $R^2$ from 0.722 to 0.788, of which +0.048 is information beyond replay; stair descent is a reliably harmful donor and sit-stand-walk a reliably beneficial one. Other users' same-activity data help while the user has only the target activity ($G_\mathrm{T} = +0.053$) and half as much once own other-activity data exist ($G_\mathrm{W} = +0.028$); at full calibration, donor value collapses after one to two target records. Per-target gains from the two sources correlate, and leave-one-participant-out gates recover most of the cross-subject value only at low calibration. Data value is hierarchical, state-dependent, and directional; the bottleneck is deciding, without test labels, when to transfer.
https://arxiv.org/abs/2611.19238
In simulation, Vision-Agent-Action (VAA) performs pick-and-place in robot cells with gripper or base-frame changes without robot demonstrations or fine-tuning. It uses pre-trained vision-language and language models for interpretation, measures the command map and camera geometry from its own motion and fingertips, estimates lens distortion, and plans grasps from measured object depth. A controlled study of eight public LIBERO-fine-tuned vision-language-action models (VLAs) varies robot hardware, camera geometry, appearance, and base frame. Gripper and frame changes dominate their losses in the tested fractional design. Across 18 cells with these changes, frozen VAA achieves 230/360 successes (64%), the refined VAA 268/360 (74%), and the strongest released VLA on this subset 76/360 (21%). Paired ablations support the self-calibration bundle, lens estimation under compounded changes, and the measured-depth pipeline. On a two-step LIBERO-Goal chain with object state carried between instructions, VAA completes 54/60 chains in changed cells, while four evaluated VLAs complete none.
https://arxiv.org/abs/2611.19198
Imitation learning for visuomotor policies typically relies on teleoperated robot demonstrations, which are costly because every episode requires a trained operator controlling a physical robot in real time through teleoperation interfaces and wearable body-tracking hardware. Egocentric glasses capture human demonstrations without a robot or handheld grippers, yet they track only the head and in-view human hands, and directly copying human motion to a robot with different stature, arm reach and hand morphology fails to produce feasible contacts. \method{} converts egocentric glasses recordings into physically verified robot training trajectories. An agentic real-to-sim stage reconstructs collision and textured visual assets from the recorded RGB-D and head streams, completes unseen surfaces when needed, and predicts target contact bands on the manipulated objects. During motion adaptation, a grasp planner turns each contact band into a feasible robot wrist pose and finger closure, bilevel stance optimization plans collision-free standing postures that keep hand targets reachable, and a whole-body motion generator synthesizes lower-body locomotion and out-of-view arm motion. Two-stage motion correction then blends visibility transitions kinematically and trains a reinforcement-learning tracking policy in physics simulation under agent-designed semantic rewards, completing manipulation phases even when the object leaves the camera view. Rendering the reconstructed scene through the robot's onboard camera along the optimized rollout yields synchronized robot-view images, proprioception and verified action labels. Fine-tuned exclusively on this converted dataset, without real-robot demonstrations, GR00T N1.7 performed loco-manipulation tasks autonomously on a Unitree G1. Project page: this https URL
https://arxiv.org/abs/2611.19196
Reinforcement learning (RL) can teach robot teams to navigate shared spaces, but trial and error causes collisions that real robots cannot afford. Control barrier function (CBF) safety filters prevent these collisions by correcting unsafe actions, yet in a team the filter becomes a centralized optimization whose number of constraints grows quadratically with the team size. We propose an approach that builds the filter's safety into the RL policy and examine how such a system behaves during filter-free deployment. However, the filter that keeps training safe also hides what the policy must learn: it masks the cost of unsafe actions, which actor-critic methods then overvalue, and it keeps near-collision states out of the training data. Our approach therefore learns only from executed safe actions with implicit Q-learning and distills the filter into the policy at synthetic near-collision states. We prove that filter distillation loss bounds the policy's constraint violation and hence how far agents can cross their safety margin, so errors never accumulate. When distillation states cover deployed states, the loss also bounds the collision probability at every step. Without a filter and acting only on local observations, our policies have no collisions in 1,800 test episodes with multiple agents. A policy trained with three agents transfers zero-shot to teams of twenty at constant per-agent computation and stays collision-free with up to eight agents. We test our policies on Crazyflie quadrotors with up to five flying at the same time.
