Nachrichten & Forschung

arXiv:2605.19469v2 Announce Type: replace-cross Abstract: Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a finite set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty, eliminating the need for explicit exploration bonuses. Under regularity conditions, we derive high-probability guarantees of safety throughout learning and a finite-time sample complexity bound for recovering a near-optimal policy. Empirically, SBSRL achieves safe and efficient exploration both in simulation and in real robotic hardware, a

arXiv:2609.28429v2 Announce Type: replace Abstract: An always-on robot faces an endless stream that never resets: instructions arrive and lapse, the scene changes, and its own past actions reshape what it must reason about. Today's action models are built for the opposite: a fixed instruction, no mid-task intervention, single-step reasoning. In an open-ended world a robot must watch a live stream for far-future cues, recall its own far-past actions, and act on them under dual-arm concurrency. We present ARMS (Always-on Robot in Multi-modal Streams), a deliberately simple streaming policy: a single pretrained $\pi$0.5 backbone augmented by three lightweight modules that turn live perception, embodied states, and the robot's own past actions into context the backbone reads before it acts. The modules update this context asynchronously, so watching and recalling never block acting and the two arms act at once. Rather than inventing new mechanisms, ARMS integrates these learned context pro

arXiv:2605.31234v2 Announce Type: replace Abstract: Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos.To address this, we propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos. Specifically, HARP uses paired human-robot demonstrations as cross-embodiment bridges and abundant unpaired human and robot videos as a scalable dynamics supervision data source. It trains a robot-adapted visual encoder and a latent action model with manipulation-centric a

arXiv:2605.07605v2 Announce Type: replace Abstract: Autonomous robotic assembly of interlocking bricks demands seamless integration of long-horizon task reasoning, spatial grounding, and fine-grained manipulation. This paper presents BrickCraft, a compositional framework designed for long-horizon and generalizable interlocking brick assembly. BrickCraft models the assembly process using a relative formulation, where each step is anchored to a reference brick within the partial structure, thereby decomposing complex tasks into a finite set of reusable primitive skills. BrickCraft bridges the gap between high-level assembly plans and physical execution through situated manuals, which provide explicit spatial guidance for learned visuomotor skills by projecting the assembly intent onto real-time robot observations. Finally, BrickCraft employs a modular execution pipeline that chains these spatially grounded skills to accomplish long-horizon assembly tasks. Extensive experimental validatio

arXiv:2604.02563v2 Announce Type: replace Abstract: Robots that traverse natural terrain must interpret contact forces generated under highly dynamic conditions. However, most terrain characterization approaches rely on quasi-static assumptions that neglect velocity- and acceleration-dependent effects arising during impact and rapid stance transitions. In this work, we investigate granular terrain interaction during high-speed hopping and develop a physics-based framework for dynamic terrain characterization using proprioceptive sensing alone. Through controlled hopping experiments with systematically varied impact speed and leg compliance, our measurements reveal that quasi-static based assumptions lead to large discrepancies in granular terrain property estimation during high-speed hopping, particularly upon touchdown and controller-induced stiffness transitions. Velocity-dependent drag alone cannot explain these discrepancies. Instead, acceleration-dependent added-mass effects - ass

arXiv:2602.18655v3 Announce Type: replace Abstract: For fully actuated rigid robots, kinematic inversion is a purely geometric problem, efficiently solved by closed-loop inverse kinematics (CLIK) schemes that compute joint velocities to position the robot body in space. For underactuated soft robots, however, not all configurations are attainable through control action, making kinematic inversion extremely ill-posed. Extensions of CLIK address this by introducing end-to-end mappings from actuation to task space for the controller to operate on, but typically assume finite dimensions of the underlying virtual configuration space. In this work, we formulate CLIK in the infinite-dimensional domain to reason about the entire soft robot shape while solving tasks, thereby skipping intermediate approximation steps. We do this by composing an actuation-to-shape map with a shape-to-task map, deriving the differential end-to-end kinematics via an infinite-dimensional chain rule, and thereby obta

arXiv:2602.02473v2 Announce Type: replace Abstract: Enabling humanoid robots to perform agile and adaptive interactions has long been a core challenge in robotics. Current approaches are bottlenecked by either the scarcity of realistic interaction data or the need for meticulous, task-specific reward engineering, which limits their scalability. To narrow this gap, we present HumanX, a unified framework that compiles human video into generalizable, real-world interaction skills for humanoids, without per-task design. HumanX integrates two co-designed components: XGen, an anchor-centric data generation pipeline that yields physically plausible robot interaction data from monocular video and augments it to create a diverse, scalable training dataset; and XMimic, an interaction-prioritized learning framework to achieve generalizable interaction skills from seconds of demonstration. Evaluated across five distinct domains--basketball, football, badminton, cargo pickup, and reactive fighting-

arXiv:2602.00915v2 Announce Type: replace Abstract: As robots are deployed across diverse environments, manipulation tasks require robot hands with different morphologies to satisfy varying task requirements, hardware capabilities, and cost constraints. However, transferring grasping policies learned on one robot hand to another with a different morphology remains a fundamental challenge due to variations in kinematic structures and degrees of freedom across embodiments. To address these limitations, we propose DiffMorphGrasp, the first diffusion-based framework that incorporates hand morphology information into the generative process for cross-embodiment dexterous grasping. The proposed approach maps grasps from diverse robotic hands into a reference hand pose, providing a common space for learning. Grasp generation is then continuously conditioned on structured representations of hand kinematics, encoded as graphs derived from hand configurations, together with object geometry. In ad

arXiv:2601.18923v2 Announce Type: replace Abstract: Depth sensors are widely deployed across robotic platforms, and advances in fast, high-fidelity depth simulation have enabled robotic policies trained on depth observations to achieve robust sim-to-real transfer for a wide range of tasks. Despite this, representation learning for depth modality remains underexplored compared to RGB, where large-scale foundation models now define the state of the art. To address this gap, we present DeFM, a self-supervised foundation model trained entirely on depth images for robotic applications. Using a DINO-style self-distillation objective on a curated dataset of 60M depth images, DeFM learns geometric and semantic representations that generalize to diverse environments, tasks, and sensors. To retain metric awareness across multiple scales, we introduce a novel input normalization strategy. We further distill DeFM into compact models suitable for resource-constrained robotic systems. When evaluated