Title :
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
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;
Conference_Titel :
Evolutionary Computation, 2002. CEC '02. Proceedings of the 2002 Congress on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7282-4
DOI :
10.1109/CEC.2002.1006997
