News & Research

arXiv:2610.24392v1 Announce Type: new Abstract: Human video demonstrations provide rich manipulation strategies for dexterous manipulation learning. We study a setting in which a fully specified simulated scene is used to generate videos that specify the demonstrated manipulation behavior. This setup provides access to scene information such as object geometry, articulation, and camera parameters, while allowing direct control over task and scene configuration. However, generated videos may contain geometric distortions, inaccurate contacts, and other physical inconsistencies, making the recovered motion difficult to execute directly on a robot. We present an end-to-end framework for converting such simulation-grounded videos into physically executable dexterous robot demonstrations. Our perception pipeline leverages the known scene through model-based object tracking with dense foundation-model features and depth-based hand-object alignment. The recovered human motion is then retarget

arXiv:2610.24312v1 Announce Type: new Abstract: Construction productivity has remained a per- sistent challenge, motivating growing interest in humanoid robots that can operate in workspaces and with tools designed for human workers. Realizing this potential requires effective motion control, for which human-derived motion transfer has emerged as a promising approach by capturing and retargeting human demonstrations to humanoid robots. While promising, however, human-derived motion transfer may not fully define how a humanoid should ultimately execute the transferred motion. Once task-relevant motion information has been con- veyed, the humanoid may also exploit its own embodiment through motions that depart from the human demonstration. This study examines whether such Robot-Specific Motion offers an advantage in motion execution efficiency over Human- Derived Motion. On an adult-sized Unitree H1-2, Human- Derived Motion was generated through vision-based capture and retargeting, wher

arXiv:2610.24285v1 Announce Type: new Abstract: Abstract Action-conditioned world models for contact-rich manipulation require data that captures how contact forms, slides, and releases under varying force. Such data are slow to collect through robot teleoperation, which often lacks force feedback and is constrained by gripper geometry. We ask whether these dynamics can instead be learned from human physical interaction and transferred to a robot. We present ACTS, a visuo-tactile world model trained only on human interaction data. Operators manipulate handheld GelSight sensors while we record third-person and wrist video, tactile images, 6-DoF sensor motion, and tactile-derived normal force, yielding React, a 4.9-hour bimanual dataset across three objects. We represent actions at the tactile sensor as motion augmented by force change, providing a shared action space for human collection and robot execution. ACTS jointly predicts future scene, wrist, and tactile observations. On held-ou

arXiv:2610.24267v1 Announce Type: new Abstract: Exposure indices that map technical capabilities onto occupational abilities have become a standard tool for anticipating how AI may reshape work, but existing measures either cover software AI or proxy robotics through patents and installation data that reflect the industrial robots of past decades. We construct the first abilities-based exposure measures for robotics and physical AI, and the first to span occupations, industries, and geographies. Following the framework of Felten et al. (2018, 2021), we build a robotics capability taxonomy of 16 capabilities in eight domains from 78 academic, industry, and standards sources, use a large language model to score the relatedness of each capability to the 52 ONET work abilities, and aggregate to Robotics Occupational Exposure (ROE) for 774 occupations, Robotics Industry Exposure (RIE) for 250 NAICS industries, and county-level Robotics Geographic Exposure (RGE). We find that robotics exposu

arXiv:2610.24257v1 Announce Type: new Abstract: Dual-operator humanoid teleoperation enables collaborative manipulation through two separate robots, but operators lack direct awareness of robot-object contact that is normally available during physical interaction. To address this, we present eXtended Reality Teleoperation (XRT), an extended reality teleoperation framework that returns a robot's fingertip contact through lightweight vibrotactile and/or auditory feedback, and a synchronized dual-humanoid testbed built on it for two operators. Sixteen dyads performed a collaborative crate lift-and-flip under vision only and the three feedback conditions in a counterbalanced within-subject design with verified feedback-channel delivery. Three results follow. First, operators rated our finger-localized vibrotactile display as more effective than our open-ear sonification: all 32 ranked it above the sonification, 18 ranked it most effective, and its cues were rated far easier to perceive and

