HuB: Learning Extreme Humanoid Balance
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_ | 1866918126244855808 |
|---|---|
| author | Zhang, Tong Zheng, Boyuan Nai, Ruiqian Hu, Yingdong Wang, Yen-Jen Chen, Geng Lin, Fanqi Li, Jiongye Hong, Chuye Sreenath, Koushil Gao, Yang |
| author_facet | Zhang, Tong Zheng, Boyuan Nai, Ruiqian Hu, Yingdong Wang, Yen-Jen Chen, Geng Lin, Fanqi Li, Jiongye Hong, Chuye Sreenath, Koushil Gao, Yang |
| contents | The human body demonstrates exceptional motor capabilities-such as standing steadily on one foot or performing a high kick with the leg raised over 1.5 meters-both requiring precise balance control. While recent research on humanoid control has leveraged reinforcement learning to track human motions for skill acquisition, applying this paradigm to balance-intensive tasks remains challenging. In this work, we identify three key obstacles: instability from reference motion errors, learning difficulties due to morphological mismatch, and the sim-to-real gap caused by sensor noise and unmodeled dynamics. To address these challenges, we propose HuB (Humanoid Balance), a unified framework that integrates reference motion refinement, balance-aware policy learning, and sim-to-real robustness training, with each component targeting a specific challenge. We validate our approach on the Unitree G1 humanoid robot across challenging quasi-static balance tasks, including extreme single-legged poses such as Swallow Balance and Bruce Lee's Kick. Our policy remains stable even under strong physical disturbances-such as a forceful soccer strike-while baseline methods consistently fail to complete these tasks. Project website: https://hub-robot.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07294 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HuB: Learning Extreme Humanoid Balance Zhang, Tong Zheng, Boyuan Nai, Ruiqian Hu, Yingdong Wang, Yen-Jen Chen, Geng Lin, Fanqi Li, Jiongye Hong, Chuye Sreenath, Koushil Gao, Yang Robotics Artificial Intelligence Machine Learning Systems and Control The human body demonstrates exceptional motor capabilities-such as standing steadily on one foot or performing a high kick with the leg raised over 1.5 meters-both requiring precise balance control. While recent research on humanoid control has leveraged reinforcement learning to track human motions for skill acquisition, applying this paradigm to balance-intensive tasks remains challenging. In this work, we identify three key obstacles: instability from reference motion errors, learning difficulties due to morphological mismatch, and the sim-to-real gap caused by sensor noise and unmodeled dynamics. To address these challenges, we propose HuB (Humanoid Balance), a unified framework that integrates reference motion refinement, balance-aware policy learning, and sim-to-real robustness training, with each component targeting a specific challenge. We validate our approach on the Unitree G1 humanoid robot across challenging quasi-static balance tasks, including extreme single-legged poses such as Swallow Balance and Bruce Lee's Kick. Our policy remains stable even under strong physical disturbances-such as a forceful soccer strike-while baseline methods consistently fail to complete these tasks. Project website: https://hub-robot.github.io |
| title | HuB: Learning Extreme Humanoid Balance |
| topic | Robotics Artificial Intelligence Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2505.07294 |