@inproceedings{3a2cfd1a80cf4c2bb4f1c1b2a2d53645,
title = "Online actor-critic learning for motion control of non-holonomic mobile robot",
abstract = "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.",
keywords = "Actor-critic algorithms, Hamilton-Jacobi-Bellman equation, Lyapunov stability, Neural networks, Non-holonomic mobile robots",
author = "Kai Wang and Yingmin Jia and Junping Du and Fashan Yu",
year = "2012",
doi = "10.1007/978-1-4471-2467-2\_209",
language = "英语",
isbn = "9781447124665",
series = "Lecture Notes in Electrical Engineering",
pages = "1763--1770",
booktitle = "Electrical, Information Engineering and Mechatronics 2011 - Proceedings of the 2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011",
note = "2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011 ; Conference date: 23-12-2011 Through 25-12-2011",
}