News & Research

arXiv:2511.22354v2 Announce Type: replace Abstract: This paper introduces CoMuRoS (Collaborative Multi-Robot System), a generalizable hierarchical architecture for heterogeneous robot teams that unifies centralized deliberation with decentralized execution, and supports event-driven replanning. A Task Manager LLM interprets natural-language goals, classifies tasks, and allocates subtasks using static rules plus dynamic contexts (task, history, robot and task status, and events).Each robot runs a local LLM that composes executable Python code from primitive skills (ROS2 nodes, policies), while onboard perception (VLMs/image processing) continuously monitors events and classifies them into relevant or irrelevant to the task. Task failures or user intent changes trigger replanning, allowing robots to assist teammates, resume tasks, or request human help. Hardware studies demonstrate autonomous recovery from disruptive events, filtering of irrelevant distractions, and tightly coordinated t

arXiv:2511.21886v2 Announce Type: replace Abstract: Multi-Agent Path Finding (MAPF) studies how to coordinate multiple agents to reach their goals without collisions and underpins a range of large-scale robotic systems, including automated warehousing and manufacturing. Recent advances enable MAPF solvers to compute high-quality plans for hundreds of agents. However, these plans are generated using simplified robot models with discretized time and action spaces. When they are deployed in physical systems, heterogeneous robot dynamics, asynchronous interactions, communication delays, and other real-world factors can lead to substantial deviations from planned performance. We bridge the gap between discrete planning and real-world execution through ExecTimeNet, a learned world model of MAPF execution that predicts how a discrete MAPF solution will unfold on physical robots, mapping each discrete action to its realized execution state, including its wall-clock completion time and the kino

arXiv:2511.20906v2 Announce Type: replace Abstract: Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task complexity, leading to computational inefficiency for simple subtasks while potentially underperforming on challenging ones. To address these issues, we introduce Difficulty-Aware Stochastic Interpolant Policy (DA-SIP), a framework that enables robotic controllers to adaptively adjust their integration horizon in real time based on task difficulty. Our approach employs a difficulty classifier that analyzes observations to dynamically select the step budget, the optimal solver variant, and ODE/SDE integration at each control cycle. DA-SIP builds upon the stochastic interpolant formulation to provide a unified framework that unlocks diverse training and inference configurations for diffusion- and flow

arXiv:2510.22126v3 Announce Type: replace Abstract: Despite recent advances in Unmanned Underwater Vehicle (UUV) attitude control, existing methods still struggle with generalizability, robustness to real-world disturbances, and efficient deployment. To address the above challenges, this paper presents EasyUUV, a Large Language Model (LLM)-enhanced, platform-agnostic, and lightweight simulation-to-reality reinforcement learning (RL) framework for robust attitude control of UUVs. EasyUUV combines parallelized RL training with a hybrid control architecture, where a learned policy outputs high-level attitude corrections executed by an adaptive S-Surface controller. A multimodal LLM is further integrated to adaptively tune controller parameters at runtime using visual and textual feedback, enabling training-free adaptation to unmodeled dynamics. Also, we have developed a low-cost 6-DoF UUV platform and applied an RL policy trained through efficient parallelized simulation. Extensive simula

arXiv:2510.17525v3 Announce Type: replace Abstract: Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on simplified 2D crowd navigation and fail to account for the full complexity of human body dynamics beyond root motion. We present HumanHalo, a Model Predictive Control (MPC) framework for 3D Micro Air Vehicle (MAV) navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel twist to reachability-based safety formulation that constrains only the initial control input for safety while modeling its effects over the entire planning horizon, enabling safe yet efficient navigation. We validate HumanHalo in both simulated experiments using real human trajectories and in the real-world, demonstrating its effectiveness across tasks ranging from goal-directed navigation to visual servoing for huma

