A Reinforcement Learning Fuzzy Controller for the Ball and Plate system

Author

Mohajerin, Nima ; Menhaj, Mohammad B. ; Doustmohammadi, Ali

Author_Institution

Sch. of Sci. & Technol., Orebro Univ., Orebro, Sweden

fYear

2010

fDate

18-23 July 2010

Firstpage

1

Lastpage

8

Abstract

In this paper, a new fuzzy logic controller, namely Reinforcement Learning Fuzzy Controller (RLFC), is proposed and implemented. Based on fuzzy logic, this newly proposed online-learning controller is capable of improving its behavior by learning from experiences it gains through interaction with the plant. RLFC is well established for hardware implementation with or without a priori knowledge about the plant. To evidence this claim, a hardware implementation of Ball and Plate system was established, and RLFC was then developed and applied to it. The obtained results are illustrated in this paper.

Keywords

fuzzy control; learning (artificial intelligence); nonlinear control systems; RLFC; a priori knowledge; ball system; hardware implementation; online-learning controller; plate system; reinforcement learning fuzzy logic controller; Fuzzy logic; Hardware; Learning; Mathematical model; Mechanical sensors; Tactile sensors; Balancing Systems; Ball and Plate system; Fuzzy Logic Controller; Model-free optimization; Reinforcement Learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems (FUZZ), 2010 IEEE International Conference on

Conference_Location

Barcelona

ISSN

1098-7584

Print_ISBN

978-1-4244-6919-2

Type

conf

DOI

10.1109/FUZZY.2010.5584025

Filename

5584025