arXane › Computer Science › Computer Science
Wednesday, 4 November 2026: 56 new papers, 16 cross-lists and 53 replacements in Robotics (cs.RO), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
Training robot policies for multi-task pick and place requires demonstrations on many objects, which handheld Universal Manipulation Interfaces (UMIs) can collect quickly and cheaply. However, existing UMIs depend on external base stations, use rigid fingers that give no signal about contact forces, or use parallel-jaw fingers that limit grip strength. We present a battery-powered handheld interface, built on YUBI, whose soft, angled fingers wrap around objects, deform visibly under load as a visual proxy for force, and match the grippers of the robot. With it, we collect a 99.7-hour dataset over 53 objects, train $\pi_{0.5}$ policies on 49 of them, and hold out the other 4 as unseen objects. We find that a top camera raises success by 13 points even when only about half of the data includes it, and that mid-training on our multi-task data raises success after fine-tuning on unseen objects from 35% to 57%. Finger design, dataset, and data processing code: https://lute-corp.github.io/soft-yubi-site/
AIRoA-0 (A-0) is a bimanual manipulation system learned from 16,151 hours of handheld demonstrations, with no robot data collected at any stage. The demonstrations are recorded with YUBI, our open-source handheld gripper, which lets people record manipulation data anywhere with no robot present. From a single instruction, A-0 sorts more than a dozen small parts into their numbered cells and changes the mop pads and brush of a robot vacuum; among other tasks, it unzips a pencil case and folds a towel. It performs these tasks using only a camera on each wrist, with no head or scene camera, at a site where none of its training data was recorded. Across the ten tasks of our evaluation, it averages a success rate of 78%, against 27% for the strongest of four other vision-language-action models post-trained on the same task demonstrations. We collect no teleoperation data and use no reinforcement learning or on-robot corrections, and the robot appears only at test time. The system learns which regions of each wrist view matter for the task, predicts the stage the task has reached, and decodes actions as a continuous stream. A-0 is embodiment-agnostic: it runs on robots that mount the YUBI gripper, such as a bimanual Franka, TX-G2, OpenArm and UR. We are releasing the dataset, to our knowledge the largest open dataset of handheld-gripper demonstrations with task and subtask instructions, together with the pre-trained weights and the post-training recipe. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on it in under four hours on a single node of eight H200 GPUs.
In robotics, shape control, or shape servoing, refers to the automatic manipulation of a deformable object toward a desired shape. This article is the second of a two-part tutorial on data-driven, Jacobian-based shape control, in which the deformation Jacobian, a local model of how robot motion changes the measured shape, is estimated from measurements. Part I built the shape-servoing loop and derived a local stability condition. This paper starts by using the singular value decomposition of the deformation Jacobian to identify shape changes that can be produced by small robot motions, those that require large robot motions, and those that are locally unavailable. It then analyses how the choice of shape features determines how the controller regulates the object's shape and, therefore, how much the object deforms on its way to the target. It then describes three ways in which the shape control loop can fail: loss of controllability, loss of observability, and occurrence of mechanical instabilities. It closes with shape-control extensions to time-varying targets, secondary tasks, and three-dimensional objects.
Simulation benchmarks are the standard way to compare robot policies, but each benchmark brings its own evaluator, observation layout, and action convention, and evaluation is slow: 500 RoboTwin Easy episodes with one simulator and one model on one GPU take 359.7 minutes. Profiling the official StarVLA evaluator shows that simulation occupies CPU cores while the GPU averages 14.3% utilization. RoboScope Kit wraps each model once in a Python class called a Policy, and each benchmark once in an adapter around the benchmark's own evaluator, so the benchmark's rules and scoring stay unchanged. Scheduling runs simulator workers and Policy replicas as separate pools, sizes both from measured probes, and shards work deterministically across GPU instances; runtime optimization renders only the observations an action-chunk Policy reads. Adapters cover six benchmark families. On LIBERO-Long with a StarVLA checkpoint on one 48 GiB RTX 4090, the concurrency search selects twelve simulator workers sharing three Policy replicas, which evaluate 500 episodes 4.45$\times$ faster than the official StarVLA evaluation with equivalent success rates, 2.78$\times$ faster than RLinf, and 1.52$\times$ faster than vla-eval at its tuned configuration. With CUDA MPS, which lets the replicas run their kernels concurrently, the search selects sixteen workers sharing four replicas, 6.16$\times$ faster than StarVLA, 3.85$\times$ faster than RLinf, and 2.10$\times$ faster than vla-eval. On RoboTwin Easy, four GPUs with chunk-boundary observation complete the 500 episodes in 14.4 minutes, 25.04$\times$ faster than the single-GPU baseline, with identical success outcomes and terminal steps.
One big challenge in physical AI is interacting with systems whose states are defined by implicit equilibrium. Learning in these systems is difficult because their responses can be multistable, path-dependent, and sensitive over long horizons. Adjoint learning provides an efficient way to optimize trajectories without unrolling iterative equilibrium solvers, but its gradient relies on the frozen-tangent approximation, which neglects higher-order sensitivity terms and can become inaccurate when the local equilibrium varies rapidly. In this work, we introduce Self-Consistent Neural Control (SCNC), optimizing trajectories along which sensitivity variations are explicitly controlled. We derive a mathematical bound on the resulting gradient error and develop a practical finite-difference approximation. We validate the framework on deformable objects, which are representative of implicit equilibrium systems, ranging from simple quadratic energy models such as elastic rods to complex systems including thin-walled tubes, measuring tapes, and Slinky-like structures. Compared with the adjoint learning and the gradient-free iCEM baselines, SCNC achieves faster convergence and more stable optimization by reducing switching to undesirable equilibrium branches, doubling the stable optimization rate over adjoint learning 83.3% vs. 41.7% and reducing the average loss by more than 1.5 orders of magnitude on thin-walled tubes, where sensitivity variations are pronounced.
Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation. Existing semi-dense matchers predict confidence on fixed grids, limiting correspondences to predefined locations and requiring costly high-resolution grids for precise localization. We present CoReMatch (Coordinate Refinement Match), a recurrent framework that refines correspondences directly in continuous coordinate space rather than predicting discrete confidence maps. CoReMatch progressively improves correspondence estimates by propagating information across iterations. At the coarse stage, a Deep Aggregated Transformer captures global context and iteratively updates correspondence coordinates, while a lightweight regression head further sharpens their localization. Experiments on indoor and outdoor benchmarks show that CoReMatch strikes a strong balance between accuracy and efficiency, outperforming Efficient LoFTR in accuracy while running more than 10x faster on embedded edge hardware. These results demonstrate that recurrent coordinate refinement offers an efficient and scalable approach to real-time feature matching for robotic perception.
Computing distances between sets is important in many robotic applications, such as motion planning and control. In many applications, derivatives of the distance are needed as well. It is well known that the Euclidean distance is not always differentiable, which create issues to algorithms that need a derivative. In this paper, we introduce NESDF, the Normal Euclidean Signed Distance Function between two general (with mild regularity assumptions but possibly non-convex) sets. This metric is still not differentiable, but it allows us to introduce a generalization, $h$-NESDF, which has a smoothing parameter $h$ such that the metric is infinitely differentiable for all $h>0$ and that reduces to the NESDF when $h$ goes to $0$. The metric is amenable to GPU parallelization, and thus can be computed efficiently. We show extensive simulation results to evaluate its viability in motion planning.
Robot swarms harness simple, local interactions among many individually limited robots to produce complex, coordinated collective behavior, making them valuable across domains from agriculture to disaster response. We envision the next frontier for such swarms as open swarms, in which robots join or leave the swarm dynamically at runtime. The ability to dynamically adjust swarm size has been shown to be beneficial, for instance by reducing inconsistencies and network partitioning, especially under sparse connectivity or in complex environments, ultimately improving task performance. For practical deployment, however, open swarms requires governance, particularly protection against Byzantine behavior (i.e., faulty or malicious robots), since allowing robots to join freely also makes the swarm easier to infiltrate. Blockchain technology has recently been incorporated into robot swarms, offering secure, decentralized coordination and improved resilience, though largely in closed settings with a fixed, predetermined membership. In this work, we extend these benefits to open swarms by introducing robot swarms governed by a blockchain-based decentralized autonomous organization (DAO), in which the swarm regulates itself using autonomous rules encoded in smart contracts. We outline several DAO-based governance mechanisms for robot swarms, depending on the needs of the application, and present a proof-of-concept implementation of a simple DAO that regulates swarm membership and prevents Byzantine infiltration. Our simulation results and real-robot validations show that DAO-governed access control and robot removal can maintain proper swarm functioning while keeping the number of Byzantine robots within acceptable limits.
World models are increasingly used to support prediction and planning in embodied agents, but the knowledge is usually established before deployment and then carried into later encounters. Continual operation faces a different problem. A familiar environment may change, and the agent must use previous experience without allowing old expectations to override current physical evidence. This study asks what repeated physical experience must contribute for a spatial world model to become progressively more useful rather than simply more persistent. A physics-grounded dynamic maze separates recurring spatial change from the continuous consequences of action. Cross-episode Spatial Change Memory learns relations among environmental transformations, while state-action-outcome experience refines predictions of motion. Structured experience progressively reduces the need for future route correction and transfers to spatial transitions not encountered during learning. The advantage disappears when past changes contain no information about future ones. Continuous navigation further shows that predictive memory changes behavior when a previous decision becomes invalid but leaves behavior unchanged when the decision remains correct. Physical tests expose a complementary limit: correct topology does not guarantee correct action prediction, and accumulated physical experience reduces this mismatch within the modeled dynamics. The results characterize continual world knowledge as experience that improves future prediction and action beyond stored episodes while remaining revisable by the physical outcomes it is intended to predict.
