RoboSpan enables better coordination for whole-body robot tasks
RoboSpan: Learning Modular Coordination Policies for High-DoF Whole-Body Mobile Manipulation with Teleoperation
Robotics
Summary
Robots that move their whole body to complete tasks face challenges because their legs, arms, and hands all need to work together smoothly. The authors created RoboSpan, a system that breaks down these complex movements into smaller parts and uses a special method to coordinate them. Their approach also includes touch sensors on the robot’s hands to help with delicate tasks. Tests show RoboSpan helps robots do complicated, multi-step jobs more successfully and with better control.
What this means in practice
- •For robotic automation teams: Control mobile robots with complex arms and hands to execute multi-stage manipulation tasks accurately over time.
- •For industrial robotics operators: Use tactile feedback integrated into robot hands for improved handling of objects in contact-rich environments.
Authors
Keqiang Ren, Xuecheng Ye, Hanyu Liu, Zhihua Wang, Tao Jian, Yunsheng Ma, Jiayi Wen, Xinran Li, Zhigong Song
Abstract
Whole-body mobile manipulation suffers from two fundamental challenges: inherent motion heterogeneity across locomotion, arm, and hand modules, and progressive error accumulation over long-horizon multi-stage tasks. Existing teleoperation platforms also lack integrated dexterous tactile sensing to support coordinated whole-body decision-making. This paper presents RoboSpan, a high-DoF whole-body teleoperation and demonstration platform, and the Hierarchical Modular Framework (HMF) for learning modular coordination policies. HMF functionally decouples the 29-DoF action space into fine hand manipulation, arm pose adjustment, and mobile-base spatial configuration branches, and introduces the Coordinated Modular Embodied Transformer (COMET) with inter-modular cross-attention to enable dynamic information exchange and action coordination. Vision-language model driven hierarchical task decomposition structurally suppresses temporal error propagation, while a full-palm 2D tactile representation encodes distributed contact signals for cross-module tactile empowerment. Experiments on a physical 29-DoF robot demonstrate that the proposed method achieves over 20\% higher task success rate than mainstream baselines across a range of long-horizon whole-body tasks, markedly improving stability and robustness in contact-rich manipulation.