Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand
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_ | 1866909511742128128 |
|---|---|
| author | Bai, Fengshuo Li, Yu Chu, Jie Chou, Tawei Zhu, Runchuan Wen, Ying Yang, Yaodong Chen, Yuanpei |
| author_facet | Bai, Fengshuo Li, Yu Chu, Jie Chou, Tawei Zhu, Runchuan Wen, Ying Yang, Yaodong Chen, Yuanpei |
| contents | Retrieving objects buried beneath multiple objects is not only challenging but also time-consuming. Performing manipulation in such environments presents significant difficulty due to complex contact relationships. Existing methods typically address this task by sequentially grasping and removing each occluding object, resulting in lengthy execution times and requiring impractical grasping capabilities for every occluding object. In this paper, we present a dexterous arm-hand system for efficient object retrieval in multi-object stacked environments. Our approach leverages large-scale parallel reinforcement learning within diverse and carefully designed cluttered environments to train policies. These policies demonstrate emergent manipulation skills (e.g., pushing, stirring, and poking) that efficiently clear occluding objects to expose sufficient surface area of the target object. We conduct extensive evaluations across a set of over 10 household objects in diverse clutter configurations, demonstrating superior retrieval performance and efficiency for both trained and unseen objects. Furthermore, we successfully transfer the learned policies to a real-world dexterous multi-fingered robot system, validating their practical applicability in real-world scenarios. Videos can be found on our project website https://ChangWinde.github.io/RetrDex. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand Bai, Fengshuo Li, Yu Chu, Jie Chou, Tawei Zhu, Runchuan Wen, Ying Yang, Yaodong Chen, Yuanpei Robotics Retrieving objects buried beneath multiple objects is not only challenging but also time-consuming. Performing manipulation in such environments presents significant difficulty due to complex contact relationships. Existing methods typically address this task by sequentially grasping and removing each occluding object, resulting in lengthy execution times and requiring impractical grasping capabilities for every occluding object. In this paper, we present a dexterous arm-hand system for efficient object retrieval in multi-object stacked environments. Our approach leverages large-scale parallel reinforcement learning within diverse and carefully designed cluttered environments to train policies. These policies demonstrate emergent manipulation skills (e.g., pushing, stirring, and poking) that efficiently clear occluding objects to expose sufficient surface area of the target object. We conduct extensive evaluations across a set of over 10 household objects in diverse clutter configurations, demonstrating superior retrieval performance and efficiency for both trained and unseen objects. Furthermore, we successfully transfer the learned policies to a real-world dexterous multi-fingered robot system, validating their practical applicability in real-world scenarios. Videos can be found on our project website https://ChangWinde.github.io/RetrDex. |
| title | Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.18423 |