Causal inference has emerged as a powerful paradigm enabling robots to make safe, efficient decisions by reasoning about the ``why'' behind events. However, its real-world application is hindered by the difficulty of collecting causal data, especially in human-populated environments where training takes time, while users expect immediate operation. To this end, we tackle the challenge of transferring simulation-learnt causal relations to the real world with minimal effort. While retaining the invariant high-level causal structure, we empirically demonstrate the system adapts efficiently to real-world situations by updating only the causal model parameters with a limited set of new observations. Our results show that the parameter update enables rapid sim-to-real transfer. The framework runs efficiently onboard of a mobile robot and significantly outperforms a non-causal baselines navigating successfully and safely in complex human-shared scenarios.
A mobile manipulator asked to "put the toys away in the toy box" must decide which objects are toys and which container the user means, then find base poses, grasps, and placements it can execute. Because a scene representation is built before the instruction is known, it may lack the attributes, affordances, or concepts needed to resolve the task. We present FEIJOA, a language-model agent that grounds the instruction at test time. It queries a grounding tool over a posed RGB-D scan, inspects the returned candidates, and refines its queries until they resolve the instruction. An embodiment-aware harness checks each skill's preconditions, samples base poses from which the target is reachable, and verifies the skill's effect from observations before and after execution. On 103 open-ended grounding queries, FEIJOA resolves 94.2% exactly, compared with 68.0% for the best prebuilt representation. Over 50 real-world trials on Spot, it completes 35 tasks; 17 of these successes follow recovery from a failed tool call or verification check. Of the 15 failed trials, 13 were caused by the robot's physical skills, and only 2 by grounding or the agent's reasoning. Project website: https://williamshen-nz.github.io/feijoa/.
As robot learning moves beyond the tabletop, many tasks require mobility, adjustable reach, active perception, and bimanual dexterity. Commercial platforms combining these capabilities are costly, while affordable open-source alternatives cover only a subset and require software integration. We present MABEL, an open-source anthropomorphic mobile bimanual robot with 56 degrees of freedom (DOF) and a US$8.1k parts cost. It combines two 7-DOF arms with 17-DOF hands, a pitching torso, a lift, a 3-DOF neck, and a holonomic base. Back-drivable arms and torso support compliant interaction, with fingertip reach from floor level to 2.23 m. The head and torso roughly triple modeled camera coverage relative to a torso-fixed camera. Apple Vision Pro head and hand tracking enables whole-body teleoperation without handheld controllers, with 137 ms mean glass-to-glass stereo video latency over the robot's Wi-Fi hotspot. We demonstrate an end-to-end imitation learning pipeline, from teleoperated data collection to policy deployment, using a shared command interface and whole-body controller.
Object rearrangement planning in cluttered environments is often non-monotone, requiring objects to be temporarily relocated before reaching their final destinations. Although search-based planners can solve such tasks, they incur substantial computational cost and require expensive replanning when the environment changes. We propose the Visual Adaptive Rearrangement Planner (VARP), which learns non-monotone rearrangement directly from visual state representations generated from expert demonstrations. VARP predicts pick-and-place actions from the current and goal visual state representations, and incorporates an Action Refinement Strategy (ARS) to improve action feasibility and a Progress Enforcement Strategy (PES) to mitigate progress stagnation. By continuously updating actions from the latest visual state representations, VARP adapts online to disturbances without replanning from scratch or performing online combinatorial search. In challenging rearrangement benchmarks, VARP achieves a 98.3\% success rate with only 0.4 s planning time per task, 97.5\% success under execution-time disturbances, and 94.5\% under continuous severe disturbances, while generalizing effectively to unseen object counts. These results demonstrate that VARP provides a scalable and robust solution for non-monotone object rearrangement.
Hamilton-Jacobi (HJ) reachability provides certified backward reachable tubes (BRTs) for safety-critical robotic systems, but the level-set computation scales exponentially in the state dimension and has historically been performed offline. As autonomy stacks (ADAS/AV, humanoid robotics, and vision-language-action models) increasingly rely on black-box, probabilistic policies, a deterministic safety layer with formal guarantees is an essential complement. We present a CUDA implementation of the canonical WENO5 + TVD-RK3 + Lax-Friedrichs level-set Hamilton-Jacobi-Isaacs solver for 2D, 3D, and 4D dynamics that is fast enough to run inside a robot's control loop. In 32-bit floating point (FP32) on a single workstation GPU (NVIDIA RTX 4000 Ada), it computes the 3D Air3D BRT at 112 Hz, a 4D pursuit-evasion BRT at 61 Hz, and a 2D wind-affected drifter BRT at 74-147 Hz, 5.9-17.5x faster than the JAX reference hj_reachability at matched precision and 1.7-16x faster than a torch.compile reimplementation of the same scheme. In 64-bit floating point (FP64) it agrees with hj_reachability on eight benchmark cases, reproduces Mitchell's Air3D BRT to within 0.04% of the reference cell count, and runs 2.0-4.6x faster. On an embedded NVIDIA Jetson AGX Thor it computes Air3D at 66 Hz (N=41) and the 2D drifter at 54 Hz, 3.8-8.9x faster than hj_reachability on the same device. As a multi-agent application, an in-kernel label-propagation extension recovers the K-agent capture-basin Voronoi tessellation from a single combined HJ solve, independent of fleet size; it runs at 4.0 ms per tick in a closed-loop wildfire-response simulation of six quadcopters under time-varying, non-uniform wind.
This paper presents an innovative guidance and control method for a space manipulator that actively maneuvers its base to hold a tumbling object stationary relative to the base during proximity operations. This simplifies motion planning, reduces collision risk, and enables impact-free capture using single- or multi-arm configurations, with or without predefined grasping interfaces. The proposed approach involves two phases. In the pre-grasping phase, a synchronization control aligns the target's center of mass (CoM) with the system's instantaneous center of rotation (ICR), virtually rigidizing the target-servicer system to keep the object stationary for reliable grasping. In the post grasping phase, a control strategy based on Hamiltonian dynamics and optimal control stabilizes the combined system by minimizing time, fuel, or energy, while respecting base torque limits and multiple grasping constraints. For structured targets, applied forces and torques stay within their bounds; for unstructured ones, friction constraints prevent slipping. A case study demonstrates the method's effectiveness in enabling both the subsequent grasping and detumbling phases.
Humanoid locomotion requires deciding where to step and how to distribute contact forces. However, a disturbance can invalidate the nominal plan, requiring coordinated revision under constraints that switch with every footfall. To solve this online, the proposed approach employs the single-rigid-body model, which retains attitude dynamics and the full contact wrench. An iterative linear-quadratic-regulator MPC (iLQR-MPC) then jointly optimizes contact forces and footstep locations in a single receding-horizon problem, without a separate step planner. Specifically, contact and motion constraints are incorporated into the backward pass through augmented-Lagrangian and relaxed-barrier penalties. A whole-body controller subsequently maps the plan to joint torques at 500 Hz while preserving contact feasibility. The model-based formulation makes disturbance responses interpretable through explicit costs and constraints, and requires no platform-specific policy training. In MuJoCo simulations, the iLQR-MPC replans at 100 Hz (mean solve time 8.9 ms); the Unitree G1 sustains steady-state walking and recovers from impulsive 245 N forward and 175 N lateral pushes.
Disturbances can invalidate the conditions required by a robot's next action even when much of its task program remains useful. A recovery system must therefore choose a response suited to the current state. We present DiMuRe (diagnosis-guided multilevel recovery), a framework for robot-use agents that uses phase-specific evidence and method preconditions to select program reuse or predefined recovery skills, including bounded vision-language-action (VLA) grasping. After the original program exits, a multimodal large language model (MLLM) can generate corrective code from images and execution feedback. Local verification checks the outcome of each recovery attempt. We also introduce LIBERO-Disturb, a benchmark for robustness and recovery under mid-execution disturbances, supporting program-based agents and VLA policies. On 801 scheduled disturbed Encore development cases, Local DiMuRe (program reuse and recovery skills) achieves 77.65% complete-task success, compared with 58.68% for the original program under the same physical-step allowance. Full DiMuRe achieves 81.90% with terminal replanning, an additional step allowance, and early handoff. Local DiMuRe also uses fewer physical steps per scheduled episode than the original program.
Operating rooms (ORs) increasingly contain ambient sensing infrastructure to enable AI-based optimization of workflows and utilization. We pursue an alternative path: using ambient AI to guide robot action and optimize utilization. Deploying humanoids in the OR without ambient AI is severely limited by cumbersome de novo orientation and planning due to partial onboard observations. We posit that this can be achieved by coupling an ambient AI-based agentic orchestrator with the humanoid robotic actor, providing shared perception and execution feedback for humanoid autonomy in the OR. ActOR fuses a wall-mounted ambient camera and the robot's head-mounted camera into a shared object-level digital twin (DT). A large language model agent plans over the DT using pre-programmed locomotion and manipulation skills without task-specific training. During execution, DT updates and execution outcomes inform retries, alternative approaches, or replanning. We evaluated ActOR in simulated and physical environments. Across three tasks in two simulated ORs reconstructed from real rooms, ambient perception reduced exploration from 1.05 to 0.12 Explore calls per trial when targets were initially outside the robot's view. Closed-loop feedback increased success from 46.7% to 83.3% under nominal execution and from 8.3% to 51.7% under injected navigation, object-relocation, and grasp perturbations. In a physical mock OR with a humanoid, ActOR completed 14 of 20 single-object disposal trials and demonstrated replanning after scene changes. Ambient AI-based observations provide scene state that improves robot action planning, increasing success and reducing exploration compared with robot-only observations. Feeding skill outcomes and DT updates back to the planner improves multi-step task success. Our results show the feasibility of humanoid task autonomy for multi-step disposal tasks in a mock OR.