https://arxiv.org/abs/2611.19190
Recovering the forces behind a motion is ill-posed: different controllers can reproduce the same movement while generating different contact forces. Physics-based motion imitation resolves this ambiguity through simulation, but relies on fixed-gain proportional-derivative (PD) control. We show that fixed gains impose a trade-off between motion and force tracking, as contact and swing place conflicting demands on joint stiffness and damping. We introduce ImpedanceMimic, a reinforcement-learning policy that modulates per-joint stiffness, damping, and position setpoints from motion and force measurements, but requires only motion at inference. Across 129 participants and six activities, ImpedanceMimic outperforms matched fixed-gain PD under every integration scheme, direct-torque, muscle-actuated and existing imitation controllers in kinematic and force fidelity, approaching a dedicated motion-to-force regressor. By expressing gains as multiples of inertia-scaled priors, a single policy controls subject-specific biomechanical models without explicit anthropometric input and transfers zero-shot to unseen humans and a humanoid robot. The learned impedance forms a low-dimensional representation of motor state, shared across bodies, that generalizes to withheld activities: stiffness scales with load, and damping anticipates unloading.
https://arxiv.org/abs/2611.19153
Autonomous driving is turning to vision-language-action models (VLAs). They answer and plan by decoding, one step at a time. Each step is another forward pass, so a plan can take over a second of GPU time. Embodied AI often pairs such a slow, reasoning System 2 with a fast System 1 that acts. Human drivers plan at a glance, with System 1. Faster designs usually put System 1 outside the vision-language model (VLM), in a planner without its abilities. Yet before a VLM writes its first token, it has already read the scene into one hidden state. We show that, once trained, this hidden state is enough to drive and to answer questions about what the model sees. SuperGlance reads it to turn a decoder-only VLM into an encoder-style driving policy. Its linear head scores a fixed set of 5,273 candidate trajectories. With the set fixed, rewards are computed offline, so supervised targets can be reward-weighted and reinforcement learning maximizes the exact expected reward. Before and during policy training, multiple-choice training keeps the VLM's visual abilities in one pass, so the policy still answers questions about driving scenes. Training questions are built against shortcuts. Each must be answered right in two option orders. Against drift, a KL term keeps each stage near its starting model. One pass offers VLAs a more plausible path to System 1. SuperGlance answers visual multiple-choice questions as well as its base VLM does by decoding. It plans in 84 ms of GPU time, six times faster than Qwen-Drive-1.0, and at least as well on NAVSIM, PAI-AV and WOD-E2E. In AlpaSim closed loop, km per at-fault incident holds for both planners up to a 300-ms delay and drops beyond. With GPU time charged as delay, SuperGlance's lead over Qwen-Drive-1.0 grows from 2.8 to 3.9 times. Delayed by 1.2 s, our model falls below Qwen-Drive-1.0 at its own 518 ms.
https://arxiv.org/abs/2611.19138
Vision-language-action (VLA) models enable embodied artificial intelligence (AI) by translating visual observations and language instructions into robotic actions. Emerging use cases in physical AI are expected to drive the need for efficient inference and communication, as the computational demands of the VLA models pose challenges for real-time control with limited onboard resources. Test-time scaling through latent reasoning allows these models to refine hidden representations without generating explicit chain-of-thought (CoT) tokens, but introduces a trade-off between task success, inference latency, and energy consumption. In this paper, we address the efficient collaborative inference under a realistic communication scenario. We propose a wireless edge-assisted framework for adaptive latent reasoning (WEALR) that augments onboard computation with edge computing. A decision-making agent jointly selects the execution location and latent-reasoning convergence threshold. We formulate this joint adaptation as a constrained Markov decision process (CMDP). A Lagrangian-constrained deep reinforcement learning (CDRL) approach, namely trust region policy optimization Lagrangian (TRPO-Lag), learns to balance task performance and resource consumption under varying wireless conditions and task requirements. We evaluate the framework using LIBERO manipulation tasks, profiled VLA inference costs, and ray-traced wireless channels. Experimental results demonstrate that TRPO-Lag achieves up to 23% higher feasibility-weighted task success rate compared to benchmark CDRL methods.
