Incremental Learning of Robot Dynamics using Random Features

摘要：

Analytical models for robot dynamics often perform suboptimally in practice, due to various non-linearities and the difficulty of accurately estimating the dynamic parameters. Machine learning techniques are less sensitive to these problems and therefore an interesting alternative for modeling robot dynamics. We propose a learning method that combines a least squares algorithm with a non-linear feature mapping and an efficient update rule. Using data from five different robots, we show that the method can accurately model manipulator dynamics, either when trained in batch or incrementally. Furthermore, the update time and memory usage of the method are bounded, therefore allowing use in real-time control loops.

作者: Arjan Gijsberts Giorgio Metta

作者单位: Department of Robotics,Brain and Cognitive Sciences,Italian Institute of Technology,Via Morego 30,16 Department of Robotics,Brain and Cognitive Sciences,Italian Institute of Technology,Via Morego 30,16

会议类型: 国际会议

会议名称: 2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

会议地点: 上海

会议语种:英文

页码: 951-956

在线出版日期: 2011-05-09（万方平台首次上网日期，不代表论文的发表时间）