Dexterous Functional Pre-Grasp Manipulation with Diffusion Policy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917657937182720 |
|---|---|
| author | Wu, Tianhao Gan, Yunchong Wu, Mingdong Cheng, Jingbo Yang, Yaodong Zhu, Yixin Dong, Hao |
| author_facet | Wu, Tianhao Gan, Yunchong Wu, Mingdong Cheng, Jingbo Yang, Yaodong Zhu, Yixin Dong, Hao |
| contents | In real-world scenarios, objects often require repositioning and reorientation before they can be grasped, a process known as pre-grasp manipulation. Learning universal dexterous functional pre-grasp manipulation requires precise control over the relative position, orientation, and contact between the hand and object while generalizing to diverse dynamic scenarios with varying objects and goal poses. To address this challenge, we propose a teacher-student learning approach that utilizes a novel mutual reward, incentivizing agents to optimize three key criteria jointly. Additionally, we introduce a pipeline that employs a mixture-of-experts strategy to learn diverse manipulation policies, followed by a diffusion policy to capture complex action distributions from these experts. Our method achieves a success rate of 72.6\% across more than 30 object categories by leveraging extrinsic dexterity and adjusting from feedback. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12421 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dexterous Functional Pre-Grasp Manipulation with Diffusion Policy Wu, Tianhao Gan, Yunchong Wu, Mingdong Cheng, Jingbo Yang, Yaodong Zhu, Yixin Dong, Hao Robotics In real-world scenarios, objects often require repositioning and reorientation before they can be grasped, a process known as pre-grasp manipulation. Learning universal dexterous functional pre-grasp manipulation requires precise control over the relative position, orientation, and contact between the hand and object while generalizing to diverse dynamic scenarios with varying objects and goal poses. To address this challenge, we propose a teacher-student learning approach that utilizes a novel mutual reward, incentivizing agents to optimize three key criteria jointly. Additionally, we introduce a pipeline that employs a mixture-of-experts strategy to learn diverse manipulation policies, followed by a diffusion policy to capture complex action distributions from these experts. Our method achieves a success rate of 72.6\% across more than 30 object categories by leveraging extrinsic dexterity and adjusting from feedback. |
| title | Dexterous Functional Pre-Grasp Manipulation with Diffusion Policy |
| topic | Robotics |
| url | https://arxiv.org/abs/2403.12421 |