This paper presents humanoid manipulator hardware designed specifically for human-level performance throughout its broad domain of tasks, from heavy payloads to highly dynamic motions. Unlike conventional designs targeting uniform workspace capability, the proposed approach derives force, speed, and endurance targets from published measurements of task-relevant human upper-limb performance. These targets guide the actuator, mechanism, and thermal design toward torque transparency and sustained operation. The platform integrates force-oriented upper-arm components, speed-oriented forearm components, and a posture-dependent elbow mechanism that shifts its torque-speed behavior. These components are driven by planetary actuators and compact actuator-embedded electronics. Experimental results validate broad task capability, demonstrating a peak payload of 20 kg (2.25x its own mass), an endpoint speed of 20.6 m/s, and continued operation under repeated hammering impacts. Thermal analysis further confirms that the robot's sustained operation capability exceeds the published human load--duration boundary across nearly the entire load spectrum. These findings show that hardware targets derived from human-task measurements narrow the human-to-humanoid capability gap. A supplementary video is available at https://youtu.be/xVUWFICD5G0
Adapting a generalist vision-language-action (VLA) policy to a target task with limited demonstrations can improve nominal task success while reducing robustness to variations in appearance, objects, and instructions. We introduce reasoning-aligned fine-tuning (RAFT), a two-stage post-training procedure: RAFT first trains low-rank adapters on task-relevant reasoning annotations, then freezes them while fine-tuning the policy on action demonstrations. On a physical DROID robot, RAFT achieves $75.0\%$ out-of-distribution success, compared with $27.9\%$ for plain fine-tuning; on a multi-stage bimanual YAM task, it reaches $70.0\%$ mean success, compared with $36.0\%$ for the strongest baseline. RAFT also improves success under visual, object, and instruction shifts in simulated pick-and-place and open-drawer tasks. Compared with plain fine-tuning, RAFT policies place more attention on annotated task regions and yield higher linear-probe accuracy for object identity in later layers. A broader reasoning-data mixture further improves downstream success across demonstration budgets.
Humanoid robots operating in cluttered environments must react to unexpected contacts before the first impact peak, which arrives within tens of milliseconds. Learned whole-body policies running at 50 Hz introduce a policy-cycle delay and may suppress a protective withdrawal as a tracking error. To address these challenges, we propose ARC (Ascending Reflex Control), a bottom-up framework that integrates instantaneous tactile reflexes with learned whole-body control. ARC consists of two components: an instantaneous reflex pathway and bottom-up reflex integration. The reflex pathway detects hazardous contacts from full-body tactile sensing, solves a whole-body withdrawal pose, and delivers it directly to the motors within 10 ms. Bottom-up reflex integration combines reflex-in-the-loop policy learning, reflex-transparent policy alignment, and reflex-informed policy adaptation to sustain the withdrawal, maintain balance, and complete longer-horizon recovery. We deploy ARC on a Unitree G1 and evaluate three categories of hazardous contact. Compared with an otherwise identical reflex delayed by 20 ms, ARC reduces the first force peak by 34.1% and reduces the contact impulse from 0.2632 N s to 0.1225 N s (a 2.15x ratio). We further demonstrate protected motion tracking, teleoperation, and vision-free obstacle traversal guided by foot tactile sensing. Project page: https://minusmodulo.github.io/reflexarc-website/
Diffusion-based policies have achieved strong performance on single-task robotic manipulation. However, a single model trained jointly on multiple tasks consistently underperforms the per-task specialists trained on the same demonstrations. We focus on two challenges. First, the convolutional encoders commonly used in diffusion-based policies produce visual conditions that are not discriminative enough. Second, gradients from incompatible action modes update the shared denoiser's dense parameters along the same directions, causing destructive interference during joint training. To address both, we propose SR-DP (Spectrally Routed Diffusion Policy). A frozen VGGT encoder with a spatial-compression adapter produces compact multi-scale semantic-geometric tokens, a task-discriminative visual condition for tasks that share a workspace. We first train the denoiser as a standard diffusion policy, then decompose selected linear layers by SVD into a frozen basis of orthogonal rank-one experts, adapted through spectral routing and Householder input rotations. On six RoboTwin tasks, SR-DP averages a 68.4% success rate, surpassing multi-task VO-DP by 21.8 points and the strongest per-task baseline by 3.8 points. On four real-world bimanual tasks, Stage 2 reaches a 43.0% average success rate and improves over Stage 1 by 19.0 points.
Visual Foundation Models (VFMs) provide semantic cues such as depth and segmentation useful for robotic manipulation, but directly deploying them in closed-loop control is impractical due to high computational cost, temporal inconsistency, and distribution shift between static internet images and egocentric robot observations. We propose All-For-One (AFO), a two-stage distillation framework that leverages VFMs strictly as privileged information during training, using downstream robotic data. Following the privileged learning paradigm, AFO decouples semantic representation learning from inference-time policy execution. In the All stage, a teacher policy fuses RGB observations with outputs from multiple VFMs to learn a semantically enriched representation. In the For-One stage, this knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway for transferring foundation-model knowledge to robotic control.
Predicting how the world evolves in response to robot actions is central to policy learning, evaluation, and planning. However, many action-conditioned world models predict future observations in 2D image or video space without explicitly modeling the underlying 3D scene, making spatial consistency across viewpoints and over long-horizon interactions challenging. We introduce 3D World Simulator, an action-conditioned multimodal world modeling framework that jointly predicts appearance, geometry, and tactile observations from a unified 3D representation. Our approach combines a hybrid particle-voxel autoencoder that compresses point clouds into compact 3D voxel latents with an action-conditioned latent dynamics model that predicts their evolution. The shared 3D representation supports geometrically consistent rendering from arbitrary viewpoints and flexible integration of spatially aligned tactile signals. Our experiments demonstrate interactive, long-horizon, multimodal prediction at 50 Hz. We then show how our model enables scalable data generation for policy training and evaluation using tactile and multi-view visual observations, including wrist-mounted and novel camera views. Furthermore, we scale our method to large datasets containing diverse objects and demonstrate model-based planning with unseen objects and robot configurations. Together, these results highlight the potential of hybrid particle-voxel dynamics as a foundation for multimodal 3D world simulation.
Learning robust manipulation policies for diverse everyday objects remains challenging because objects with different materials exhibit distinct deformation and contact dynamics. While diffusion policies provide a powerful framework for modeling multimodal manipulation behaviors, they typically lack explicit physical reasoning and may produce averaged actions when facing heterogeneous objects. We present a physics-aware diffusion policy that augments visual imitation learning with object physical understanding. Our framework recovers material properties from visual demonstrations by coupling 3D Gaussian Splatting with differentiable Material Point Method simulation, where video guidance and particle-level constraints enable accurate physical parameter estimation. The estimated physics conditions are further integrated into a material-aware Mixture-of-Experts diffusion policy, allowing adaptive behavior generation across different physical regimes. For practical deployment, we introduce a physics memory bank that provides efficient physical retrieval without requiring online simulation optimization. Experiments on a wide range of simulated and real-world objects demonstrate improved manipulation success and generalization over existing diffusion-based approaches. These results show that incorporating physical knowledge is critical for scalable robot manipulation in diverse environments.
Coordinating autonomous underwater vehicles requires translating operator intent into feasible assignments while preserving autonomous execution when communication is limited. We present a hierarchical framework that couples Large Language Model (LLM) interpretation of natural-language mission instructions with Mixed-Integer Linear Programming (MILP) and distributed Behaviour Tree (BT) execution. The LLM extracts assignment and ordering constraints, which the MILP optimizer combines with vehicle capabilities and temporal requirements. A BT-LLM Bridge distributes the resulting allocations to onboard BT Mission Managers. Per-vehicle Robotic Agents assess local faults and request selective replanning, allowing unaffected vehicles to continue their assigned tasks. Evaluation in a ROS-based AUV simulator compares Qwen-3-8B and Llama-3.1-8B on constraint extraction and tests recovery from sensor degradation and critical vehicle faults. Qwen-3-8B provides more accurate constraint extraction, and all tasks are completed in the tested failure scenarios. These simulation results support the feasibility of combining language-based mission specification with structured allocation and distributed execution.
Vision-Language-Action (VLA) models have achieved promising performance for generalized robotic manipulation, yet their reliance on expensive real-robot data remains a fundamental bottleneck. A scalable alternative is to transfer knowledge from off-the-shelf human-centric videos. However, existing methods extract latent action representations that are entangled with scene-specific noise, diluting the transferred knowledge. Motivated by this limitation, we propose Action-Intent Transfer (AIT), a two-stage method that transfers knowledge through a clean action representation shared across humans and robots. In the first stage, AIT extracts explicit action intents and disentangles the implicit action intent from manipulation videos. In the second stage, AIT aligns the human and robot domains within this shared intent space and decodes the intent into executable robot actions. Extensive experiments in both simulation and real-world environments demonstrate that AIT transfers human knowledge more effectively and consistently outperforms prior baselines.
