JAEGER: Dual-Level Humanoid Whole-Body Controller
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_ | 1866916794750468096 |
|---|---|
| author | Ding, Ziluo Jiang, Haobin Wang, Yuxuan Sun, Zhenguo Zhang, Yu Niu, Xiaojie Yang, Ming Zeng, Weishuai Xu, Xinrun Lu, Zongqing |
| author_facet | Ding, Ziluo Jiang, Haobin Wang, Yuxuan Sun, Zhenguo Zhang, Yu Niu, Xiaojie Yang, Ming Zeng, Weishuai Xu, Xinrun Lu, Zongqing |
| contents | This paper presents JAEGER, a dual-level whole-body controller for humanoid robots that addresses the challenges of training a more robust and versatile policy. Unlike traditional single-controller approaches, JAEGER separates the control of the upper and lower bodies into two independent controllers, so that they can better focus on their distinct tasks. This separation alleviates the dimensionality curse and improves fault tolerance. JAEGER supports both root velocity tracking (coarse-grained control) and local joint angle tracking (fine-grained control), enabling versatile and stable movements. To train the controller, we utilize a human motion dataset (AMASS), retargeting human poses to humanoid poses through an efficient retargeting network, and employ a curriculum learning approach. This method performs supervised learning for initialization, followed by reinforcement learning for further exploration. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-art methods in both simulation and real environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06584 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JAEGER: Dual-Level Humanoid Whole-Body Controller Ding, Ziluo Jiang, Haobin Wang, Yuxuan Sun, Zhenguo Zhang, Yu Niu, Xiaojie Yang, Ming Zeng, Weishuai Xu, Xinrun Lu, Zongqing Robotics Artificial Intelligence This paper presents JAEGER, a dual-level whole-body controller for humanoid robots that addresses the challenges of training a more robust and versatile policy. Unlike traditional single-controller approaches, JAEGER separates the control of the upper and lower bodies into two independent controllers, so that they can better focus on their distinct tasks. This separation alleviates the dimensionality curse and improves fault tolerance. JAEGER supports both root velocity tracking (coarse-grained control) and local joint angle tracking (fine-grained control), enabling versatile and stable movements. To train the controller, we utilize a human motion dataset (AMASS), retargeting human poses to humanoid poses through an efficient retargeting network, and employ a curriculum learning approach. This method performs supervised learning for initialization, followed by reinforcement learning for further exploration. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-art methods in both simulation and real environments. |
| title | JAEGER: Dual-Level Humanoid Whole-Body Controller |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2505.06584 |