Title :
Evolving multiple sensory-motor controllers based on cellular neural network
Author_Institution :
Dept. of Comput. Sci., Yonsei Univ., Seoul, South Korea
Abstract :
There has been extensive work done to construct an optimal neural network for controlling a mobile robot by evolutionary approaches such as genetic algorithms, genetic programming, and so on. However, evolutionary approaches have difficulty in obtaining a controller that conducts complex and general behaviors. In order to overcome this shortcoming, we propose a method of combining several evolved modules by a rule-based approach. The multi-module integration method can make complex and general behaviors by combining several modules that are evolved or programmed to perform simple behaviors. Experimental results show the potential of the multi-module integration method as a sophisticated technique to make an evolved neural network carry out complex and general behaviors
Keywords :
cellular neural nets; evolutionary computation; mobile robots; neurocontrollers; optimal control; subroutines; cellular neural network; complex behaviors; evolutionary approaches; evolved module combination; general behaviors; genetic algorithms; genetic programming; mobile robot control; multi-module integration method; multiple sensory-motor controller evolution; neurocontrol; optimal neural network; rule-based approach; Artificial neural networks; Automatic control; Biological neural networks; Cellular neural networks; Control systems; Genetic algorithms; Genetic programming; Mobile robots; Neural networks; Robot control;
Conference_Titel :
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-7078-3
DOI :
10.1109/NAFIPS.2001.944414