World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction. However, iterative video denoising is costly, and inaccurate visual predictions can compromise action prediction. Our key idea is to make this predictive knowledge available through visual representations computed from the current observation, enabling action prediction without generating future videos. We introduce DreamFree, a WAM that repurposes a pretrained video diffusion model as a predictive visual encoder through representation distillation. The visual encoder learns to predict a frozen video diffusion model's representation using only the current observation. An action module is then trained to predict actions by extracting action-relevant information from the visual encoder. Across real-world and simulated tasks, DreamFree achieves higher success rates than state-of-the-art VLAs and WAMs, while performing real-time closed-loop control at 11Hz with a 14B video diffusion backbone. Experiments show that DreamFree can translate stronger video priors and additional video data into better robot control and enable learning new robot tasks from video demonstrations, including videos from a different embodiment, without action annotation for the new tasks.
Robotics and AI systems are increasingly deploying large vision-language models (LVLMs) to follow high-level instructions, from routine household chores to more complex organizational tasks. Yet, broad directives like "clean the room" or "organize the desk" frequently omit crucial details about user preferences and specific arrangement of objects that influence the desired outcome. Without any further guidance, such models tend to overestimate their grasp of ambiguous instructions and frequently assume they have sufficient understanding despite missing important details. In this paper, we propose CLARA (Conversational cLArification for Robotic Arrangement), a cognitively-driven clarification framework that proactively elicits key information from users, in a similar fashion as humans' clarification seeking behavior. Through targeted questioning, CLARA refines ambiguous requests into structured, detailed instructions describing precisely how objects should be organized or rearranged, according to the user's preferences. These clarifications then guide a diffusion-based image generation pipeline, producing realistic visual renderings of the final, desired scene. This final rendering also serves as a visual confirmation of the system's understanding from the user. Experimental results and user studies demonstrate that CLARA leads to more accurate and consistent outcomes compared to another State-of-the-Art LVLM system, highlighting the importance of interactive clarification for bridging the gap between vague directives and fully grounded task specifications.
Multicopters are a type of aerial robot seeing extensive real-world applications but with range and endurance as critical bottlenecks. Optimization of its energy efficiency through energy-aware flight planning (e.g. cruise speed-scheduling) has hence been an important topic. The mass of the multicopter is an important factor to consider, as it has a significant impact on efficiency, and many common applications are subject to frequent mass variation due to payload change. This work derives closed-form scaling relationships between the energy-optimal steady horizontal flight behavior of a multicopter and its vehicle mass, and validates them experimentally on two multirotor platforms. Specifically, for mass-only variation, i.e., when payload changes the vehicle mass while the airframe geometry, aerodynamic characteristics, and rotor configuration remain unchanged, we show through a combination of numerical simulation, theoretical derivation, and experimental validation that (1) the energy-optimal velocity is proportional to the square root of vehicle mass; (2) the energy-optimal pitch angle is constant with respect to mass; and (3) the optimal energy per meter is proportional to mass. The analysis shows that these three relationships arise from a common mass-similarity property of the steady-state flight and rotor-aerodynamic equations. Furthermore, the obtained scaling relationships enable simple yet effective cruise-speed planning to optimize energy efficiency and extend the range and endurance of the multicopter.
Humanoid loco-manipulation requires coordinated body motion and hand interaction over time, and a plausible-looking command sequence can still drop a held object or leave an interaction incomplete. We present action-conditioned latent foresight, a latent world-action model (WAM) that evaluates proposed command sequences before execution. An action generator proposes joint motion-hand command sequences from vision, language, and the robot state. An action-conditioned endpoint predictor estimates the visual features each sequence prefix reaches and measures progress toward a demonstration-derived subgoal, while a joint temporal prior scores temporal consistency given the robot state and preceding commands. The robot executes the first commands of the best-scoring sequence and replans from the next observation. During training, action consistency regularization reconstructs the first demonstrated command from observed and predicted feature changes, encouraging the predictor to retain action-relevant information. On ten tasks in the humanoid loco-manipulation simulation benchmark SIMPLE, our method achieves 89.7% average success, compared with 73.7% for Psi-Zero and 82.0% for DiT4DiT. On seven real-robot tasks, it achieves 85.7% under standard conditions and 65.7% under unseen object configurations, while GR00T N1.7 achieves 70.0% and 48.6%, respectively. Project page: https://ju6276.github.io/Action-Grounded-Foresight/
A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.
Automotive radar is a key sensing modality for safety-critical vehicle functions due to its robustness under adverse weather and lighting conditions. Recent advances in AI-based radar perception enable the direct estimation of object parameters from a single radar measurement cycle. However, the internal decision process of data-driven models is typically not explicitly linked to the underlying radar sensing physics. Consequently, object estimates may achieve high statistical accuracy while remaining physically inconsistent with the measured radar signature, particularly in previously unseen scenarios. Such inconsistencies are especially critical for heading estimation, as they directly affect trajectory prediction and collision assessment in pre-crash scenarios. This paper presents a physics-based consistency assessment framework for validating AI-derived vehicle hypotheses in automotive radar perception. The proposed approach generates an expected radar signature from AI-estimated object parameters using a physics-based reference model that incorporates occlusion-dependent edge visibility, aspect- and angle-dependent RCS modeling, and characteristic wheel-induced MD signatures. The expected signature is compared with the observed radar point cloud using a Wasserstein-distance-based consistency metric computed from three complementary features: the spatial distribution of detections along object edges, the local detection count, and the radar reflection intensity. In this way, physically implausible object hypotheses can be identified and corrected independently of the underlying neural network architecture and without model retraining or architectural modifications. The proposed consistency module is integrated as a cascaded post-processing stage for vehicle heading estimation.
Video world models enable candidate actions to be evaluated through imagined outcomes, but high predicted rewards can favor trajectories with poor execution quality. We introduce Trusting Imagined Futures (TIF), an offline supervision selection method for vision-language-action (VLA) post-training that audits predicted rewards using execution feedback. A multidimensional reward model predicts a utility score for candidate ranking and five dimensions of execution quality. An auditor uses reward predictions and uncertainty to identify overestimation patterns learned from paired imagined videos and real executions. TIF accepts the candidate with the highest predicted utility when its advantage over the existing trajectory exceeds a margin and its audit risk passes a threshold; otherwise, it retains the existing supervision. The retained real trajectories then supervise behavior cloning. Across four LIBERO suites and three training seeds, TIF achieves a mean success rate of 76.25%, improving over training on the existing trajectories by 3.00 percentage points with the same trajectory count and training budget. Adding audit gating yields 1.47 percentage points with the reward model and advantage margin held fixed. The gains persist against advantage ranking and logistic regression risk selection at matched replacement counts. On recorded videos from three real robot tasks, TIF increases clean completion among selected trajectories from 58.33% to 70.00% across 60 candidate pools.
Multi-Agent Reinforcement Learning (MARL) shows promise in coordinating connected and automated vehicles but offers no safety guarantee. Although Control Barrier Functions (CBFs) can add this guarantee, their optimization problem can become infeasible in practice due to control bounds. Moreover, they often overapproximate vehicle and road geometry, which makes them conservative. This paper proposes the Backup-Horizon CBF (BH-CBF), which evaluates safety along a horizon until all vehicles stop. BH-CBF is recursively feasible under control bounds, and it considers the exact vehicle and road geometry. Based on BH-CBF, we derive a fully decentralized safety filter that only needs a single broadcast of vehicle states and routes per step and stays real-time in dense traffic. We use BH-CBF to safeguard a MARL policy over its life cycle: as a reward during pre-training, as a run-time filter at deployment, and as a filter in the training loop that keeps fine-tuning on unseen maps collision-free. In simulations on real-world maps of a roundabout and an intersection, BH-CBF avoids all collisions of unsafe MARL policies and keeps its safety guarantee at every step. Existing filters either collide, lose the guarantee, or fall back to full braking far more often. In recorded roundabout traffic with 1264 human-driven vehicles over 115 km, our safeguarded policies shorten the median travel time by 14% compared with the human drivers, without any collision.
By harnessing the inherent commonsense capabilities of pretrained Large Language Models (LLMs) and Vision-Language Models (VLMs), current Vision-Language Action(VLA) models for legged robots excel at interpreting language-based navigation commands but lack the physical grounding and explicit safety assurance required for real-world operation. Therefore, this paper aims to cage Legged-Vision-Language Navigation (VLN) through a safety architecture that provides physical grounding and ensures navigation safety. The key idea is not to abandon the powerful capabilities of end-to-end VLA planning, but rather to augment and cage them. In particular, we integrate a high-level VLA planner with a low-level physical-grounding layer that leverages efficient state estimation, in-situ 3D spatial perception, and an Signed Distance Field (SDF) representation to generate executable trajectories. We provide a navigation planner with provable collision-avoidance guarantees under the stated assumptions by combining a low-dimensional Bezier-parameterized MPPI planner with Discrete Exponential Barrier Function (dEBF) constraints. The proposed Legged-VLN system is modular, making it compatible with various VLM/VLA models and agnostic to the robot platform. The proposed system is validated with extensive real-world experiments on humanoid and quadrupedal robots, demonstrating versatile, efficient, and safe vision-language driven navigation capabilities.
We investigate the automated generation of executable robot reinforcement learning (RL) policies from natural-language task descriptions. Rather than using large language models (LLMs) as execution-time decision makers, we use them as designers that construct RL pipelines before deployment, including Markov decision process (MDP) formulation and simulator implementation. We identify a phase-wise structure in this problem: MDP formulation is dependency-structured and sequential, whereas simulator implementation becomes modular once the formulation is fixed. Based on this structure, we propose ARPG, a dependency-aware agentic framework that performs sequential MDP modeling, localized verification and correction, and simulator-structured implementation while externalizing intermediate artifacts. ARPG targets a key failure mode of automated policy generation: executable code may still yield non-learnable policies when state, action, reward, and termination artifacts are not semantically aligned. Experiments in Isaac Sim show that ARPG improves modeling correctness, environment executability, and policy-generation success compared with monolithic LLM baselines and off-the-shelf agentic systems. Additional demonstrations on custom robotics, standard RL, and engineering-domain MDPs further suggest that the same modeling pipeline can be reused beyond the main benchmark suite.