arXiv:2610.24256v1 Announce Type: new Abstract: Safe, real-time motion planning is especially difficult when a dynamic obstacle actively pursues the ego agent, requiring rapid adaptation as the environment changes. We present TrajEdit, a hierarchical trajectory planner for pursuit-evasion that combines flow matching, trajectory editing, and safety filtering. Rather than regenerating trajectories from scratch at every step, TrajEdit follows the current plan under nominal conditions and adapts its remaining portion through FlowEdit as the pursuer approaches, and falls back to a control barrier function safety filter if the adversarial agent is within a safety threshold. Our use of FlowEdit for trajectory editing reduces computation time while maintaining a comparable success rate. We evaluate TrajEdit in 2D pursuit-evasion with static obstacles and an adversarial pursuer, demonstrating high success rates with low capture and collision rates, while achieving computational time savings ove

arXiv:2610.24241v1 Announce Type: new Abstract: This work demonstrates the use of a fast simulation-based training framework to learn control policies using reinforcement learning. The hardware requirements are minimal and the simulation-learned policies transfer reliably to the real world. With this setup, we show that a quadruped robot can learn to traverse diverse real-world terrains reliably---including in a lunar-analog facility---after less than 20 minutes of training on a single consumer-grade GPU. These results provide a glimpse of a future where reinforcement learning is a crucial tool in developing more capable and robust space robotic systems. Video demonstrations are available at https://youtu.be/vUFJiZdJaQ0.

arXiv:2610.24235v1 Announce Type: new Abstract: With advancements in learning-based policies, robots are increasingly being deployed in human-centric environments, such as manufacturing floors and homes, where safe and precise operation requires compensating for unknown loads while remaining compliant during human interactions. Reliably distinguishing between these interaction types is challenging with a single sensing modality, as force signals cannot separate payloads from human pushes, and vision is susceptible to occlusions. We propose a task-agnostic interaction estimation and adaptive control framework that addresses this challenge by fusing force history and 3D point cloud through a transformer-based classifier. Trained with modality dropout for occlusion resilience and fine-tuned from simulation to hardware, the classifier achieves 91.89% accuracy and maintains above 90% under complete occlusion of one modality. The classifier drives a system identification framework that selec

arXiv:2610.24149v1 Announce Type: new Abstract: Fast motion planning requires both sample-efficient exploration and computationally efficient local steering. Conventional straight-line steering is inexpensive but wastes samples by rejecting colliding extensions. Quadratic program controllers with control barrier function (CBF) constraints can be used to achieve effective local steering but can increase the planning time due to the expensive sequential evaluations. We develop a method to accelerate CBF steering by computing a time horizon within which CBF-filtered velocity may be applied constantly using closed-form kinematic bounds on collision-clearance. Our method, FLASH-CBF-RRT, significantly reduces the number of evaluations compared to prior CBF-RRT approaches because the planner can take adaptive steering step sizes that are shorter near obstacles and longer in open space. We implement this steering procedure as an extension of RRT-Connect in OMPL. Across 689 MotionBenchMaker pro

arXiv:2610.24129v1 Announce Type: new Abstract: Reducing actuator count simplifies robot hardware but also removes independent inputs for maneuvering. The original Rollbot steered by modulating a quasi-stable helical orbit, but moved slowly and relied on external motion capture. Rollbot 2 preserves the single-actuator design while its redesigned mass distribution enables near-straight rolling and more direct travel toward commanded paths and beacon targets. Onboard inertial and ultra-wideband sensing support learned steering, beacon seeking, and waypoint following through one motor-velocity command. Rollbot 2 autonomously approaches UWB beacons without motion capture and completes a 468~m manually commanded indoor route at 0.87~m/s. On the shared 4.8~m ``N'' waypoint benchmark, all 16 trials complete the path with a mean traversal time of 10.8~s and mean time-averaged deviation of 7~cm. Its fastest traversal takes 8.0~s, over 70 times faster than the original Rollbot's 564~s run despit

