arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.11048cs.ROcs.AIcs.LG
收藏

RP1M:面向双臂灵巧机器人手弹钢琴的大规模运动数据集

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

University of Oulu(奥卢大学);Aalto University(阿尔托大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Southern California(南加利福尼亚大学)

Yi Zhao, Le Chen, Jan Schneider, Quankai Gao, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler

AI总结:

为解决强化学习在多曲目机器人钢琴演奏中的泛化难题,提出含超百万轨迹的RP1M数据集,通过最优传输实现自动标注,并验证其能显著提升模仿学习方法的演奏性能。

摘要:

赋予机器人手人类水平的灵巧性一直是一个长期的研究目标。双臂机器人弹钢琴构成了一项任务,它结合了动态任务的挑战(如生成快速且精确的运动)与较慢但接触丰富的操作问题。尽管基于强化学习的方法在单任务性能上展现出了有前景的结果,但这些方法在多曲目设定下表现吃力。我们的工作旨在弥合这一差距,从而使得大规模的机器人弹钢琴模仿学习方法成为可能。为此,我们引入了 Robot Piano 1 Million (RP1M) 数据集,包含超过一百万条轨迹的双臂机器人弹钢琴运动数据。我们将手指放置形式化为最优传输问题,从而能够对大量未标注曲目进行自动标注。对现有模仿学习方法的基准测试表明,这些方法通过利用 RP1M 达到了当前最先进的机器人弹钢琴性能。

英文摘要:

It has been a long-standing research goal to endow robot hands with human-level dexterity. Bi-manual robot piano playing constitutes a task that combines challenges from dynamic tasks, such as generating fast while precise motions, with slower but contact-rich manipulation problems. Although reinforcement learning based approaches have shown promising results in single-task performance, these methods struggle in a multi-song setting. Our work aims to close this gap and, thereby, enable imitation learning approaches for robot piano playing at scale. To this end, we introduce the Robot Piano 1 Million (RP1M) dataset, containing bi-manual robot piano playing motion data of more than one million trajectories. We formulate finger placements as an optimal transport problem, thus, enabling automatic annotation of vast amounts of unlabeled songs. Benchmarking existing imitation learning approaches shows that such approaches reach state-of-the-art robot piano playing performance by leveraging RP1M.

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。

↑