arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.18481cs.RO

用于更好示范的仪器化:一项案例研究

Instrumentation for Better Demonstrations: A Case Study

AI and Robotics Lab (IDLab-AIRO), Ghent University—imec(人工智能与机器人实验室(IDLab-AIRO),根特大学—imec)

Remko Proesmans, Thomas Lips, Francis wyffels

AI总结:

本研究通过为挤压瓶配备压力传感器并利用PI控制器自动化数据收集,证明仪器化能提升示范质量,使基于Transformer的策略在78%情况下优于人类数据训练的策略。

摘要:

从示范中学习是机器人操作的一种强大范式,但其有效性取决于所收集数据的数量和质量。在这项工作中,我们提出了一项关于仪器化(即传感器集成)如何提高示范质量并实现数据收集自动化的案例研究。我们为挤压瓶配备压力传感器,以学习液体分配任务,通过PI控制器实现自动化数据收集。基于Transformer的策略在自动化示范上训练,在78%的情况下优于在人类数据上训练的策略。我们的发现表明,仪器化不仅促进了可扩展的数据收集,还带来了性能更优的策略,凸显了其在追求通用机器人智能体方面的潜力。

英文摘要:

Learning from demonstrations is a powerful paradigm for robot manipulation, but its effectiveness hinges on both the quantity and quality of the collected data. In this work, we present a case study of how instrumentation, i.e. integration of sensors, can improve the quality of demonstrations and automate data collection. We instrument a squeeze bottle with a pressure sensor to learn a liquid dispensing task, enabling automated data collection via a PI controller. Transformer-based policies trained on automated demonstrations outperform those trained on human data in 78% of cases. Our findings indicate that instrumentation not only facilitates scalable data collection but also leads to better-performing policies, highlighting its potential in the pursuit of generalist robotic agents.

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。

↑