Conference item
Learning generalizable manipulation policy with adapter-based parameter fine-tuning
- Abstract:
- This study investigates the use of adapters in reinforcement learning for robotic skill generalization across multiple robots and tasks. Traditional methods are typically reliant on robot-specific retraining and face challenges such as efficiency and adaptability, particularly when scaling to robots with varying kinematics. We propose an alternative approach where a disembodied (virtual) hand manipulator learns a task (i.e., an abstract skill) and then transfers it to various robots with different kinematic constraints without retraining the entire model (i.e., the concrete, physical implementation of the skill). Whilst adapters are commonly used in other domains with strong supervision available, we show how weaker feedback from robotic control can be used to optimize task execution by preserving the abstract skill dynamics whilst adapting to new robotic domains. We demonstrate the effectiveness of our method with experiments conducted in the SAPIEN ManiSkill environment, showing improvements in generalization and task success rates. All code, data, and additional videos are at this GitHub link: https://kl-research.github.io/genrob.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 5.1MB, Terms of use)
-
- Publisher copy:
- 10.1109/iros58592.2024.10801544
Authors
- Publisher:
- IEEE
- Host title:
- 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Pages:
- 13510-13517
- Publication date:
- 2024-10-18
- Acceptance date:
- 2024-10-14
- Event title:
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
- Event location:
- Abu Dhabi, United Arab Emirates
- Event website:
- http://iros2024-abudhabi.org/
- Event start date:
- 2024-10-14
- Event end date:
- 2024-10-18
- DOI:
- EISSN:
-
2153-0866
- ISSN:
-
2153-0858
- EISBN:
- 9798350377705
- ISBN:
- 9798350377712
- Language:
-
English
- Keywords:
- Pubs id:
-
2078555
- Local pid:
-
pubs:2078555
- Deposit date:
-
2025-03-04
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2024
- Rights statement:
- © 2024 IEEE
- Notes:
- This paper was presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), 14th-18th October 2024, Abu Dhabi, United Arab Emirates. The author accepted manuscript (AAM) of this paper has been made available under the University of Oxford's Open Access Publications Policy, and a CC BY public copyright licence has been applied.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record