arXiv:2610.24016v1 Announce Type: new Abstract: Robots that follow natural-language instructions unlock a wide range of autonomous applications in households, warehouses, and labs. Real-world environments are diverse and often heavily cluttered, requiring robots to plan over multiple steps, act, and replan as they work toward a goal. We present CLARO (CLutter-Aware Robot Orchestrator), a VLM agent that orchestrates a set of perception and manipulation skills: open-vocabulary object detection, segmentation, 6-DoF grasping, and non-prehensile pushing to locate and retrieve a language-specified target in clutter. CLARO maintains a memory of its past actions to support long-horizon execution, and emits manipulation targets (grasp poses/3D waypoints) allowing transfer across robot arms without task-specific training. We evaluate CLARO against a range of methods on a dynamic simulation environment and standard image-based benchmarks, demonstrating strong generalization across object classes,

arXiv:2610.24008v1 Announce Type: new Abstract: When a robot possesses more degrees of freedom than a task requires, multiple trajectories can achieve the same objective using distinct motion styles. Compositional robot control aims to preserve a selected style while simultaneously executing an independent task command, effectively balancing these potentially competing objectives. In this paper, we present CODES, a framework for compositional robot control that discovers a coherent style repertoire from diverse recordings and composes it with independent commands. First, motion retargeting maps the recordings to motions executable by the target robot; next, weakly supervised consensus encoding and density-based clustering identify styles within and across recordings without a prescribed count; finally, reinforcement learning trains a policy to compose the discovered styles with independent commands. We evaluate CODES on a Unitree Go2 quadruped across two simulators and physical hardwar

arXiv:2610.23973v1 Announce Type: new Abstract: Robotic rearrangement tasks require planning sequences of actions that fulfill high-level specifications while also being geometrically feasible. Symbolic abstractions make the combinatorial structure of rearrangement tasks tractable, but they usually do not fully capture the geometric constraints that determine which actions a robot can actually realize. These constraints are hard to express in the symbolic model. We propose REAP (Rearrangement with Elicited Action Preconditions), a framework in which a relational graph neural network heuristic is learned over a simple symbolic abstraction. A motion planner serves as a supervisor that elicits the hidden geometric preconditions of the problem during training. Deployed with greedy best-first search, the learned heuristic generalizes out-of-distribution along object count, plan length, and object arrangement, and can be trained jointly on several domains. Compared to classical heuristic sea

arXiv:2610.23943v1 Announce Type: new Abstract: Motion planning in unstructured environments is a bottleneck for robot deployment. Current visuomotor policies predominantly rely on external cameras, introducing perceptual blind spots and fragility due to occlusions, clutter, and calibration constraints. To overcome these limitations, we propose ESCAPE, an online egocentric sensing framework for collision-free trajectory generation. ESCAPE aggregates sparse measurements from distributed depth sensors, converting them into a structured, obstacle-aware point cloud representation. Our policy leverages a flow matching-based generative framework, and trains on a high-quality dataset comprising over 100K safety-critical trajectories. With joint optimization of goal-reaching and collision objectives, it produces safe trajectories directly from these egocentric inputs. Crucially, ESCAPE is trained entirely in simulation and transfers zero-shot to physical hardware without any real-world fine-tu

arXiv:2610.23913v1 Announce Type: new Abstract: Universal Manipulation Interface (UMI) pairs wrist-camera videos with camera trajectories and gripper openings, providing scalable, robot-free data for learning how bimanual actions change a shared scene. Existing interactive world models, however, typically rely on text or single-camera control and struggle to follow each arm's actions while maintaining consistency between the two wrist views. We introduce UMI-WM, an action-conditioned bimanual world model that jointly generates both wrist views from observation history, per-arm relative camera poses, and gripper widths, with cross-view consistency, action following, and visual fidelity. UMI-WM injects each arm's actions into its own wrist stream, while sparse hub tokens exchange scene information between the two streams. Camera-aware geometry conditioning and camera-guided noise further support per-view motion control and cross-view geometric exchange. We adapt the model for block-causa