https://arxiv.org/abs/2611.19131
We study supported reaching to extend a humanoid robot's workspace by bracing against the environment for stabilization using a straightforward yet capable whole-body model predictive control (MPC) approach, exclusively with local sensing and fiducial markers. While typical solutions for whole body humanoid control aim at avoiding or accommodating contact, contact is explicitly required to reach objects placed on surfaces far out of normal reach. We employ sampling-based MPC for whole-body leaning, bracing, reaching, and recovery on a Unitree H1-2 humanoid. The controller runs in real-time at 34 Hz on a laptop, transfers sim-to-real, extends reach by about 50 cm beyond the unbraced standing workspace, and sustains the loaded posture for over four minutes, before pose estimation drifts. The controller reaches the commanded target in 89% of trials and completes the full reach-and-recovery cycle in 81%, across 54 trials spanning six targets and three table heights. We further characterize why such a small real-time sampling budget is sufficient, finding that temporal persistence of sampled actions and exploration scale strongly govern success, while CEM provides the widest operating region over planning rate and model mismatch. These results establish a real-world baseline for online, contact-rich humanoid manipulation. Code, videos, and full hardware details are available at this https URL
https://arxiv.org/abs/2611.19100
Hamilton-Jacobi (HJ) reachability computes the maximal safe set and a safety filter for a given obstacle configuration, but it must be re-solved whenever the obstacles change, which a deployed robot cannot afford. Learning a single value function conditioned on the obstacle set removes the re-solve, yet it sharpens the central weakness of learned reachability: one network must now cover a whole family of safety problems, and its approximation error carries no preferred sign, so rare obstacle configurations silently produce false-safe states. To address these challenges, we present a conditioned reachability model designed so that the remaining error falls on the conservative side. Specifically, our method caps the obstacle margin, which makes the value function provably local, in the sense that obstacles farther than a known threshold cannot affect it, so the model reads only a body-frame window, trains on small scenes, and transfers to scenes of any size with millisecond per-scene preparation. Moreover, the output structure builds the value bound into the model. By training with counterexample mining over the finite-dimensional window configuration space, we maximize the claimed safe volume subject to the HJ inequality, so the learned set grows toward the true safe set from the conservative side. Across all tested obstacle settings, ours is the only method that combines recovery comparable to per-scene DeepReach training with near-zero rollout collisions. We also extend the method to a 10D quadrotor, again with markedly lower collision rates than the baselines.
https://arxiv.org/abs/2611.19088
Integrating MLLM-based agents with robotic foundation models has attracted increasing attention as a means of enhancing robotic capabilities. However, the improvement of such integrated systems remains largely decoupled across their agent and model components, with advances in one component not necessarily benefiting the other, substantially limiting the capabilities of the combined system. As both MLLMs and robotic foundation models become increasingly capable, fully realizing their combined potential calls for co-evolution, an iterative process in which improvements in agents and robotic foundation models reinforce one another. We propose RoboCoEvo, a failure-guided co-evolution framework that couples the refinement of the agent's explicit and reusable executable knowledge with parameter learning in robotic foundation models, such as vision-language-action (VLA) models. Through a code-as-policy formulation, the agent develops and refines executable failure-detection and recovery programs, generating targeted corrective experience. Post-training consolidates the resulting corrective behaviors into the robotic model's end-to-end policy, improving autonomous task execution. Changes in the updated policy's failure distribution, in turn, guide subsequent revisions to the agent's programs. Experiments on BEHAVIOR-1K, RoboCasa, and RoboTwin demonstrate sustained improvements in autonomous VLA task performance across successive co-evolution rounds.
