General Humanoid Whole-Body Control via Pretraining and Fast Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912900330815488 |
|---|---|
| author | Wang, Zepeng Wang, Jiangxing Yao, Shiqing Zhang, Yu Ding, Ziluo Yang, Ming Wang, Yuxuan Jiang, Haobin Ma, Chao Shi, Xiaochuan Lu, Zongqing |
| author_facet | Wang, Zepeng Wang, Jiangxing Yao, Shiqing Zhang, Yu Ding, Ziluo Yang, Ming Wang, Yuxuan Jiang, Haobin Ma, Chao Shi, Xiaochuan Lu, Zongqing |
| contents | Learning a general whole-body controller for humanoid robots remains challenging due to the diversity of motion distributions, the difficulty of fast adaptation, and the need for robust balance in high-dynamic scenarios. Existing approaches often require task-specific training or suffer from performance degradation when adapting to new motions. In this paper, we present FAST, a general humanoid whole-body control framework that enables Fast Adaptation and Stable Motion Tracking. FAST introduces Parseval-Guided Residual Policy Adaptation, which learns a lightweight delta action policy under orthogonality and KL constraints, enabling efficient adaptation to out-of-distribution motions while mitigating catastrophic forgetting. To further improve physical robustness, we propose Center-of-Mass-Aware Control, which incorporates CoM-related observations and objectives to enhance balance when tracking challenging reference motions. Extensive experiments in simulation and real-world deployment demonstrate that FAST consistently outperforms state-of-the-art baselines in robustness, adaptation efficiency, and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11929 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | General Humanoid Whole-Body Control via Pretraining and Fast Adaptation Wang, Zepeng Wang, Jiangxing Yao, Shiqing Zhang, Yu Ding, Ziluo Yang, Ming Wang, Yuxuan Jiang, Haobin Ma, Chao Shi, Xiaochuan Lu, Zongqing Robotics Learning a general whole-body controller for humanoid robots remains challenging due to the diversity of motion distributions, the difficulty of fast adaptation, and the need for robust balance in high-dynamic scenarios. Existing approaches often require task-specific training or suffer from performance degradation when adapting to new motions. In this paper, we present FAST, a general humanoid whole-body control framework that enables Fast Adaptation and Stable Motion Tracking. FAST introduces Parseval-Guided Residual Policy Adaptation, which learns a lightweight delta action policy under orthogonality and KL constraints, enabling efficient adaptation to out-of-distribution motions while mitigating catastrophic forgetting. To further improve physical robustness, we propose Center-of-Mass-Aware Control, which incorporates CoM-related observations and objectives to enhance balance when tracking challenging reference motions. Extensive experiments in simulation and real-world deployment demonstrate that FAST consistently outperforms state-of-the-art baselines in robustness, adaptation efficiency, and generalization. |
| title | General Humanoid Whole-Body Control via Pretraining and Fast Adaptation |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.11929 |