Robust reinforcement learning-based tracking control for wheeled mobile robot

Author

Luy, Nguyen Tan ; Thanh, Nguyen Duc ; Thanh, Nguyen Thien ; Ha, Nguyen Thi Phuong

Author_Institution

Nat. Key Lab. for Digital Control & Syst. Eng., Hochiminh City Univ. of Technol., Ho Chi Minh City, Vietnam

Volume

1

fYear

2010

fDate

26-28 Feb. 2010

Firstpage

171

Lastpage

176

Abstract

This paper proposes a method to design a robust reinforcement learning-based tracking control scheme for the wheeled mobile robot. A policy iteration algorithm and a neural network are used to design an adaptive critic robust controller. A H_Â¿ - tracking performance index optimal function is evaluated by this con troller. The stability of the closed-loop system while learning is proven by Lyapunov theory. The simulation results for wheeled mobile robot verify the effects of the proposed controller.

Keywords

H^Â¿ control; Lyapunov methods; adaptive control; closed loop systems; control engineering computing; control system synthesis; iterative methods; learning (artificial intelligence); mobile robots; neural nets; tracking; H_Â¿-tracking performance index; Lyapunov theory; closed-loop system; neural network; robust reinforcement learning; tracking control; wheeled mobile robot; Adaptive control; Automatic control; Control systems; Learning; Mobile robots; Neural networks; Performance analysis; Programmable control; Robust control; Wheels; Adaptive critic; policy iteration; robust reinforcement learning; wheeled mobile robot;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4244-5585-0

Electronic_ISBN

978-1-4244-5586-7

Type

conf

DOI

10.1109/ICCAE.2010.5451973

Filename

5451973