https://arxiv.org/abs/2611.19081
Diffusion policies, which generate short action sequences by denoising random noise, are a leading way to learn robot skills from demonstrations. Once deployed, they meet constraints the demonstrations never contained, and retraining for each is impractical. A safety filter edits the policy's action to satisfy them, but the edit ignores the task, and a large edit can leave the policy where it cannot continue. We propose CAST (Certified Action Selection at Test time): draw a few action chunks from the frozen policy, certify each with a barrier condition, and execute the certified chunk that a learned value ensemble ranks highest. We prove that a certified step is safe whatever the critic does; that, whenever a certified sample exists, the executed chunk stays within log N nats of the policy conditioned on feasibility, while a safety-filter projection can be singular to it; and that an exact closed-loop identity splits the gain of ranking into availability, spread and the critic's target. Certifying the next chunk is not enough: a generative controller can have safe actions available now and none later. We characterise the safe control authority of a frozen policy under finite sampling, and CAST-V preserves it through a policy-conditioned viability, estimated with a model under a finite-sample guarantee or learned from the controller's own logs (CAST-VL). On robomimic manipulation, a planar quadrotor, a MuJoCo humanoid and a unicycle, with frozen policies, CAST raises joint task-and-constraint success above the output filter in nearly every setting; certifying before ranking is decisive where a filter's edit is large, and viability removes most dead ends that one-step certification cannot see. Project page: this https URL.
https://arxiv.org/abs/2611.19047
A frozen chunked robot policy can spend deployment-time inference compute in two coupled ways: more work within each policy call to refine a predicted action chunk, or more frequent policy calls to replan from fresh observations. We study this allocation without updating model weights. Our evaluation procedure reports success with both nominal compute rate and complete attempt cost, selects comparisons on discovery tasks, and tests prespecified comparisons on held-out tasks. Comparisons added after inspecting the held-out results only summarize observed patterns. We demonstrate the procedure with one frozen SmolVLA checkpoint in synchronous LIBERO simulation, using denoising count as the refinement control and fixing chunk length at K=50. Arithmetic and latency characterize cost differently: at d=10, 82.1% of counted arithmetic is independent of denoising, whereas a descriptive affine fit to fixed-input host time assigns 17.7% to its intercept. At h=2, d=2 succeeds on 139/160 attempts versus 122/160 for d=5 (+10.6 percentage points; task-conditional 95% interval: +4.4 to +16.9), while using 5.9% less arithmetic per control step. Executing h=5 rather than h=2 at d=2 yields 138/160 versus 139/160 successes and 60.7% lower arithmetic per attempt; equivalence is not established. The case study shows why deployment adaptation must evaluate generation effort and feedback frequency jointly; it does not define a universal setting.
https://arxiv.org/abs/2611.19034
This paper argues that the robotics and AI community should adopt disclosure standards for demonstration videos. As physical and financial constraints limit direct public access to embodied AI, public dissemination of progress in robotics is mainly through curated demonstration videos rather than direct experience with the technology. In a large-scale (N=9,341), pre-registered experiment across six countries, we find that the general public struggles to discern both the visual authenticity (e.g., distinguishing real footage from CGI) and behavioral authenticity (e.g., distinguishing autonomy from teleoperation) of robot demonstration videos. The omission of these details distorts public perception, leading people to overestimate the ability of robots to perform tasks and navigate real world environments. Using evidence from behavioral science, we design a disclosure intervention and demonstrate that the inclusion of clear disclosures in robot demonstration videos significantly improves discernment of visual and behavioral authenticity, as well as understanding robots' capabilities. We propose the adoption of disclosure standards for robot demonstration videos to accurately calibrate public expectations and promote transparency in robotics research.
