Evolution of control systems for mobile robots

Author

Ki Kim, Pang ; Vadakkepat, Prahlad ; Lee, Tong-Heng ; Peng, Xiao

Author_Institution

Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore

Volume

1

fYear

2002

Firstpage

617

Lastpage

622

Abstract

The advantages and disadvantages of evolving neural control systems for mobile robots using genetic algorithms are investigated. The Khepera robot is trained using the evolutionary neural networks (ENN) algorithm for the task of obstacle avoidance. The feasibility of using Q-learning for robot learning is also studied. It is found that Q-learning can be successfully used to train a robot and is more promising than the ENN algorithm in this case. The Webots simulation software has been used to carry out all the experiments

Keywords

collision avoidance; control system analysis computing; digital simulation; genetic algorithms; intelligent control; learning (artificial intelligence); mobile robots; neurocontrollers; optimal control; Khepera robot training; Q-learning; Webots simulation software; evolutionary neural networks; genetic algorithms; mobile robot control systems; neural control systems evolution; obstacle avoidance; robot learning; Artificial intelligence; Control systems; Genetic algorithms; Infrared sensors; Learning; Light sources; Mobile robots; Robot control; Robot sensing systems; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2002. CEC '02. Proceedings of the 2002 Congress on

Conference_Location

Honolulu, HI

Print_ISBN

0-7803-7282-4

Type

conf

DOI

10.1109/CEC.2002.1006997

Filename

1006997