EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation

TL;DR

This paper presents a reinforcement learning framework for humanoid robots to imitate human upper-body motions while maintaining stability, using a novel Executable Motion Prior to ensure safety and robustness.

Contribution

It introduces an Executable Motion Prior module that adjusts target motions for stability, and a retargeting network for large-scale motion dataset generation, advancing humanoid motion imitation.

Findings

Framework achieves stable upper-body motion imitation in simulation.

Real-world tests confirm practical applicability and robustness.

Motion adjustments improve stability with minimal amplitude change.

Abstract

To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the stability of the entire body. Thus we introduce a reinforcement learning based framework for humanoid robots to imitate human upper-body motions while maintaining overall stability. Our approach begins with designing a retargeting network that generates a large-scale upper-body motion dataset for training the reinforcement learning (RL) policy, which enables the humanoid robot to track upper-body motion targets, employing domain randomization for enhanced robustness. To avoid exceeding the robot's execution capability and ensure safety and stability, we propose an Executable Motion Prior (EMP) module, which adjusts the input target movements based on the robot's current state. This adjustment improves standing stability while minimizing changes to motion amplitude. We evaluate our framework through simulation and real-world tests, demonstrating its practical applicability.