https://arxiv.org/abs/2611.18982
Recent humanoid loco-manipulation in articulated environments has largely focused on geometry-dominant interactions, where success is primarily determined by geometric alignment and motion execution. In contrast, forceful multi-finger manipulation requires the robot to adapt to real-world uncertainties in contact and interaction dynamics. We present Tactile-Driven Motor Adaptation (TMA) and an integrated whole-body system for zero-shot sim-to-real forceful humanoid manipulation, and study round-doorknob opening as a challenging benchmark requiring stable multi-finger frictional grasping, sufficient torque generation without slip, force-regulated pushing, and whole-body stability. TMA structures policy learning around interactions observable through tactile feedback, uses cone geometry as an inductive bias for multi-finger contact representation, and adapts motor behavior online from tactile history. An upper-body manipulation policy is trained alongside a pretrained general locomotion controller to coordinate dexterous interaction and whole-body stabilization. Trained entirely in simulation, TMA transfers zero-shot to a Unitree G1 humanoid with BrainCo Revo2 multi-fingered hands and substantially outperforms standard Rapid Motor Adaptation (RMA) and reactive tactile policy baselines across four commercial round doorknobs in the real world.
https://arxiv.org/abs/2611.18976
Single-point linearization provides a computationally efficient basis for optimization-based trajectory planning of nonlinear robot manipulators. However, planning performance depends on the selected linearization point. This paper presents an offline performance-driven approach that treats the location of a single linearization as an optimization variable. Candidate operating points are sampled from a common cubic seed trajectory, and each corresponding affine model is used to solve an identical constrained finite-horizon quadratic program (QP). The resulting control sequences are executed on the original nonlinear dynamics, and the operating point minimizing the nonlinear trajectory objective is selected through grid search and bounded refinement. Evaluation on four point-to-point motions of a three-degree-of-freedom UR5 manipulator yields optimal normalized operating-point locations between 0.325 and 0.935, demonstrating trajectory-dependent selection. Compared with the best-performing conventional initial, midpoint, or terminal linearization, the proposed approach reduces the nonlinear trajectory objective by 17-18%, 21-22%, 37-38%, and 7-8% across the four tasks, respectively. Additional nonlinear execution with identical PID feedback correction confirms that the performance advantage persists for a representative task. These results demonstrate that systematic operating-point selection can substantially improve single-linearization trajectory planning while preserving a fixed affine planning model.
https://arxiv.org/abs/2611.18935
Supervisory control of multiple autonomous unmanned aerial vehicles (UAVs) imposes high visual and cognitive demands on human operators, particularly when communicating mission objectives and system constraints. Voice command provides a natural interaction modality that can reduce operator workload; however, its reliability is affected by environmental noise, speech variability, and recognition errors. This paper presents a dependable voice command framework for multi-UAV swarm supervision using Small Language Models (SLMs). The proposed architecture integrates an Automatic Speech Recognition (ASR) module with an SLM-based semantic processing layer to transform spoken operator commands into structured task definitions for downstream multi-UAV planning and execution. To evaluate robustness, an end-to-end assessment pipeline is developed using a Probabilistic Context-Free Grammar (PCFG) to generate synthetic supervisory commands, which are converted into audio samples with varying operator accents and environmental signal-to-noise ratios (SNR). The resulting speech signals are processed by the ASR module, and the SLM performs contextual interpretation and phonetic correction of transcriptions when required. The evaluation isolates the resilience of the voice command pipeline under acoustic degradation and speech variation, demonstrating reliable task generation for multi-UAV supervision in challenging operational conditions.
https://arxiv.org/abs/2611.18924
Robots in homes, warehouses and farms must pick up objects they have never seen, usually without a 3D model or a category label. A grasping policy that works directly on the point cloud from a depth sensor needs only the geometry the robot observes, so it applies to any new object. Offline grasp generators such as Contact-GraspNet work this way, but they rank grasps by learned plausibility rather than by whether the grasp actually lifts the object. Reinforcement learning (RL) can optimize for that directly and make a point-cloud grasping policy much better on average, yet it leaves specific grasps persistently unsolved. We present a human-in-the-loop failure loop that targets those grasps: situations an RL policy keeps failing are mined automatically, sent to a virtual-reality application where a person picks the object up with their own hands, and returned to training as two grasp points. The person contributes only where to grasp; the robot chooses its own approach. In simulation, RL raises success on unseen objects from 55% with Contact-GraspNet to 83%. Adding 58 human demonstrations nearly doubles success on the hard cases RL kept failing, from 24% to 45%, and recovers performance that RL alone loses on similar cases that were never demonstrated, without reducing success on unseen objects.
