SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

ICLR 2025 Conference Submission510 Authors

Keywords: Robotic Assembly Tasks; Skill Retrieval; Skill Adaptation; Sim-to-real Transfer; Reinforcement Learning Fine-tuning;

TL;DR: We introduce SRSA, a novel pipeline that retrieves relevant skills from a pre-existing skill library and adapts them to efficiently solve new robotic assembly tasks.

Abstract: Enabling robots to learn novel tasks in a data-efficient manner is a long-standing challenge. Common strategies involve carefully leveraging prior experiences, especially transition data collected on related tasks. Although much progress has been made in developing such strategies for general pick-and-place manipulation, far fewer studies have investigated contact-rich assembly tasks, where precise control is essential. In this work, we present SRSA (Skill Retrieval and Skill Adaptation), a novel framework designed to address this problem by utilizing a pre-existing skill library containing policies for diverse assembly tasks. The challenge lies in identifying which skill from the library is most relevant for fine-tuning on a new task. Our key hypothesis is that skills showing higher zero-shot success rates on a new task are better suited for rapid and effective fine-tuning on that task. To this end, we propose to predict the transfer success for all skills in the skill library on a novel task, and then use this prediction to guide the skill retrieval process. Through extensive experiments, we demonstrate that SRSA significantly outperforms the leading baseline, achieving a 22\% relative improvement in success rate, 3.7x higher stability, and 2.4x greater sample efficiency when retrieving and fine-tuning skills on unseen tasks. Moreover, in a continual learning setup, SRSA efficiently learns policies for new tasks and incorporates them into the skill library, enhancing future policy learning. Additionally, policies trained with SRSA in simulation achieve a 90% mean success rate when deployed in the real world. Please visit our project webpage at https://srsa2024.github.io/ for videos.

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 510