跳到主要导航 跳到搜索 跳到主要内容

Online actor-critic learning for motion control of non-holonomic mobile robot

  • Kai Wang*
  • , Yingmin Jia
  • , Junping Du
  • , Fashan Yu
  • *此作品的通讯作者
  • Beihang University
  • Beijing University of Posts and Telecommunications
  • Henan Polytechnic University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

This paper presents a control structure designed for non-holonomic mobile robots by an online algorithm based on policy iteration for learning the continuous-time (CT) optimal control solution with infinite horizon cost. The algorithm learns online in real-time to the solution of Hamilton-Jacobi-Bellman (HJB) equation which has been used for optimal control design. This method finds in real-time suitable approximations of both the optimal cost and control policy, while also guaranteeing closed-loop stability, which implemented as an actor/critic structure involves simultaneous continuous-time adaptation of both actor and critic neural networks (NNs). Simulation examples show the effectiveness of the new algorithm.

源语言英语
主期刊名Electrical, Information Engineering and Mechatronics 2011 - Proceedings of the 2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011
1763-1770
页数8
DOI
出版状态已出版 - 2012
活动2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011 - Jiaozuo, Henan, 中国
期限: 23 12月 201125 12月 2011

出版系列

姓名Lecture Notes in Electrical Engineering
138 LNEE
ISSN(印刷版)1876-1100
ISSN(电子版)1876-1119

会议

会议2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011
国家/地区中国
Jiaozuo, Henan
时期23/12/1125/12/11

指纹

探究 'Online actor-critic learning for motion control of non-holonomic mobile robot' 的科研主题。它们共同构成独一无二的指纹。

引用此