Hierarchical Equivariant Policy via Frame Transfer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915164210593792 |
|---|---|
| author | Zhao, Haibo Wang, Dian Zhu, Yizhe Zhu, Xupeng Howell, Owen Zhao, Linfeng Qian, Yaoyao Walters, Robin Platt, Robert |
| author_facet | Zhao, Haibo Wang, Dian Zhu, Yizhe Zhu, Xupeng Howell, Owen Zhao, Linfeng Qian, Yaoyao Walters, Robin Platt, Robert |
| contents | Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between these hierarchy levels remains underexplored, and existing hierarchical methods often ignore domain symmetry, resulting in the need for extensive demonstrations to achieve robust performance. To address these issues, we propose Hierarchical Equivariant Policy (HEP), a novel hierarchical policy framework. We propose a frame transfer interface for hierarchical policy learning, which uses the high-level agent's output as a coordinate frame for the low-level agent, providing a strong inductive bias while retaining flexibility. Additionally, we integrate domain symmetries into both levels and theoretically demonstrate the system's overall equivariance. HEP achieves state-of-the-art performance in complex robotic manipulation tasks, demonstrating significant improvements in both simulation and real-world settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Equivariant Policy via Frame Transfer Zhao, Haibo Wang, Dian Zhu, Yizhe Zhu, Xupeng Howell, Owen Zhao, Linfeng Qian, Yaoyao Walters, Robin Platt, Robert Robotics Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between these hierarchy levels remains underexplored, and existing hierarchical methods often ignore domain symmetry, resulting in the need for extensive demonstrations to achieve robust performance. To address these issues, we propose Hierarchical Equivariant Policy (HEP), a novel hierarchical policy framework. We propose a frame transfer interface for hierarchical policy learning, which uses the high-level agent's output as a coordinate frame for the low-level agent, providing a strong inductive bias while retaining flexibility. Additionally, we integrate domain symmetries into both levels and theoretically demonstrate the system's overall equivariance. HEP achieves state-of-the-art performance in complex robotic manipulation tasks, demonstrating significant improvements in both simulation and real-world settings. |
| title | Hierarchical Equivariant Policy via Frame Transfer |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.05728 |