News & Research

arXiv:2609.27308v2 Announce Type: replace Abstract: We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation benchmark for coding agents spanning contact-rich manipulation, deformable objects, and long-horizon tasks requiring up to half an hour of continuous interaction. We find that frontier coding agents can solve complex long-horizon tasks and transfer prior solutions across both tasks and embodiments. We also design supporting tools that help agents more effectively solve these tasks. However, the resulting solutions require substantial iterative interaction and are typically specialized to individual task instances. We therefore introduce EMBODIEDSWE-GEN, which expands a single solution from coding agent into large diverse trajectories for training a VLA. VLA performance improves with more generated demonstrations, and ag

arXiv:2605.30834v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose \textbf{Hide-and-Seek}, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level anno

arXiv:2605.21704v2 Announce Type: replace Abstract: Locomotion in microgravity often relies on sparsely and irregularly arranged anchors, motivating grasp-based mobility with multiple limbs. In this setting, dynamic traversal requires consecutive anchored interactions under coupled dynamic and kinematic constraints, yet the effects of gait-level motion design on locomotion feasibility and performance remain insufficiently understood. This paper formulates the feasibility and performance objectives for grasp-based dynamic locomotion and develops a gait-level parameter-metric framework that relates motion parameters to corresponding evaluation metrics. A physics-based simulation study instantiates the framework across two quadruped morphologies in randomized three-dimensional anchor environments. Controlled variations in gait-level parameters reveal broadly consistent effects on contact support, motion-induced loading, kinematic feasibility, actuation demand, and traversal time across th

arXiv:2605.14174v2 Announce Type: replace Abstract: Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforcement learning (RL) methods assess safety through average cumulative cost. Such metrics can mask dangerous tail-risk behaviors. To address this, we propose a framework that trains risk-sensitive policies through Conditional Value-at-Risk (CVaR) constrained optimization on an off-policy TD3 backbone and evaluates their safety margins post-training through neural network reachability verification. During training, the policy is optimized under CVaR constraints on cumulative costs, promoting sensitivity to high-cost tail outcomes rather than average behavior alone. After training, we compute action reachable sets under bounded observation uncertainty using Taylor Model analysis, yielding a safety rate metric that quantifies the proportion of evaluated states at

arXiv:2605.05236v2 Announce Type: replace Abstract: In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-winding control based on multi-intelligent body reinforcement learning has become a research hotspot. One of the core problems at present is to coordinate multiple robots to complete the unwinding operation in a highly constrained environment. The existing distributed training framework faces some observability challenges in high-density barrier and unstable environments, resulting in poor learning results. This paper proposes a topology-driven Multi-Agent Reinforcement Learning (TD-MARL) framework to coordinate multi-robot systems to avoid entanglement. Specifically, the critical network adopts centralized learning, so that each intelligent body can perceive the strategies of other intelligent bodies by sharing the topological state, thus alleviating the training instability cause

arXiv:2604.27508v2 Announce Type: replace Abstract: Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactive feedback, robots must recognize human actions as early as possible from incomplete observations. \textit{Sub-actions} offer the semantic and hierarchical cues needed for this, since human actions are inherently structured and can be decomposed into smaller, meaningful units. However, conventional approaches focus primarily on holistic actions and often overlook the rich semantic structure embedded in sub-actions, making them poorly suited for early recognition. To address this gap, we introduce SASI (Sub-Action Semantics Integrated cross-modal fusion), a novel framework that integrates existing graph convolution networks to fuse spatiotemporal features with sub-action semantics. SASI exploits a segmentation model with a traditional skeleton-based graph convolution network, capturing

arXiv:2603.07096v2 Announce Type: replace Abstract: Robots that share space with people need human motion predictions with reliable uncertainty, not just accurate means. This paper presents a structured multitask variational Gaussian process (GP) for probabilistic full-body human motion prediction. The model integrates one-shot prediction of the full horizon, multitask outputs that couple future time steps, a factorization into one sparse variational GP per joint-dimension pair of the rotation representation, and a continuous 6D rotation representation with forward kinematics that preserves bone lengths. Its predictive distribution is available in closed form: a Gaussian with full temporal covariance for each rotation coordinate, which downstream planners operating in rotation coordinates can use without sampling, density estimation, or forward kinematics. On Human3.6M, the model achieves lower kernel-density-estimated negative log-likelihood (KDE NLL) than Motron and DLow at every pre

arXiv:2509.25685v3 Announce Type: replace Abstract: We propose Structured-Diffuser, a diffusion planner that embeds task and motion structure directly into the noise model. Unlike standard diffusion-based planners that rely on zero-mean, isotropic Gaussian corruption, we introduce task-conditioned structured Gaussians whose means and covariances are derived from Gaussian Process Motion Planning (GPMP), explicitly encoding trajectory smoothness and task semantics in the prior. We first formulate diffusion under a task-conditioned, non-isotropic Gaussian prior with closed-form forward and posterior expressions. Building on this formulation, our hierarchical design separates prior instantiation from trajectory denoising. At the upper level, sparse task-centric key states and timings are obtained, which instantiate a structured Gaussian prior (mean and covariance). At the lower level, the full trajectory is denoised under this prior, treating the upper-level outputs as noisy observations.

