KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
By: Weiji Xie , Jinrui Han , Jiakun Zheng and more
Potential Business Impact:
Robots learn to copy fast, tricky human moves.
Humanoid robots are promising to acquire various skills by imitating human behaviors. However, existing algorithms are only capable of tracking smooth, low-speed human motions, even with delicate reward and curriculum design. This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing through multi-steps motion processing and adaptive motion tracking. For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints to the maximum extent. For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance based on the current tracking error, creating an adaptive curriculum mechanism. We further construct an asymmetric actor-critic framework for policy training. In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions. Our method achieves significantly lower tracking errors than existing approaches and is successfully deployed on the Unitree G1 robot, demonstrating stable and expressive behaviors. The project page is https://kungfu-bot.github.io.
Similar Papers
KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
Robotics
Robots learn many new body movements easily.
A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot
Robotics
Robots copy human moves, staying balanced.
Whole-Body Control Framework for Humanoid Robots with Heavy Limbs: A Model-Based Approach
Robotics
Helps robots with heavy legs walk better.