arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.08689cs.ROcs.LGcs.SYeess.SY
收藏

多机器人迁移学习:动态系统视角

Multi-Robot Transfer Learning: A Dynamical System Perspective

University of Toronto(多伦多大学)

Mohamed K. Helwa, Angela P. Schoellig

AI总结:

本文从动态系统角度研究多机器人迁移学习中的最优转移映射性质,提出无需详细动力学知识的算法,通过实验验证该算法在四旋翼平台间迁移学习中减少60-70%的误差。

摘要:

多机器人迁移学习允许一个机器人利用第二个相似机器人生成的数据来改进自身行为。潜在优势是减少训练时间并降低训练阶段不可避免的风险。迁移学习算法旨在找到不同机器人之间的最优转移映射。本文通过单输入单输出(SISO)系统的理论研究,探讨了此类最优转移映射的性质。我们首先证明最优迁移学习映射通常是一个动态系统。本文的主要贡献是提供一种确定该最优动态映射性质的算法,包括其阶数和回归器(即它所依赖的变量)。所提出的算法不需要详细的机器人动力学知识,但依赖于通过简单实验测试可获得的基本系统属性。我们通过两个不同四旋翼平台间的迁移学习示例验证了所提算法。实验结果表明,通过我们的算法获得的最优动态映射在减少迁移学习误差方面比直接转移数据或使用最优静态映射的情况减少了60-70%。

英文摘要:

Multi-robot transfer learning allows a robot to use data generated by a second, similar robot to improve its own behavior. The potential advantages are reducing the time of training and the unavoidable risks that exist during the training phase. Transfer learning algorithms aim to find an optimal transfer map between different robots. In this paper, we investigate, through a theoretical study of single-input single-output (SISO) systems, the properties of such optimal transfer maps. We first show that the optimal transfer learning map is, in general, a dynamic system. The main contribution of the paper is to provide an algorithm for determining the properties of this optimal dynamic map including its order and regressors (i.e., the variables it depends on). The proposed algorithm does not require detailed knowledge of the robots' dynamics, but relies on basic system properties easily obtainable through simple experimental tests. We validate the proposed algorithm experimentally through an example of transfer learning between two different quadrotor platforms. Experimental results show that an optimal dynamic map, with correct properties obtained from our proposed algorithm, achieves 60-70% reduction of transfer learning error compared to the cases when the data is directly transferred or transferred using an optimal static map.

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。

↑