arXiv:2412.20699v3 Announce Type: replace Abstract: Air-ground collaborative robots have shown great potential in the field of fire and rescue. Mapping and navigation, as the key foundation for air-ground collaborative robots to achieve efficient task execution, have attracted a great deal of attention. This growing interest in collaborative robot mapping and navigation is conducive to enhancing the intelligent execution of fire and rescue tasks, but there has been no comprehensive investigation of this field to highlight their strengths. In this paper, we present a systematic review of the air-ground collaborative robots for fire and rescue from a new perspective of mapping and navigation. First, an air-ground collaborative robots framework for fire and rescue missions based on unmanned aerial vehicle (UAV) mapping and unmanned ground vehicle (UGV) navigation is introduced. Then, the research progress of mapping and navigation under this framework is systematically summarized, includi

arXiv:2609.31507v1 Announce Type: cross Abstract: Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery. SatNav targets city-level navigation missions and uses satellite crops as approximations of UAV nadir views for visual observations. Through an automated cue-to-episode pipeline, SatNav constructs 118K episodes from 59 scenes across 18 cities, with an average trajectory length of 379 m. To stress-test long-horizon memory and geospatial reasoning, SatNav defines three task families: Boundary, Landmark, and Route, targeting loop progress tracking, landma

arXiv:2609.31005v1 Announce Type: cross Abstract: Open-vocabulary 3D maps enable robots to reason about previously unknown environments using natural language. However, existing systems typically segment every incoming image, associate detections with persistent 3D segments, and frequently perform costly Vision-Language (VL) inference. We present TRACKGRAPH, an online open-vocabulary system that maintains short-term 2D mask identity directly in the image stream before fusing segments into 3D. FastSAM masks and CLIP features are computed at sparse keyframes, while dense DINOv3 features are used to propagate masks at a high rate in between. The resulting tracked masks are fused into a class-agnostic 3D segment layer within a hierarchical scene graph, with 3D association handling tracking interruptions and long-term revisits. Compact multi-view CLIP embeddings enable open-vocabulary retrieval. Across Replica, ScanNet++, and HM3D, TRACKGRAPH achieves competitive open-vocabulary segmentatio

arXiv:2609.30629v1 Announce Type: cross Abstract: Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constraints. However, corruption of transmitted intermediate features creates a deployment mismatch for clean-trained split interfaces, while stronger channel-aware codecs can impose substantial onboard cost. We present FreshLatent, a lightweight channel-aware latent adapter that trains a power-normalized encoder-decoder through wireless corruption while keeping the surrounding VLM frozen. We formulate deployment around a mission-conditioned perception requirement and embedded interface cost, linking channel quality and communication budget to the operating conditions under which perception remains usable. At 0 dB and the tightest communication budget, FreshLatent improves gIoU and cIoU over clean split compression by 20.79 and 20.87 points, respectively. At the most adverse evaluated SNR (0 dB)

arXiv:2609.31606v1 Announce Type: new Abstract: Learning robot policies for tasks with sparse success signals is challenging when completion depends on coordinated actions, precise contact outcomes, or satisfying several conditions together. Intricate physical interactions with the world further complicate these requirements. Prior work using conventional reward shaping mechanisms provides dense feedback but local progress might not translate into eventual task completion. We present Signal Temporal Logic-guided Stein Variational Policy Gradient (STL-SVPG), a population-based method that uses smooth STL robustness as a trajectory-level training objective. Differentiating this objective through the dynamics assigns credit to policy actions according to their effect on the complete task specification, rather than local progress alone. We evaluate the approach on six quadcopter and manipulator tasks that involves event-triggered responses, strictly ordered behavior, responses within speci

arXiv:2609.31577v1 Announce Type: new Abstract: General purpose humanoids require locomotion controllers that are multi-skill, perceptive, dynamic, and robust enough to go anywhere humans can. In this work, we present a two layer locomotion architecture: (1) a perceptive flow matching motion generator plans whole body trajectories from raw depth images while a (2) perceptive tracking policy trained with control-guided RL follows these motions. Both policies are trained on a library of terrain consistent motion clips created with dynamically optimized human data which yields both accurate velocity tracking and terrain consistent references. Our central contribution is a simple yet effective off-policy RL fine tuning loop that improves the motion generator. A structured search method is used with the generator to gather data for advantage weighted regression. This off-policy loop is much more sample efficient than on-policy residual fine tuning and improves terrain consistency on unseen