FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909593177686016 |
|---|---|
| author | Liu, Jason Jingzhou Li, Yulong Shaw, Kenneth Tao, Tony Salakhutdinov, Ruslan Pathak, Deepak |
| author_facet | Liu, Jason Jingzhou Li, Yulong Shaw, Kenneth Tao, Tony Salakhutdinov, Ruslan Pathak, Deepak |
| contents | Many contact-rich tasks humans perform, such as box pickup or rolling dough, rely on force feedback for reliable execution. However, this force information, which is readily available in most robot arms, is not commonly used in teleoperation and policy learning. Consequently, robot behavior is often limited to quasi-static kinematic tasks that do not require intricate force-feedback. In this paper, we first present a low-cost, intuitive, bilateral teleoperation setup that relays external forces of the follower arm back to the teacher arm, facilitating data collection for complex, contact-rich tasks. We then introduce FACTR, a policy learning method that employs a curriculum which corrupts the visual input with decreasing intensity throughout training. The curriculum prevents our transformer-based policy from over-fitting to the visual input and guides the policy to properly attend to the force modality. We demonstrate that by fully utilizing the force information, our method significantly improves generalization to unseen objects by 43\% compared to baseline approaches without a curriculum. Video results, codebases, and instructions at https://jasonjzliu.com/factr/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17432 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning Liu, Jason Jingzhou Li, Yulong Shaw, Kenneth Tao, Tony Salakhutdinov, Ruslan Pathak, Deepak Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Many contact-rich tasks humans perform, such as box pickup or rolling dough, rely on force feedback for reliable execution. However, this force information, which is readily available in most robot arms, is not commonly used in teleoperation and policy learning. Consequently, robot behavior is often limited to quasi-static kinematic tasks that do not require intricate force-feedback. In this paper, we first present a low-cost, intuitive, bilateral teleoperation setup that relays external forces of the follower arm back to the teacher arm, facilitating data collection for complex, contact-rich tasks. We then introduce FACTR, a policy learning method that employs a curriculum which corrupts the visual input with decreasing intensity throughout training. The curriculum prevents our transformer-based policy from over-fitting to the visual input and guides the policy to properly attend to the force modality. We demonstrate that by fully utilizing the force information, our method significantly improves generalization to unseen objects by 43\% compared to baseline approaches without a curriculum. Video results, codebases, and instructions at https://jasonjzliu.com/factr/ |
| title | FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.17432 |