https://arxiv.org/abs/2611.18919
In multi-robot navigation, rigid global schedules are sensitive to execution deviations, while local methods lack long-horizon coordination. We propose a passage-focused framework combining soft global coordination with flexible local execution. A passage-induced graph of convex sets supports priority-ordered planning with two levels of soft coordination. Passage-aware route selection accounts for passage usage and traversal directions, while route-restricted continuous space-time planning penalizes temporal conflicts. The resulting references guide a model predictive path integral controller that avoids collisions online. Adaptive temporal and geometric tracking accommodates execution deviations, while selective replanning maintains coordination without rigid trajectory reservations. Across 1,200 instances in 4 different environments with 5-30 robots, the framework achieves a near-perfect success rate and outperforms evaluated baselines in makespan and flowtime. Hardware experiments with 8 robots demonstrate successful completion of all trials without collisions. These results highlight the effectiveness of passage-focused coordination in balancing long-horizon cooperation with flexible execution.
https://arxiv.org/abs/2611.18877
This report presents the design and implementation of Auriga Robotics' 1:10 scale autonomous vehicle, developed at Shahid Beheshti University's Robotics and Intelligent Automation Laboratory. The platform integrates a custom mechanical chassis, a distributed embedded system based on ESP32 microcontrollers, and a Jetson Orin NX module for high-level perception and control. The embedded layer manages sensor interfacing, real-time data acquisition, and actuator control, while the Jetson handles environment perception through deep-learning--based lane, sign, and traffic light detection, as well as decision-making and trajectory control. System communication is achieved via structured UART links, ensuring synchronized operation between perception and control subsystems. The vehicle's software stack incorporates ROS, modular firmware design, and multiple control algorithms---Stanley, PID, and Pure Pursuit---to achieve stable autonomous navigation in structured driving scenarios. The overall system demonstrates robust performance and reliability in urban-like environments, serving as a modular research platform for future autonomous driving studies.
https://arxiv.org/abs/2611.18855
Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, whereas open-weight models remain substantially less capable. We show that an open-weight 27B reasoning model can be trained to use real robots natively through reinforcement learning, entirely in simulation and without demonstrations. Like a computer-use agent (CUA), the model observes the environment, reasons in a chain of thought, and generates the next end-effector pose, without any harness. We build a Post-training Engine for Agentic Robotics (PEAR) and use it to train the model on simulated robot tasks at scale with robot-use reinforcement learning (RURL), mirroring how frontier models acquire computer use. We find that the skills acquired in simulation generalize well beyond the training tasks: they transfer to an unseen robot, to the real world, and to novel instructions. After training on LIBERO and RoboDojo in simulation, the model succeeds in 60% of our trials on a real dual-arm robot, whereas the base model succeeds in none. On LIBERO, training raises the success rate from 1.6% to 74.4%, approaching GPT-6 Astra and GPT-6.1 Sol at maximum reasoning effort. Compared with $\pi_{0.5}$, a vision-language-action model fine-tuned on demonstrations, our model is substantially more robust to changes in the task itself. On LIBERO-Pro, $\pi_{0.5}$ succeeds in only 0.75% of episodes when assigned a new task in a familiar scene whereas our model succeeds in 57.4%. Finally, the model retains its general capabilities, with no measurable degradation on nine reasoning, coding and vision benchmarks. These results highlight robot-use reinforcement learning as a promising component of foundation-model post-training.
https://arxiv.org/abs/2611.18562