Embracing Bulky Objects with Humanoid Robots: Whole-Body Manipulation with Reinforcement Learning
Chunxin ZHENG, Kai Chen, Zhihai Bi, Yulin Li, Liang Pan, Jinni ZHOU, Haoang Li, Jun Ma
AI summary
Problem
Traditional end-effector grasping is limited by stability and payload constraints when handling bulky objects. Existing whole-body manipulation methods struggle with high DOF complexity and precise geometric perception during contact-rich tasks.
Approach
The authors employ a teacher-student RL architecture to distill human motion data into a prior, combined with a neural signed distance field (NSDF) for accurate spatial awareness of the robot's body relative to objects.
Key results
- First RL framework for active whole-body embracing of bulky objects
- Accelerated policy convergence via distilled human motion priors
- Improved contact awareness and robustness using NSDF representation
- Successful sim-to-real transfer demonstrated in real-world experiments
Why it matters
This enhances the payload capacity and robustness of humanoid robots for industrial and home service tasks involving large items.
Abstract
Whole-body manipulation (WBM) for humanoid robots presents a promising approach for executing embracing tasks involving bulky objects, where traditional grasping relying on end-effectors only remains limited in such scenarios due to inherent stability and payload constraints. This paper intro- duces a reinforcement learning framework that integrates a pre- trained human motion prior with a neural signed distance field (NSDF) representation to achieve robust whole-body embracing. Our method leverages a teacher-student architecture to distill large-scale human motion data, generating kinematically natu- ral and physically feasible whole-body motion patterns. This fa- cilitates coordinated control across the arms and torso, enabling stable multi-contact interactions that enhance the robustness in manipulation and also the load capacity. The embedded NSDF further provides accurate and continuous geometric perception, improving contact awareness throughout long- horizon tasks. We thoroughly evaluate the approach through comprehensive simulations and real-world experiments. The results demonstrate improved adaptability to diverse shapes and sizes of objects and also successful sim-to-real transfer. These indicate that the proposed framework offers an effec- tive and practical solution for multi-contact and long-horizon WBM tasks of humanoid robots. The open-source project can be found at https://github.com/Chunx1nZHENG/ Embracing-Bulky-Objects-with-Humanoid-Robots.