A modified approach to fuzzy Q learning for mobile robots

Author

Ritthipravat, Panrasee ; Maneewarn, Thavida ; Laowattana, Djitt ; Wyatt, Jeremy

Author_Institution

Inst. of Field Robotics, King Mongkut´´s Univ. of Technol. Thonburi, Bangkok, Thailand

Volume

3

fYear

2004

fDate

10-13 Oct. 2004

Firstpage

2350

Abstract

A modified approach to fuzzy Q-learning is presented in this paper. A reward sharing mechanism is added to increase the learning speed and to allow treatment of each fuzzy rule as a separate learning node. A new method of exploration is also proposed to increase the learning performance. Two basic robot behaviours which are a goal-seeking and an obstacle avoidance behaviour are simulated to show the promise of the proposed techniques. The goal-seeking behaviour is implemented on a real robot. The experimental results show that this method is practical for a real-world problem.

Keywords

collision avoidance; fuzzy reasoning; fuzzy set theory; mobile robots; fuzzy Q learning; fuzzy rule; goal-seeking behaviour; learning speed; mobile robots; obstacle avoidance behaviour; reward sharing mechanism; robot behaviours; Computer science; Error correction; Fuzzy logic; Fuzzy systems; Hybrid intelligent systems; Input variables; Learning; Mobile robots; Orbital robotics; Robot sensing systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2004 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-8566-7

Type

conf

DOI

10.1109/ICSMC.2004.1400680

Filename

1400680