World Action Models (WAMs) improve robotic manipulation by jointly modeling visual dynamics and robot actions. However, most existing WAMs model dense short-horizon visual dynamics, capturing local interactions but providing limited long-range task context. Extending prediction horizons increases uncertainty and computation while entangling task-level evolution with fine-grained local dynamics, obscuring their dependencies and distinct roles in action generation. We propose HiLo-WAM, which decouples long-horizon task evolution from local visual dynamics while jointly modeling their interaction with robot actions. A sparse long-horizon visual stream captures historical task context and future evolution, while a dense local dynamics visual stream models short-horizon robot-object interactions. The two streams operate at different temporal scales within a unified dual-DiT architecture and guide actions through structured cross-stream attention. Progressive inference further reduces unnecessary computation through stream-wise partial denoising, joint denoising, and dynamic skipping. Experiments demonstrate strong long-horizon manipulation performance: HiLo-WAM achieves a 93.70% average success rate on RoboTwin 2.0 and a 17.43 progress score on RoboDojo long-horizon tasks, with robust in-domain and OOD performance on the Fourier GR-3 robot. Ablations confirm the complementary contributions of long-horizon task evolution and local interaction dynamics, while temporal-scale analyses highlight the importance of balancing temporal coverage and resolution. Progressive inference further achieves a 2.93x speedup while improving performance.
Multi-agent systems offer significant advantages in terms of flexibility and redundancy, enabling the efficient distribution of complex tasks among multiple robots. However, their deployment requires advanced control strategies to ensure optimal cooperation between autonomous agents and human operators. We propose a modification of the global connectivity maintenance algorithm to incorporate measurements taken in agent's local frame, using sensors with limited fields of view. This algorithm, responsible for the autonomous behavior of the multi-robot system, is combined with different adaptive supervision strategies, allowing the user to exert control at varying scales over the entire group. (i) Single Agent Control (S): The operator directly controls a single robot, (ii) Pinning Control (P): The operator imposes constraints on multiple robots to influence the group, (iii) Centroid Control (C): The operator acts on the system's center of mass to steer the entire fleet. In conjunction with the connectivity maintenance algorithm, these methods ensure compliance with inter-agent constraints while providing haptic feedback to the user regarding the system's connectivity state. The effectiveness of these approaches was evaluated through a user study, comparing performance with and without haptic feedback across multiple scenarios tailored to the different control modes.
Recent multimodal language models can reason directly about robot scenes, but it is unclear whether they need to repeatedly reinterpret raw visual observations at every step of an interaction. We propose shifting routine spatial reasoning from images to text and symbols through a 3D geometric abstraction that is refreshed locally from observations and read directly by the language models. Specifically, our interface represents scene geometry via typed, evidence-aware symbolic references to object parts, grounds them from calibrated RGB-D, and returns compact textual checkpoints with metric residuals after each action. Symbolic task structure can thus be reused across decisions while metric values are rebound to the current scene, with direct visual reasoning invoked only on demand. Across offline policy synthesis and continuous online execution, reasoning over grounded text and symbols improves multi-step manipulation completion while substantially reducing repeated multimodal queries, positioning explicit geometric state as an effective substrate for agentic robot policies.
Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring future-aware by explicitly predicting candidate-conditioned future states over the planning horizon, which we term rollout. However, rollout incurs high inference cost and accumulates prediction errors. We argue that planning does not require reconstructing a full future scene for each candidate, but only future-relevant information for reliable comparison. We therefore propose RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation. RFWorld constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low. At inference time, candidate trajectories directly query the shared memory via sparse spatial readout for scoring, reducing computation by roughly the planning horizon times the number of candidate trajectories, while avoiding recursive rollout errors. Experiments on NAVSIM and Bench2Drive show that RFWorld learns a more planning-aligned world representation and achieves state-of-the-art performance.
Teleoperation of mobile robots in communication-denied environments requires maintaining a communication link while allowing the operator to maneuver freely. We propose a shared-autonomy framework in which a teleoperated leader is followed by a chain of autonomous robots that relays a line of sight to a fixed base station, a geometric proxy for the link. Connectivity is enforced geometrically through visibility-based Control Barrier Functions (CBFs), with each agent computing its control input locally through a quadratic program. A strict visibility constraint guarantees connectivity, but a follower with no independent motion objective remains stationary, stalling the leader at the boundary of the safe set. Relaxing it preserves mobility at the cost of the guarantee. Our framework resolves this conflict through nested hard-soft visibility constraints: a full field-of-view (FoV) constraint enforced strictly to guarantee connectivity and a contracted FoV constraint imposed on each follower as a relaxed behavioral objective that drives it inward before the connectivity boundary is reached. We prove feasibility of the local quadratic programs and forward invariance of the connected, collision-free set under the resulting distributed controller. The contraction parameter shapes follower behavior without affecting the guarantee, which follows from the strict constraint alone. The framework is evaluated in confined and cluttered environments on two simulated systems: a kinematic integrator and software-in-the-loop Crazyflie quadrotors. Compared with a baseline tuned to reach the goal in comparable time, the framework keeps the links far closer to the connected set and moves the followers less.
Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments. However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for real-world deployment due to the need for substantial human intervention. While prior work has studied non-episodic RL in relatively small policies trained from scratch, its behavior when fine-tuning modern large-scale pre-trained vision-language-action (VLA) models remains underexplored. In this work, we introduce CRONOS, a simulation benchmark for RL fine-tuning of VLAs under non-episodic scene resets. CRONOS leverages high-fidelity physics simulators and adopts shared-scene multi-task settings. Using CRONOS, we show that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models. Moreover, we find that non-episodic training enhances long-horizon manipulation and improves generalization to previously unseen object configurations and task sequences. Project page: https://embodiedai-ntu.github.io/cronos/
Post-training quantization (PTQ) for vision-language-action (VLA) models promises smaller and faster VLA deployments. However, when analyzing existing VLA quantization works, we realised that it is hard to reason about the performance of the suggested quantization method compared to existing, similar, or in many cases, simpler PTQ methods. We present LoopQ, a closed-loop benchmark that compares multiple quantization policies on the same checkpoint, layers and engine, varying only the method and the kernels. We evaluate RTN, AWQ, GPTQ, ActQuant and QuantVLA on four VLAs with more than 180,000 episodes of LIBERO and LIBERO-plus, compare against QVLA's reported results on the same layers, and benchmark whether the four public VLA-quantization releases can be reproduced. We benchmark the methods on an NVIDIA H100, an L4, and a Jetson AGX Thor. Our results show that while quantization reliably saves memory, 2-3x for real low-bit models, VLA-specific PTQ methods underperform compared to simpler generic baselines. At 4 bits, RTN, AWQ and GPTQ match or exceed ActQuant and QuantVLA, plain RTN matches the calibrated methods, and plain AWQ matches the success QVLA reports for itself. Standard LIBERO hides the losses that do exist: configurations with no significant LIBERO loss lose 1.5-4.3 points under paired LIBERO-plus perturbations. Speed is a weaker story. At batch 1 on the H100, no quantized pi0.5 or OpenVLA-OFT configuration is faster than its 16-bit model (1.06-1.58x slower on library kernels); only the L4 with int8 kernels gains (4-14%), the Thor is slower on every 4-bit configuration, and the engine alone changes latency by 2.1x. Profiling explains why: pi0.5's quantized backbone is compute-bound, while its memory-bound action expert, 63% of GPU time and 13% of the parameters, stays in 16 bits.
Hierarchical pipelines for humanoid loco-manipulation typically pair a task-agnostic whole-body controller (WBC) with a downstream task policy. Such WBCs are often trained through manual reward shaping, which yields visibly machine-like motions; more consequentially, they are trained without the manipulated object in the scene. Object dynamics are instead approximated through randomized end-effector force disturbances, a proxy that fails to reproduce the distributed multi-contact wrench a real payload applies across the arms and torso, with the gap becoming critical near the platform's payload limit. In this work, we train the low-level (LL) controller itself as an object-aware motion prior: a single policy trained via motion imitation on retargeted motion-capture (MoCap) references that span the core motion primitives of the downstream task, with the manipulated object physically present in the scene. This single stage inherits natural human-like coordination from the references and absorbs the realistic contact wrench at its source, while exposing the same compact task-space command interface used by command-tracking WBCs. A reference-free high-level (HL) policy is then trained on top, with its action channel anchored to the empirical envelope of the low-level training data so that it generalizes the priors to a long-horizon multi-stage task while structurally preventing queries that would push the low level off-distribution. We instantiate the framework on a Unitree G1 for bimanual box pick-and-place: the same deployed policy generalizes across object masses and dimensions, initial and goal poses, and reactively recovers from intentional drops mid-carry. Video: https://youtu.be/viR_ULnRDQQ.
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 https://dex-hot.github.io/.
