Score: 0

Learning Robust Motion Skills via Critical Adversarial Attacks for Humanoid Robots

Published: July 11, 2025 | arXiv ID: 2507.08303v1

By: Yang Zhang , Zhanxiang Cao , Buqing Nie and more

Potential Business Impact:

Makes robots walk better on tricky ground.

Business Areas:
Robotics Hardware, Science and Engineering, Software

Humanoid robots show significant potential in daily tasks. However, reinforcement learning-based motion policies often suffer from robustness degradation due to the sim-to-real dynamics gap, thereby affecting the agility of real robots. In this work, we propose a novel robust adversarial training paradigm designed to enhance the robustness of humanoid motion policies in real worlds. The paradigm introduces a learnable adversarial attack network that precisely identifies vulnerabilities in motion policies and applies targeted perturbations, forcing the motion policy to enhance its robustness against perturbations through dynamic adversarial training. We conduct experiments on the Unitree G1 humanoid robot for both perceptive locomotion and whole-body control tasks. The results demonstrate that our proposed method significantly enhances the robot's motion robustness in real world environments, enabling successful traversal of challenging terrains and highly agile whole-body trajectory tracking.

Country of Origin
🇨🇳 China

Page Count
10 pages

Category
Computer Science:
Robotics