KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915578326810624 |
|---|---|
| author | Xie, Weiji Han, Jinrui Zheng, Jiakun Li, Huanyu Liu, Xinzhe Shi, Jiyuan Zhang, Weinan Bai, Chenjia Li, Xuelong |
| author_facet | Xie, Weiji Han, Jinrui Zheng, Jiakun Li, Huanyu Liu, Xinzhe Shi, Jiyuan Zhang, Weinan Bai, Chenjia Li, Xuelong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills Xie, Weiji Han, Jinrui Zheng, Jiakun Li, Huanyu Liu, Xinzhe Shi, Jiyuan Zhang, Weinan Bai, Chenjia Li, Xuelong Robotics Artificial Intelligence 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. |
| title | KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2506.12851 |