Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912953718013952 |
|---|---|
| author | Xu, Weisheng Wu, Qiwei Zhang, Jiaxi Jing, Tan Li, Yangfan Fang, Yuetong Xiong, Jiaqi Wu, Kai Ou, Rong Xu, Renjing |
| author_facet | Xu, Weisheng Wu, Qiwei Zhang, Jiaxi Jing, Tan Li, Yangfan Fang, Yuetong Xiong, Jiaqi Wu, Kai Ou, Rong Xu, Renjing |
| contents | Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the performance ceiling of the trained control policies. Additionally, the method of acquiring high-quality data through professional motion capture systems is constrained by costs, making it difficult to achieve large-scale scalability. To address these issues, we propose a closed-loop automated motion data generation and iterative framework. It can generate high-quality motion data with rich action semantics, including martial arts, dance, combat, sports, gymnastics, and more. Furthermore, our framework enables difficulty iteration of policies and data through physical metrics and objective evaluations, allowing the trained tracker to break through its original difficulty limits. On the PHC single-primitive tracker, using only approximately 1/10 of the AMASS dataset size, the average failure rate on the test set (2201 clips) is reduced by 45% compared to the baseline. Finally, we conduct comprehensive ablation and comparative experiments to highlight the rationality and advantages of our framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21599 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control Xu, Weisheng Wu, Qiwei Zhang, Jiaxi Jing, Tan Li, Yangfan Fang, Yuetong Xiong, Jiaqi Wu, Kai Ou, Rong Xu, Renjing Robotics Computer Vision and Pattern Recognition Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the performance ceiling of the trained control policies. Additionally, the method of acquiring high-quality data through professional motion capture systems is constrained by costs, making it difficult to achieve large-scale scalability. To address these issues, we propose a closed-loop automated motion data generation and iterative framework. It can generate high-quality motion data with rich action semantics, including martial arts, dance, combat, sports, gymnastics, and more. Furthermore, our framework enables difficulty iteration of policies and data through physical metrics and objective evaluations, allowing the trained tracker to break through its original difficulty limits. On the PHC single-primitive tracker, using only approximately 1/10 of the AMASS dataset size, the average failure rate on the test set (2201 clips) is reduced by 45% compared to the baseline. Finally, we conduct comprehensive ablation and comparative experiments to highlight the rationality and advantages of our framework. |
| title | Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.21599 |