CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914317536854016 |
|---|---|
| author | Chen, Sirui Cao, Zi-ang Luo, Zhengyi Castañeda, Fernando Li, Chenran Wang, Tingwu Yuan, Ye Fan, Linxi "Jim" Liu, C. Karen Zhu, Yuke |
| author_facet | Chen, Sirui Cao, Zi-ang Luo, Zhengyi Castañeda, Fernando Li, Chenran Wang, Tingwu Yuan, Ye Fan, Linxi "Jim" Liu, C. Karen Zhu, Yuke |
| contents | Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14689 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation Chen, Sirui Cao, Zi-ang Luo, Zhengyi Castañeda, Fernando Li, Chenran Wang, Tingwu Yuan, Ye Fan, Linxi "Jim" Liu, C. Karen Zhu, Yuke Robotics Machine Learning Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening. |
| title | CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2512.14689 |