Dexterous Teleoperation of 20-DoF ByteDexter Hand via Human Motion Retargeting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911038525407232 |
|---|---|
| author | Wen, Ruoshi Zhang, Jiajun Chen, Guangzeng Cui, Zhongren Du, Min Gou, Yang Han, Zhigang Hu, Junkai Huang, Liqun Niu, Hao Xu, Wei Zhang, Haoxiang Zhu, Zhengming Li, Hang Ren, Zeyu |
| author_facet | Wen, Ruoshi Zhang, Jiajun Chen, Guangzeng Cui, Zhongren Du, Min Gou, Yang Han, Zhigang Hu, Junkai Huang, Liqun Niu, Hao Xu, Wei Zhang, Haoxiang Zhu, Zhengming Li, Hang Ren, Zeyu |
| contents | Replicating human--level dexterity remains a fundamental robotics challenge, requiring integrated solutions from mechatronic design to the control of high degree--of--freedom (DoF) robotic hands. While imitation learning shows promise in transferring human dexterity to robots, the efficacy of trained policies relies on the quality of human demonstration data. We bridge this gap with a hand--arm teleoperation system featuring: (1) a 20--DoF linkage--driven anthropomorphic robotic hand for biomimetic dexterity, and (2) an optimization--based motion retargeting for real--time, high--fidelity reproduction of intricate human hand motions and seamless hand--arm coordination. We validate the system via extensive empirical evaluations, including dexterous in-hand manipulation tasks and a long--horizon task requiring the organization of a cluttered makeup table randomly populated with nine objects. Experimental results demonstrate its intuitive teleoperation interface with real--time control and the ability to generate high--quality demonstration data. Please refer to the accompanying video for further details. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03227 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dexterous Teleoperation of 20-DoF ByteDexter Hand via Human Motion Retargeting Wen, Ruoshi Zhang, Jiajun Chen, Guangzeng Cui, Zhongren Du, Min Gou, Yang Han, Zhigang Hu, Junkai Huang, Liqun Niu, Hao Xu, Wei Zhang, Haoxiang Zhu, Zhengming Li, Hang Ren, Zeyu Robotics Replicating human--level dexterity remains a fundamental robotics challenge, requiring integrated solutions from mechatronic design to the control of high degree--of--freedom (DoF) robotic hands. While imitation learning shows promise in transferring human dexterity to robots, the efficacy of trained policies relies on the quality of human demonstration data. We bridge this gap with a hand--arm teleoperation system featuring: (1) a 20--DoF linkage--driven anthropomorphic robotic hand for biomimetic dexterity, and (2) an optimization--based motion retargeting for real--time, high--fidelity reproduction of intricate human hand motions and seamless hand--arm coordination. We validate the system via extensive empirical evaluations, including dexterous in-hand manipulation tasks and a long--horizon task requiring the organization of a cluttered makeup table randomly populated with nine objects. Experimental results demonstrate its intuitive teleoperation interface with real--time control and the ability to generate high--quality demonstration data. Please refer to the accompanying video for further details. |
| title | Dexterous Teleoperation of 20-DoF ByteDexter Hand via Human Motion Retargeting |
| topic | Robotics |
| url | https://arxiv.org/abs/2507.03227 |