RoboSpan, a high-DoF whole-body teleoperation and demonstration platform, and the Hierarchical Modular Framework (HMF) for learning modular coordination policies are presented, with experiments demonstrating that the proposed method achieves over 20\% higher task success rate than mainstream baselines across a range of long-horizon whole-body tasks.
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.
A unified whole-body controller trained with reinforcement learning that directly maps 6-DoF end-effector targets to coordinated actions for the bipedal base and robotic arm, providing a common end-effector interface for diverse manipulation tasks.
Experimental results demonstrate that a single policy enables a Unitree G1 humanoid to complete the full task using only onboard depth sensing and proprioception, while generalizing robustly across task variations and transferring effectively from simulation to reality.
Ze-Jie Tian, Rui-Bing Hou, Bin Ma et al.· arXiv.org· 0 citations
Changing a humanoid robot's manipulation policy should not require retraining the controller that maintains the robot's balance. This study introduces DUET, a decoupled execution framework that enables locomotion and manipulation controllers to operate simultaneously by combining their commands only at the robot interf...
Kapalik Khanal, Biswash Khatiwada, S. Afrifa et al.· 0 citations
Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-body mobile manipulation, where long horizons amplify compounding errors and coordinated arm, torso, and base motion makes exhaustive demonstration coverage imp...
Wen-Si Ai, Christopher Luey, Karthik Dharmarajan et al.· 0 citations
This paper aims to develop a hand–eye–body coordination (HEBC) framework for mobile manipulation in modular manufacturing, addressing the coupling of workspace perception, task planning, target visibility and whole-body motion.
The proposed HEBC framework integrates active workspace exploration, manipulabili...
Yu-Lin Zhang, Tuan-Jie Li, Li-Xiang Ban et al.· Industrial robot· 0 citations
This work presents a gated residual coordination framework that keeps both modules frozen and applies bounded corrections to their outputs, and describes the contributions of reward gating, adaptive correction authority, and separate body and hand correction heads.