arXiv:2510.10759v2 Announce Type: replace Abstract: Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address both issues by proposing Reward-Oriented Gains via Embodied Regulation (ROGER), which adapts reward-weighting gains online based on penalties received throughout the embodied interaction process. The ratio between the positive reward (primary reward) and negative reward (penalty) gains is automatically reduced as the learning approaches the constraint thresholds to avoid violation. Conversely, the ratio is increased when learning is in safe states to prioritize performance. With a 60-kg quadruped robot, ROGER achieved near-zero constraint violation throughout multiple learning trials. It also achieved up to 50% more primary reward than the equivalent state-of-the-art techniques. In MuJoCo continuous

arXiv:2510.02469v2 Announce Type: replace Abstract: Driving scene manipulation using real-world sensor data has emerged as a promising alternative to traditional driving simulators. Despite advances in language control and neural scene representations, existing methods treat grounding, editing, and simulation as loosely connected stages, relying on heuristic object localization, manual guidance, and single-agent validation, thereby constraining semantic expressiveness and hindering scalable, reactive scenario generation. We introduce SIMSplat, a driving scene editor built on scene-graph-based 4D Gaussian Splatting augmented with language-aligned features. By embedding appearance, motion, and location semantics directly into Gaussian scene-graph nodes, SIMSplat makes reconstructed scenes queryable through free-form natural language, bridging language understanding to object-level editing and multi-agent simulation within a single framework. Building on this language-grounded scene graph

arXiv:2509.23650v3 Announce Type: replace Abstract: Vision-based locomotion has shown great promise in enabling legged robots to perceive and adapt to complex environments. However, visual information is inherently fragile, being vulnerable to occlusions, reflections, and lighting changes, which often cause instability in locomotion. Inspired by animal sensorimotor integration, we propose KiVi, a Kinesthetic-Visuospatial integration framework, where kinesthetics encodes proprioceptive sensing of body motion and visuospatial reasoning captures visual perception of surrounding terrain. Specifically, KiVi separates these pathways, leveraging proprioception as a stable backbone while selectively incorporating vision for terrain awareness and obstacle avoidance. This modality-balanced, yet integrative design, combined with memory-enhanced attention, allows the robot to robustly interpret visual cues while maintaining fallback stability through proprioception. Extensive experiments show that

arXiv:2509.18671v2 Announce Type: replace Abstract: Determining where to execute the manipulation policy is a fundamental challenge in mobile manipulation. Most approaches have formulated this as a geometric search problem, prioritizing physical reachability. However, given the high sensitivity of modern learning-based manipulation policies, geometric criteria alone are insufficient. Optimal performance requires base positioning that is aware of the policy's preference. While recent works have attempted to address this, they remain limited in practicality due to reliance on pre-built scene reconstruction and slow inference. In this work, we introduce N2M that systematically reformulates the approach to base positioning problem, naturally overcoming limitations of previous methods. Our key insight is that policy preferences are inherent to the local scene structure and can be effectively learned from the policy rollouts. Technically, we propose a novel viewpoint augmentation strategy th

arXiv:2509.17390v3 Announce Type: replace Abstract: While 3D Gaussian Splatting (3DGS) has emerged as a strong representation for photorealistic rendering, its vast ecosystem of assets remains difficult to use for high-performance LiDAR simulation, a critical tool for robotics and autonomous driving. We present \textbf{FGGS-LiDAR}, a geometry-first framework that bridges this gap in a plug-and-play manner. Our method converts pretrained 3DGS assets into watertight meshes directly from Gaussian parameters, without requiring LiDAR-specific supervision or architectural alterations, via volumetric discretization and Truncated Signed Distance Field (TSDF) extraction. We pair this with a GPU-accelerated ray-casting module that simulates LiDAR returns at over 500 FPS and supports batched multi-environment simulation with up to 4096 environments. In large-scale parallel settings, FGGS-LiDAR achieves an order-of-magnitude lower LiDAR simulation latency than Isaac Sim. We validate FGGS-LiDAR on