Web services provide walking directions for nearly every city, but following them reliably over long routes remains challenging for autonomous robots. Point-goal navigation policies rely heavily on accurate GNSS, while most vision-language navigation models struggle to execute even short instructions outdoors. We present WayTrace, a hierarchical system that connects web-map directions to robot motion through language. An off-the-shelf orchestrator vision-language model reads the turn-by-turn directions, a satellite map and recent camera images, and issues one atomic language command at a time, such as "cross the road to the left". An onboard trace predictor, trained on over one million automatically labelled samples from street-level images, draws the path for this command in the image, and a reinforcement learning policy tracks it. In long-range simulated missions, WayTrace remains robust to GNSS noise and rarely leaves crosswalks or sidewalks, while point-goal baselines degrade sharply with about ten times more violations. Deployed on a wheeled-legged robot, WayTrace completes real-world missions of up to 1.37 km at about 1.1 m/s through a busy city centre, rural trails and a university campus, handling crosswalks, staircases and construction sites. Project page: https://way-trace.github.io
Scaling vision-language foundation models has significantly advanced generalist robot manipulation, but the increased model scale introduces computational latency that degrades real-time physical reactivity. Existing Vision-Language-Action (VLA) architectures execute high-level semantic reasoning and action ex- ecution sequentially within the primary control loop, creating a fundamental tension between semantic-reasoning capability and robot agility. To address this, we propose Asynchronous Robot Policy (ARP), an architectural framework that decouples semantic reasoning from low-level action generation using asynchronous processes operating at independent frequencies. In ARP, a high-capacity Vision-Language Model (VLM) asynchronously updates a semantic memory at low fre- quency, while a lightweight Vision-Action Expert, conditioned on this semantic memory, generates robot actions at a much higher control frequency. Such a formulation, enables having a fast perception-action loop without compromising on the semantic capability. To overcome asynchronous memory staleness, ARP trains the vision-action expert on the semantic staleness and execution delay, with temporally mismatched observation across processes. On Franka manipulation tasks, ARP achieves an 18% higher success rate and 20% less time need for execution in quasi-static setups, while 3-5 times baseline performance in dynamic simulation environments. Furthermore, ARP enables operating the VLM at 10 times lower than its nominal frequency with no significant performance loss making it much more efficient than the baseline. These results highlight the architectural advantages of modeling robot policies as asynchronous processes, enabling real-world reactive deployment without sacrificing the scale of foundation models.
Robot foundation models have shown remarkable performance in robot control, yet adapting them to a new task still relies heavily on teleoperated demonstrations. Egocentric human videos offer a scalable substitute, but overlaying rendered robots on human videos or retargeting human poses into robot actions leaves significant visual or action gaps for high-DoF robot embodiments. To address this limitation, we propose RoboTryOn, which treats human-to-robot translation as virtual try-on: try-on keeps the person and swaps the garment, RoboTryOn keeps the demonstrated motion and swaps the human for the robot. Specifically, RoboTryOn converts a human video into a video of the target robot specified by a reference image, while preserving the original task, objects, and background. To maintain visual consistency, we translate selected keyframes autoregressively and use them to guide video synthesis with motion conditioned on the human hand skeleton. Additionally, we use an inverse dynamics model (IDM) that incorporates depth features to infer action labels from synthesized videos for policy learning. Our experiments across multiple humanoid embodiments show that policies trained with our synthetic data improve the average success rate on novel tasks, including challenging bimanual manipulation, from 2% to 60%, without any real robot demonstration of those tasks. Moreover, training with our synthetic data matches the performance of policies trained solely on teleoperated demonstrations at approximately a third of the collection cost, demonstrating the cost efficiency of our approach.
Moving robot swarms from simulation into the physical world can be difficult because small discrepancies in hardware, timing and communication can cascade across interacting robots and alter group behaviour. This challenge is known as the reality gap. When swarms operate in human environments, a second challenge emerges: a perceptual gap between what the swarm physically does and what human onlookers actually perceive. This study examines the same decentralised coordination code deployed across three robotic swarms-tabletop, aerial and human-scale mobile manipulators-during live artistic performances. We find that while the underlying algorithms executed reliably on all three platforms, physical embodiment drastically altered visible motion-distorting execution timescales by more than a factor of three and reshaping trajectory geometry. More importantly, audience surveys revealed that human interpretation does not mirror technical success: how observers attribute meaning (perceived purpose) and how they react emotionally (comfort versus threat) depend heavily on physical form. Meaning attribution and emotional responses did not vary together. Our results demonstrate that successfully transferring swarm software to physical hardware is insufficient for real-world deployment. Addressing the reality gap does not guarantee that the resulting collective motion will be readily interpreted by human observers. Swarms destined for human environments must be engineered not only for decentralised stability but also for the expressive physical dynamics through which humans interpret collective motion.
Vision-language-action (VLA) models increasingly pair a pre-trained vision-language model (VLM) with a flow-matching expert that conditions its action predictions on the VLM's key-value representations. Those representations must carry information useful for control, yet the VLM was never trained for the action expert's flow-matching objective. Two signals can address this: gradients backpropagated from the expert's loss (coupling), or VLM supervision to predict discrete tokens encoding the same target actions. Prominent training recipes forgo the first, blocking expert-to-VLM gradients (insulation) to protect the VLM's existing capabilities, while also supervising it on vision-language data and action tokens. Because vision-language co-training also aims to preserve those capabilities, the additional protection provided by insulation is unclear. At the same time, insulation removes a direct signal about which features continuous action prediction requires. On the other hand, action-token supervision offers an alternative way to learn action-relevant representations, which may explain why insulation succeeds in practice. We disentangle these factors in autonomous driving and manipulation by independently varying action-token supervision and whether the expert's loss updates the VLM. In open-loop driving, insulation is competitive with coupling when action tokens are supervised; without them, coupling reduces trajectory-prediction error by roughly 25%. When both components are trained jointly from the outset, coupling increases closed-loop driving route progress by approximately 17% with action-token supervision and 40% without it, and similarly improves robot manipulation performance under both settings. These findings show that the value of gradient insulation depends on the VLM's action supervision and the evaluation setting, challenging insulation as a default VLA training recipe.
Regularizing online reinforcement learning (RL) toward a pretrained base policy can improve sample efficiency and learning stability, but regularization that is too restrictive limits how much the policy can improve. Base policies -- typically diffusion or flow-matching models trained by imitation learning on large, diverse datasets -- capture many behaviors that are reasonable but suboptimal. Existing regularizers using such base policies are too restrictive in one of two ways: behavioral cloning regularizers pull the actor toward the full base-policy distribution, penalizing it for discarding suboptimal modes, while hard support constraints forbid improvements that lie just outside the base policy's support. We propose Geometric Support Behavior Regularization (GSBR), which penalizes actions by their distance from the base policy's support. Actions within the support incur no penalty, so the actor can concentrate on high-value modes; outside the support, where value estimates are less reliable, the penalty grows smoothly with distance while still permitting improvement when the value gained outweighs the penalty. GSBR estimates this distance from a finite set of base-policy samples, so it requires only sample access to the base policy. Across 19 tasks on four robotic benchmarks, GSBR raises the average success rate from 33% for the base policy to 95%, achieving the highest average success rate and throughput among all compared methods, with about 23% higher normalized throughput than the next-best RL method. Project website and open-source code at https://charlesxu0124.github.io/gsbr/ .
Humanoid robotic hands must provide sufficient force, speed, and backdrivability within a human-scale envelope. Tendon-driven transmissions address this challenge by relocating actuators to the palm and forearm, but routing paths, moment arms, and capstan dimensions jointly determine both force capability and joint speed, so selecting them sequentially satisfies one requirement at the expense of the other. This paper presents a pose-robust actuation co-design for tendon-driven robot hands (PACT) framework that optimizes tendon routing, moment arms, and capstan dimensions under pose-dependent force requirements and drivetrain-bandwidth constraints. A feasible-force formulation enforces actuator bounds and equilibrium at all joints, while a max-min objective maximizes task-force coverage at the weakest pose. Applied to a four-degree-of-freedom finger, the framework produces an asymmetric N + 1 tendon topology using quasi-direct-drive actuators. Across eight poses, the design achieves task-force coverage of 0.88-1.00 and a predicted 5 Hz minimum isolated-joint flexion/extension bandwidth within a 70th-percentile human-size envelope. Prototype measurements deviate from predictions by up to 24.5%, primarily due to unmodeled transmission losses. These results indicate that co-designing routing with the drivetrain can meet pose-dependent force requirements without relaxing the bandwidth constraint, paving the way for human-sized robotic hands with human-level performance.
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot in the target scene and rebuilds the task in simulation: it writes the scene, an expert controller, and a success judge. The simulator supplies exact actions, and a video model conditioned on real images renders each rollout as photographic video, generating all camera views together consistently. The output is real-ready data: synchronized camera views labelled with the robot's actions, on which a policy can be trained directly and deployed on the real robot. Independent judges certify the expert and every rendered episode before admission. On five real-robot tasks, policies trained only on farm data match policies trained on as many teleoperated episodes (93 vs. 84 successes in 100 trials), and under an unseen tablecloth and coloured light they keep 87 successes where the teleoperation-trained policies fall to 46. Adapting a task is fully automatic and costs \$21 of API usage on average, paid once per task, plus \$5 for a render contract; every further episode costs \$0.80 on average for simulation, rendering, and review, with no robot or operator. One hour of three-view data for a task costs \$107 on average, these costs included, slightly below a quote of \$117 for teleoperation in China and below \$290 in labour alone in North America.
Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes little to overall policy performance. Recent work has shown that curating such unguided datasets can substantially improve policy performance, but these approaches operate by filtering existing datasets after collection and therefore do not prevent the acquisition of uninformative data. In this work, we propose GUILD, a novel Guided Data Collection (GDC) method that actively reasons about which data should be collected to maximize downstream policy performance. We introduce an iterative framework that alternates between 1) task proposal and data collection and 2) data evaluation to close the loop. For task proposal, we leverage semantic priors from vision-language models to identify relevant environments, object configurations, and goals for data collection. However, since semantic relevance does not imply policy improvement, we perform data evaluation. By leveraging predictive data attribution we approximate how the collected trajectories influence policy performance on a target deployment setting. This signal is then used as feedback to guide subsequent data collection, closing the data collection loop. We evaluate our approach in simulation and real robot settings, demonstrating that guided data collection substantially improves sample efficiency and deployment performance compared to passive data collection strategies, multiple baselines and experienced roboticists. More information at https://robin-lab.cs.utexas.edu/guild2026/
Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer across embodiments. Precise IK remains laborious: redundancy and singularities complicate the inverse mapping, execution depends on hand-tuned controllers, and training data on physical robots are costly to collect. We present PolicyIK, a goal-conditioned reinforcement learning policy for high-precision IK. It updates joint-position references from pose feedback and observes its accumulated reference relative to the measured joints, so it can retain the offset that the position controller needs at rest. Two-scale pose errors with an error-dependent action gain resolve millimeter residuals while preserving large motions. Progress and dwell rewards teach it to both reach the tolerance and stay within it. In simulation, a single attempt by the trained PPO policy keeps the mean errors over the final second within 1 mm and 0.2{\deg} on 93.5% of held-out tasks, and a deployment protocol raises success to 98.9%. When trained directly on a physical arm with an off-policy RL learner, PolicyIK achieves higher reaching and holding success than all four classical IK controllers under the same time budgets. In simulated pick-and-place, PolicyIK executes the end-effector commands of the $\pi_{0.5}$ VLA policy with 95.7% success. These results show that reinforcement learning can provide high-precision inverse kinematics for robot arms. Code is available at https://github.com/Tinaliu0123/PolicyIK.
Deploying deep learning on microcontrollers (MCUs) requires fitting both the model weights and runtime activations within tens to hundreds of kilobytes of SRAM and Flash. Existing approaches either use an interpreter with a pre-written kernel library or combine a Python code generator with hand-written C kernels. This incurs dispatch overhead and requires framework dependencies. None produces self-contained, dependency-free C code specialized to a given model. In this paper, we present te-comp, the first complete MLIR-based compiler that takes a standard model in .tflite or .safetensors format and emits all C source files needed for deployment: the inference engine (kernels, weight arrays, memory layout) and the RTOS integration layer with zero runtime dependencies. On 10 MCUNet CNN benchmarks, te-comp outperforms MCUNet TinyEngine by using 38% less SRAM (up to 5.9$\times$) and 15% less Flash, while generating complete C code rather than linking a pre-written kernel library. To demonstrate, we use te-comp to compile an 8.3M-parameter GPT-Neo transformer (TinyStories-v2) and deploy it on a single-core Cortex-M7 at 160MHz. The full firmware uses 249KB of 512KB SRAM and 3.62MB of 4MB Flash and achieves approximately 1 token/s interactive text generation via Q4_0 weight quantization, a stateful int4 KV cache, and vocabulary pruning -- a capability no existing MCU inference framework supports.
We describe our approach to the LUMPI track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.4793 combined, from a detection mAP of 0.1333 and a realism score of 0.9126. Our contribution is not a new architecture. Working from a PointPillars baseline, we obtained most of our gains from three sources. First, a diagnosis that small object failure in roadside LiDAR is a localisation problem rather than a detection problem, which led to a parameter free geometric refinement worth 86 percent relative on pedestrian AP. Second, an audit of our own post processing which revealed that a shipped rule was destroying valid predictions, the repair of which produced our single largest detection gain at 335 percent relative on the Van class. Third, treating the realism metrics analytically rather than as a black box, which showed that one of the four components is a closed form function of nine summary statistics. We also report an experimental methodology that we believe is the more transferable result. Because mean AP decomposes into independent per class terms, a single submission can carry several mutually controlled experiments, and a submission assembled entirely from previously measured components has a score that is known before it is sent. We predicted our final score to four decimal places prior to submission. We report negative results at equal length, and give a full account of data provenance and compliance in Section 8, including a full account of every mechanism contributing to the submitted score.
We describe our approach to the V2X-Real track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR from an Ouster OS1-64 unit, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.7457 combined, from a detection mAP of 0.4382 and a realism score of 0.9251. Three findings account for most of our result, and all three were diagnostic rather than architectural. First, a coordinate frame mismatch between our predictions and the evaluation ground truth was suppressing detection AP entirely; recovering it took our score from 0.3520 to 0.5147 in a single submission. Second, a single global non maximum suppression threshold was destroying genuine pedestrian detections, because pedestrians occur in groups and a 0.3 IoU threshold applied to a 0.7 m box suppresses distinct neighbouring people; correcting this per class raised overall mAP from 0.0751 to 0.4295. Third, approximately 31 percent of the real reference point cloud consists of null returns encoded as the literal point (0, 0, 0), a format feature entirely absent from our synthetic clouds, which pinned Earth Mover's Distance near its floor until we modelled it. Negative results are reported at equal length, and Section 9 gives a full account of data provenance and compliance. That section also accounts for every mechanism contributing to the submitted score.
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety. Prior attacks on VLA reasoning corrupt the rationale itself and leave visible evidence in the text. We show that visual perturbations can instead alter the physical action while keeping the generated rationale word-for-word identical. At the shared text/action interface of Alpamayo for driving and InstructVLA for manipulation, our text-neutral action-subspace (TNAS) diagnostic shows that the locally most action-sensitive direction is nearly orthogonal to the active text-loss gradients, with 1.87% and 5.28% norm overlap. At equal hidden-state perturbation norms across both models, interventions along this text-neutral residual shift actions 4.64x to 47.8x more than text-gradient perturbations, whereas text-gradient perturbations induce 21.2x to 277x more text drift. Steering visual perturbations along this direction reaches the same decoupling from the image. Across 154 obstacle-annotated driving scenes in Alpamayo, TNAS-guided attacks induce a new collision under a word-for-word identical rationale in 52.6% of scenes under full-image perturbations and 35.1% under a localized forward-camera patch, compared with 4.55% for unguided action attacks. Relative to a text-preserving baseline, TNAS guidance raises exact rationale preservation from 83.0% to 89.5% and cuts teacher-forced text drift by 68.4% at a comparable collision rate. In InstructVLA, TNAS guidance cuts text drift by 40.5% and preserves the exact response on 85.0% of examples alongside a 1.73-unit action-chunk shift. An unchanged rationale therefore cannot certify a safe action, so monitors for reasoning VLAs must verify the predicted action channel directly.
Funnels, time-varying invariant sets around nominal trajectories, certify that a closed-loop system tracks its plan, and can be composed into verified motion plans. Their computation by sum-of-squares (SOS) programming is well established in formulation but not in practice: the result depends on implementation choices such as the initial guess, Lyapunov function normalization, and termination rule, which the literature documents only briefly. This paper presents a self-contained treatment of SOS-based funnel computation, implemented in the open-source package computeSOSFunnels. We propose a minimum-volume formulation with inlet and outlet constraints under which funnels with coinciding nominal endpoints compose by construction. Numerical experiments on a unicycle, with timing studies on a cart-pole and a 12-state quadrotor, characterize the pipeline: infeasible initial guesses are partly decidable before solving, the certificate shows no violations among 39,000 boundary samples per funnel under the true dynamics, and constructing the semidefinite program, not solving it, dominates computation time.
Despite recent advances in camera-based online HD map construction, these systems remain susceptible to sensor failures due to their reliance on onboard cameras. In contrast, satellite images remain available independently of real-time sensing conditions as they are cached offline. Existing methods utilizing satellite images, however, primarily leverage them under nominal conditions, without explicitly addressing them as redundancy when a sensor degrades. To address this gap, we propose ReSMap, a redundancy-aware camera-satellite fusion framework for robust online HD map construction. Our framework explicitly leverages satellite images as a complementary source to improve robustness against camera failures. A Predict-then-Fuse (PTF) module fuses camera and satellite BEV features by using each branch's own prediction confidence as a per-pixel reliability weight, with no learned router. An Object-Centric Cooperative Multi-modal Query (OCMQ) decoder then extends this per-modality separation to the query level: each modality cross-attends only to its own BEV, and per-modality updates are merged through a learned per-token gate. Our model achieves state-of-the-art performance on nuScenes across all splits and range settings. More importantly, it also sets the new state-of-the-art under camera-failure scenarios, demonstrating that satellite images serve not only as a strong prior but as practical redundancy for robust online HD mapping.
Vision-Language-Action (VLA) models generalize across tasks, but their autoregressive decoders need sequential forward passes in proportion to the action horizon, each bounded below on embedded aerial platforms by streaming billions of parameters from memory. We present Aero-VPA, a lightweight Vision-Predictor-Action architecture for 3D navigation on edge hardware. A compact RGB-D Vision Transformer and a five-head ensemble predictor, trained without pixel reconstruction, forecast the next latent state; a Conditional Flow Matching solver generates a velocity and yaw-rate chunk in two Euler steps, so each decision takes five sequential network evaluations; and the ensemble dispersion drives an uncertainty fallback. Version 1 specified the architecture, deployment and protocol without results. This version reports the first closed-loop evaluation: PX4 software-in-the-loop simulation of quadrotor missions in procedurally generated forests. Behaviour cloning failed on all 60 missions despite open-loop errors of 0.02-0.04 m/s: the policy copies its last command, a copycat form of causal confusion. DAgger with a privileged, safety-gated supervisor gave the first successes but plateaued at 11.1-21.1% across six checkpoints. A map-free runtime shield with a 15 s depth memory, barrier constraints, a cap on motion outside the 73-degree field of view and backoff along the flown path raised the first DAgger policy's success on 180 paired missions from 21.1% to 52.2% (95% CI [45.0, 59.4]; exact McNemar p = 1.2 x 10^-10) and cut its crashes from 72.2% to 22.2%, while timeouts rose from 2.8% to 23.3%. All six checkpoints gained 30.0-34.4 percentage points, at mean speeds of 1.16-1.36 m/s. The code (https://github.com/ylee-sling/Aero-VPA), the trained policy (72.6 MB, https://huggingface.co/ylee-sling/aero-vpa) and the full benchmark dataset are public.
