Rule-based integration of multiple neural networks evolved based on cellular automata

Geum Beom Song, Sung Bae Cho

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

There has been extensive research of developing the controller for a mobile robot. Especially, several researchers have constructed the mobile robot controller that can avoid obstacles, evade predators, or catch moving prey by evolutionary algorithms such as genetic algorithm and genetic programming. In this line of research, we also presented a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, this approach has a limitation to make the robot to perform appropriate behavior in complex environments. In this paper, we have attempted to solve this problem by combining several modules evolved to do a simple behavior by rule-based approach. Experimental results show that this approach has possibility to develop a sophisticated neural controller for complex environments.

Original languageEnglish
PagesII-791 - II-796
Publication statusPublished - 1999 Dec 1
EventProceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99 - Seoul, South Korea
Duration: 1999 Aug 221999 Aug 25

Other

OtherProceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99
CitySeoul, South Korea
Period99/8/2299/8/25

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Rule-based integration of multiple neural networks evolved based on cellular automata'. Together they form a unique fingerprint.

  • Cite this

    Song, G. B., & Cho, S. B. (1999). Rule-based integration of multiple neural networks evolved based on cellular automata. II-791 - II-796. Paper presented at Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99, Seoul, South Korea, .