Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914115789783040 |
|---|---|
| author | Hong, Matthew Liang, Anthony Kim, Kevin Rajaprakash, Harshitha Thomason, Jesse Bıyık, Erdem Zhang, Jesse |
| author_facet | Hong, Matthew Liang, Anthony Kim, Kevin Rajaprakash, Harshitha Thomason, Jesse Bıyık, Erdem Zhang, Jesse |
| contents | We hand the community HAND, a simple and time-efficient method for teaching robots new manipulation tasks through human hand demonstrations. Instead of relying on task-specific robot demonstrations collected via teleoperation, HAND uses easy-to-provide hand demonstrations to retrieve relevant behaviors from task-agnostic robot play data. Using a visual tracking pipeline, HAND extracts the motion of the human hand from the hand demonstration and retrieves robot sub-trajectories in two stages: first filtering by visual similarity, then retrieving trajectories with similar behaviors to the hand. Fine-tuning a policy on the retrieved data enables real-time learning of tasks in under four minutes, without requiring calibrated cameras or detailed hand pose estimation. Experiments also show that HAND outperforms retrieval baselines by over 2x in average task success rates on real robots. Videos can be found at our project website: https://liralab.usc.edu/handretrieval/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20455 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval Hong, Matthew Liang, Anthony Kim, Kevin Rajaprakash, Harshitha Thomason, Jesse Bıyık, Erdem Zhang, Jesse Robotics We hand the community HAND, a simple and time-efficient method for teaching robots new manipulation tasks through human hand demonstrations. Instead of relying on task-specific robot demonstrations collected via teleoperation, HAND uses easy-to-provide hand demonstrations to retrieve relevant behaviors from task-agnostic robot play data. Using a visual tracking pipeline, HAND extracts the motion of the human hand from the hand demonstration and retrieves robot sub-trajectories in two stages: first filtering by visual similarity, then retrieving trajectories with similar behaviors to the hand. Fine-tuning a policy on the retrieved data enables real-time learning of tasks in under four minutes, without requiring calibrated cameras or detailed hand pose estimation. Experiments also show that HAND outperforms retrieval baselines by over 2x in average task success rates on real robots. Videos can be found at our project website: https://liralab.usc.edu/handretrieval/. |
| title | HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.20455 |