Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910184549384192 |
|---|---|
| author | Chen, Hongjin Zhang, Wei Li, Pengfei Ma, Shihao Ma, Ke Jin, Yujie Xu, Zijun Wang, Xiaohui Zheng, Yupeng Wang, Zining Zhao, Jieru Chen, Yilun Ding, Wenchao |
| author_facet | Chen, Hongjin Zhang, Wei Li, Pengfei Ma, Shihao Ma, Ke Jin, Yujie Xu, Zijun Wang, Xiaohui Zheng, Yupeng Wang, Zining Zhao, Jieru Chen, Yilun Ding, Wenchao |
| contents | Realizing interactive whole-body control for multi-humanoid systems is critical for unlocking complex collaborative capabilities in shared environments. Although recent advancements have significantly enhanced the agility of individual robots, bridging the gap to physically coupled multi-humanoid interaction remains challenging, primarily due to severe kinematic mismatches and complex contact dynamics. To address this, we introduce Rhythm, the first unified framework enabling real-world deployment of dual-humanoid systems for complex, physically plausible interactions. Our framework integrates three core components: (1) an Interaction-Aware Motion Retargeting (IAMR) module that generates feasible humanoid interaction references from human data; (2) an Interaction-Guided Reinforcement Learning (IGRL) policy that masters coupled dynamics via graph-based rewards; and (3) a real-world deployment system that enables robust transfer of dual-humanoid interaction. Extensive experiments on physical Unitree G1 robots demonstrate that our framework achieves robust interactive whole-body control, successfully transferring diverse behaviors such as hugging and dancing from simulation to reality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02856 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids Chen, Hongjin Zhang, Wei Li, Pengfei Ma, Shihao Ma, Ke Jin, Yujie Xu, Zijun Wang, Xiaohui Zheng, Yupeng Wang, Zining Zhao, Jieru Chen, Yilun Ding, Wenchao Robotics Realizing interactive whole-body control for multi-humanoid systems is critical for unlocking complex collaborative capabilities in shared environments. Although recent advancements have significantly enhanced the agility of individual robots, bridging the gap to physically coupled multi-humanoid interaction remains challenging, primarily due to severe kinematic mismatches and complex contact dynamics. To address this, we introduce Rhythm, the first unified framework enabling real-world deployment of dual-humanoid systems for complex, physically plausible interactions. Our framework integrates three core components: (1) an Interaction-Aware Motion Retargeting (IAMR) module that generates feasible humanoid interaction references from human data; (2) an Interaction-Guided Reinforcement Learning (IGRL) policy that masters coupled dynamics via graph-based rewards; and (3) a real-world deployment system that enables robust transfer of dual-humanoid interaction. Extensive experiments on physical Unitree G1 robots demonstrate that our framework achieves robust interactive whole-body control, successfully transferring diverse behaviors such as hugging and dancing from simulation to reality. |
| title | Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.02856 |