In shared settings, social robots may need to exchange information with an individual while limiting co-present others' access to or interpretation of that information. Publicly observable speech and gestures may not adequately support such exchanges. We investigate a wearable-mediated channel for discreet interaction that combines in-ear audio messages with deliberate rightward head tilts as responses. To examine its feasibility and participants' experiences, we studied 20 pairs (40 participants) playing a card game with a screen-based conversational agent representing a social robot, controlled by a researcher in a Wizard-of-Oz setup. Each pair played with and without the channel. One participant wore the device (the wearer), while the other (the non-wearer) was informed about the channel after gameplay. The channel conveyed information that could help the wearer or robot character select an opponent they could defeat. The information exchange and subsequent opponent selection occurred as intended in 39 of 40 channel-mediated turns. Wearers reported low perceived pressure/tension in both conditions, with no statistically significant difference between conditions, and favorable usability immediately after use. Retrospective interviews, however, revealed varied accounts of noticing the interaction among non-wearers and contrasting perceptions of teamwork and unfairness. These findings support the feasibility of wearable-mediated exchanges within this game and identify awareness and fairness as considerations for future designs.
Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training formulations do not by themselves ensure that actions and their predicted visual consequences are consistent, potentially limiting the use of pretrained capabilities. We treat video and action as paired modalities linked by this causal relationship and learn their correspondence through a unified training framework designed to better exploit pretrained video priors. Cycle WAM first augments video-action co-training with bidirectional conversion to reinforce cross-modal correspondence and recover forward and inverse dynamics. It then introduces a differentiable cycle-reconstruction objective to further couple the two mappings. The resulting model supports both forward and inverse dynamics, with the potential to improve performance through more effective use of pretrained video priors. Cycle WAM achieves state-of-the-art performance among comparable methods on LIBERO-Pro and substantially improves DreamZero on DROID. Comparisons with UWM characterize its inverse-dynamics performance and show sharper visual detail in the displayed forward-dynamics predictions.
We introduce iMED, the first synchronized multi-endoscope dataset for robot-assisted minimally invasive surgery (RAMIS), designed to address a fundamental limitation in surgical vision benchmarking: the absence of independent held-out viewpoints. Existing surgical datasets capture single-trajectory sequences from a single endoscope, making it impossible to distinguish geometric generalization from photometric interpolation along a narrow forward-facing path. iMED provides 340 sequences ~170K synchronized timepoints with 4 views per timepoint) recorded simultaneously from two independent stereo endoscopes across ex vivo, postmortem, and live surgical settings, spanning 14 specimens with diverse anatomical regions and motion regimes. The dataset includes calibrated camera intrinsics, ArUco-based frame-wise pose estimates with uncertainty quantification, instrument segmentation masks, and rich clinical metadata. Using a train-on-one-endoscope, test-on-another evaluation protocol, we benchmark 23 state-of-the-art methods across rigid and deformable novel view synthesis, pose estimation, feature matching, and monocular depth estimation. Our experiments show that methods relying primarily on photometric supervision degrade substantially under this held-out-endoscope setting, while methods with explicit geometric regularization are more robust across views in our benchmark. Notably, large-scale foundation models transfer surprisingly well to surgical imagery, often outperforming domain-specific models, suggesting pitfalls in current fine-tuning protocols. iMED establishes a new evaluation protocol for geometric generalization in surgical vision.
Robots in shared settings may expose information intended for an individual user to nearby bystanders. Robot tutoring makes this concern particularly salient: critical feedback is directed at an individual learner, yet bystanders may overhear or see it. To address this, we compared context-invariant and context-adaptive robot behaviors in a between-subjects study with 40 participants. Following an initial phase without a bystander, a bystander entered the setting. Participants then received two scripted critical feedback messages concerning their pronunciation and handwriting, independent of their actual performance. With the context-invariant behavior, the robot tutor delivered both messages aloud. With the context-adaptive behavior, the robot tutor scanned for the bystander, turned its body and display away after detecting them, gave a spoken attention cue, and presented the same feedback messages silently on its display. Participants rated the robot tutor higher in perceived privacy awareness and perceived social competence in the context-adaptive condition than in the context-invariant condition, while evidence for reduced experienced embarrassment was inconclusive. These findings inform the design and evaluation of robots that respond to bystander presence by adapting how they communicate potentially sensitive information.
Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause closed-loop task failure. This work introduces Dynamics-Risk Adaptive Plasticity (DRAP), a replay-free method that estimates the historical importance of adaptable model tensors from sample-level action gradients weighted by local trajectory-amplification risk. A ridge-regularized local linear model is fitted to expert state-action transitions, and the largest singular value of its state-transition matrix provides a policy-independent, Lyapunov-inspired estimate of one-step perturbation amplification. After each task, risk-weighted squared gradients are accumulated in a tensor-level importance memory. During subsequent tasks, DRAP uses normalized cumulative importance to scale the effective AdamW learning rate of each tensor, immediately reducing the plasticity of components that supported previous behavior at dynamically sensitive trajectory points. We instantiate DRAP on a fixed KappaTune-selected subnetwork of OpenVLA and evaluate replay-free sequential adaptation across the LIBERO Spatial, Object, and Goal suites. Compared with standard AdamW fine-tuning and EWC, the results show substantially improved retention of previously learned behaviors while preserving strong new-suite acquisition.
Repeated robotic monitoring requires localization across visits to the same environment, even if the environment changes. Such changes can substantially reduce persistent visual content, and repetitive structures can lead to incorrect cross-session correspondences. In this paper, we address visual multi-session registration of a new data recording (the query session) to a previously reconstructed reference map. Under substantial visual and structural changes, cross-session localization may be possible only for parts of the trajectory. In our approach, we therefore rely on a sparse set of reliable absolute pose constraints and combine them with within-session relative-pose information to register the complete trajectory to the reference map. We first estimate absolute alignment hypotheses through visual place recognition, local feature matching, and geometric verification. We then use sequence consensus to reject hypotheses that are inconsistent with a common query-to-reference alignment and retain the remaining poses as absolute anchors. These anchors are refined through featuremetric alignment against a Gaussian feature field and combined with within-session relative-pose constraints in a robust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently reconstructed Structure-from-Motion geometry. Our results show that sparse, reliable absolute anchors can provide accurate and complete trajectory registration even when reliable cross-session correspondences are available only for part of the query session.
We propose PadLoc, a training-free localization back-end that places a moving sensor within a known floor plan. Floor plans are cheap, persistent, and robust to appearance change, but recent learned-depth methods localize against them by filtering per-frame depth through dense $(x,y,\theta)$ pose grids. PadLoc keeps the swappable depth front-end and replaces the dense grid back-end with sparse geometric matching: dominant wall orientations define a small pose-candidate set, masked normalized cross-correlation scores observed free space against the plan, and a moving-pose Gaussian-mixture Bayes filter plus consensus readout decodes the trajectory. Holding each competitor's depth fixed, PadLoc matches or beats UnLoc's forward filter and the F3Loc filter at every Gibson trajectory length, and UnLoc's offline refinement from $T=35$ on; it exceeds Z-FLoc's published results with a shared MapAnything front-end. On Bonn LiLocBench, PadLoc improves pooled SR@1m over UnLoc by 23-32 pp under wheel odometry and 35-43 pp with ground-truth motion; with full-FOV LiDAR plus wheel odometry the same readout reaches 100% SR@1m at 9-10 cm median error on the static sequence. On the Hilti-Trimble Localization Challenge PadLoc localizes a camera-only fisheye rig on construction floors hundreds of metres across at 0.90-0.98 online SR@2m on three of five sessions; adding learned wall isolation, applied to every session, covers all five at 0.67-0.92 with the localizer unchanged throughout. PadLoc thus matches or outperforms dense grid back-ends while preserving sensor modularity and a compact state that does not grow with trajectory length.
Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address visibility errors in accumulated LiDAR scans, we introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal(HPR). Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction, which is an approach suited to completed scan surveys, the combined HPR and LDGVS filtering retains approximately three times the point density at comparable absolute relative error. We also apply the pipeline to the BotanicGarden dataset to systematically compare depth estimation and 3D reconstruction methods. Feedforward methods produce dense depth predictions efficiently, but their 3D reconstructions can contain duplicated structures. Conventional SfM generally produces more coherent geometry, but its reconstructions remain sparse and more prone to failure in challenging vegetated scenes. The benchmark toolkit and datasets will be released.
Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the underlying action with irrelevant visual variations, limiting transfer across embodiments. We introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner. Our approach extracts compact latent actions from the video model's rich spatiotemporal features, compressing each latent video frame by $\boldsymbol{300\times}$ ($\boldsymbol{1{,}200 \rightarrow 4}$ tokens). In addition, by leveraging the video model's generative prior, these latent actions capture action-relevant dynamics disentangled from visual appearance. The resulting latent space serves as a shared action interface across embodiments (human and robot), environments, and action parameterizations. On LARY-Bench, DreamX achieves state-of-the-art performance among latent action models. Moreover, actions encoded in one setting remain effective in another: the latent space supports any-to-any video transfer and zero-shot action transfer across diverse embodiments and environments. Furthermore, this shared interface also enables policy learning in a compact latent action space, reducing the computational cost of video-diffusion-based policies.