arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.13150cs.ROcs.LGcs.SYeess.SY
收藏

基于动力学相似性的机器人多源迁移学习经验选择

Experience Selection Using Dynamics Similarity for Efficient Multi-Source Transfer Learning Between Robots

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所)

Michael J. Sorocky, Siqi Zhou, Angela P. Schoellig

摘要:

在机器人技术文献中,已经提出了不同的知识转移方法来利用来自源任务或机器人(真实或虚拟)的经验来加速新任务或机器人的学习过程。一个常见但不常检验的假设是,将来自源任务或机器人的经验合并将是有益的。在实践中,不适当的知识转移可能导致负转移或不安全行为。在这项工作中,从鲁棒控制理论的系统间隙度量的启发,$ν$间隙,我们提出了一个数据有效的算法来估计对机器人系统之间的相似性。在一个多源机器人间的迁移学习设置,我们表明,这种相似性度量允许我们预测相对传输性能,从而信息选择的经验,从源机器人知识转移之前。我们证明了我们的方法与四旋翼实验,在那里我们从一个真正的或虚拟的源四旋翼的逆动力学模型,以提高目标四旋翼的跟踪性能在任意手绘轨迹。我们表明,选择经验的基础上提出的相似性度量有效地促进了目标四旋翼的学习,提高了62%的性能相比,一个糟糕的选择经验。

英文摘要:

In the robotics literature, different knowledge transfer approaches have been proposed to leverage the experience from a source task or robot -- real or virtual -- to accelerate the learning process on a new task or robot. A commonly made but infrequently examined assumption is that incorporating experience from a source task or robot will be beneficial. In practice, inappropriate knowledge transfer can result in negative transfer or unsafe behaviour. In this work, inspired by a system gap metric from robust control theory, the $ν$-gap, we present a data-efficient algorithm for estimating the similarity between pairs of robot systems. In a multi-source inter-robot transfer learning setup, we show that this similarity metric allows us to predict relative transfer performance and thus informatively select experiences from a source robot before knowledge transfer. We demonstrate our approach with quadrotor experiments, where we transfer an inverse dynamics model from a real or virtual source quadrotor to enhance the tracking performance of a target quadrotor on arbitrary hand-drawn trajectories. We show that selecting experiences based on the proposed similarity metric effectively facilitates the learning of the target quadrotor, improving performance by 62% compared to a poorly selected experience.

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。

↑