arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04538cs.RO
收藏

SRSA:面向机器人装配任务的技能检索与适应

SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

NVIDIA Corporation(英伟达公司);University of Southern California(南加州大学);University of Washington(华盛顿大学)

Yijie Guo, Bingjie Tang, Iretiayo Akinola, Dieter Fox, Abhishek Gupta, Yashraj Narang

AI总结:

针对机器人富接触装配任务的数据高效学习问题,提出 SRSA 框架,通过预测技能库中各技能在新任务上的零样本迁移成功率来指导技能检索与微调,显著提升了成功率、稳定性和样本效率,并在真实世界部署中达到 90% 平均成功率。

摘要:

以数据高效的方式使机器人学习新任务是一项长期存在的挑战。常见策略包括谨慎利用先验经验,特别是在相关任务上收集的转移数据。尽管在通用抓取与放置操作方面取得了诸多进展,但针对需要精确控制的富接触装配任务的研究仍然较少。我们提出了 SRSA(Skill Retrieval and Skill Adaptation,技能检索与技能适应),这是一种新颖的框架,旨在通过利用包含多种装配任务策略的预存技能库来解决此问题。挑战在于识别库中的哪个技能最适用于新任务的微调。我们的关键假设是:在新任务上表现出更高零样本成功率的技能,更适合在该任务上进行快速且有效的微调。为此,我们提出预测技能库中所有技能在新任务上的迁移成功率,并利用该预测来指导技能检索过程。我们建立了一个联合捕捉物体几何、物理动力学和专家动作特征以表示任务的框架,使我们能够高效地学习迁移成功率预测器。大量实验表明,SRSA 显著优于领先的基线方法。与基线相比,在未见任务上检索和微调技能时,SRSA 的成功率实现了 19% 的相对提升,在不同随机种子下的标准差降低了 2.6 倍,且达到满意成功率所需的转移样本减少了 2.4 倍。此外,在仿真中使用 SRSA 训练的策略在现实世界部署时达到了 90% 的平均成功率。请访问我们的项目网页 https://srsa2024.github.io/。

英文摘要:

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 for general pick-and-place manipulation, far fewer studies have investigated contact-rich assembly tasks, where precise control is essential. We introduce 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. We establish a framework that jointly captures features of object geometry, physical dynamics, and expert actions to represent the tasks, allowing us to efficiently learn the transfer success predictor. Extensive experiments demonstrate that SRSA significantly outperforms the leading baseline. When retrieving and fine-tuning skills on unseen tasks, SRSA achieves a 19% relative improvement in success rate, exhibits 2.6x lower standard deviation across random seeds, and requires 2.4x fewer transition samples to reach a satisfactory success rate, compared to the baseline. Furthermore, policies trained with SRSA in simulation achieve a 90% mean success rate when deployed in the real world. Please visit our project webpage https://srsa2024.github.io/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