arXiv:2509.17125v2 Announce Type: replace Abstract: Relational object rearrangement (ROR) tasks (e.g., insert flower to vase) require a robot to manipulate objects with precise semantic and geometric reasoning. Existing approaches either rely on pre-collected demonstrations that struggle to capture complex geometric constraints or generate goal-state observations to capture semantic and geometric knowledge, but fail to explicitly couple object transformation with action prediction, resulting in errors due to generative noise. To address these limitations, we propose Imagine2Act, a 3D imitation-learning framework that incorporates semantic and geometric constraints of objects into policy learning to tackle high-precision manipulation tasks. We first generate imagined goal images conditioned on language instructions and reconstruct corresponding 3D point clouds to provide robust semantic and geometric priors. These imagined goal point clouds serve as additional inputs to the policy model

arXiv:2509.17053v2 Announce Type: replace Abstract: Many contact-rich manipulation tasks require precise force regulation. However, most imitation learning (IL) policies remain position-centric and lack explicit force awareness, and adding force/torque sensors to collaborative robot arms is often costly and requires additional hardware design. To overcome these issues, we propose FILIC, a Force-guided Imitation Learning framework with impedance torque control. FILIC integrates a Transformer-based IL policy with an impedance controller in a dual-loop structure, enabling compliant force-informed, force-executed manipulation. For robots without force/torque sensors, we introduce a cost-effective end-effector force estimator using joint torque measurements through analytical Jacobian-based inversion while compensating with model-predicted torques from a digital twin. Experiments show that FILIC significantly outperforms vision-only and joint-torque-based methods, achieving safer, more comp

arXiv:2509.14641v2 Announce Type: replace Abstract: Dense 3D convolutions provide high accuracy for perception but are too computationally expensive for real-time robotic systems. Existing tri-plane methods rely on 2D image features with interpolation, point-wise queries, and implicit MLPs, which makes them computationally heavy and unsuitable for embedded 3D inference. As an alternative, we propose TriLift, a novel interpolation-free tri-plane lifting and volumetric fusion framework that directly projects 3D voxels into plane features and reconstructs a feature volume through broadcast and summation. This shifts nonlinearity to 2D convolutions, reducing complexity while remaining fully parallelizable. To mitigate spatial information loss inherent in projections, we incorporate a lightweight adaptive positional encoding module that helps bridge the spatial information gap, dynamically recovering fine geometric details with negligible overhead. To capture global context, we add a low-re

arXiv:2507.12744v4 Announce Type: replace Abstract: Detecting deformable linear objects (DLOs), such as floor cables, is essential for safe mobile robot navigation but remains challenging due to oblique viewpoints, thin structures, and limited edge-device resources. Existing DLO segmentation methods are primarily designed for manipulator platforms with fixed top-down views and often require heavy models, limiting their deployment on mobile robots. We formulate a cross-view DLO segmentation problem, where models trained on manipulator-view data must generalize to mobile robot perspectives. To address this, we propose ASC-SW, a lightweight and geometry-aware segmentation framework. The core network, ASCNet, introduces Atrous Strip Convolution, combining directional strip filtering with dilated receptive fields to enhance sensitivity to elongated structures at low computational cost. An Atrous Strip Convolution Spatial Pyramid Pooling module enables multi-scale anisotropic feature aggrega

arXiv:2507.08262v2 Announce Type: replace Abstract: The spatial information inherent in 3D point clouds is crucial for robotic manipulation. However, existing 3D pre-training methods face a fundamental trade-off: Masked Autoencoding (MAE) excels at capturing spatial-geometric features but lacks semantics, whereas contrastive learning, while able to distill semantics from 2D foundation models, is ill-suited for the fine-grained details required for manipulation tasks. To address these challenges, we propose CLAR, a novel 3D pre-training framework that synergizes global understanding with fine-grained local alignment. Our framework unifies MAE with global cross-modal contrastive learning to integrate robust spatial awareness with rich semantic understanding. To enhance its focus on fine-grained details, at the local level, we introduce an adaptive alignment mechanism that leverages deformable attention to force precise correspondences between local 3D geometry and 2D visual features, the