The Transactions of the Korean Institute of Electrical Engineers D (대한전기학회논문지:시스템및제어부문D)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Dynamic Selection of Neural Network Modules based on Cellular Automata for Complex Behaviors

복잡한 행동을 위한 셀룰라 오토마타 기반 신경망 모듈의 동적선택

  • 김경중 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터과학과)
  • Published : 2002.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Since conventional mobile robot control with one module has limitation to solve complex problems, there have been a variety of works on combining multiple modules for solving them. Recently, many researchers attempt to develop mobile robot controllers using artificial life techniques. In this paper, we develop a mobile robot controller using cellular automata based neural networks, where complex tasks are divided to simple sub-tasks and optimal neural structure of each sub-task is explored by genetic algorithm. Neural network modules are combined dynamically using the action selection mechanism, where basic behavior modules compete each other by inhibition and cooperation. Khepera mobile robot simulator is used to verify the proposed model. Experimental results show that complex behaviors emerge from the combination of low-level behavior modules.

Keywords

References

  1. F. Gers, H. de Garis and M. Korkin, 'CoDi-1Bit: A simplified cellular automata based neural model,' Proc. Conf. on Artificial Evolution, Nimes, France, October, 1997 https://doi.org/10.1007/BFb0026610
  2. H. de Garis, M. Korkin, F. Gers, E. Nawa and M. Hough, 'ATRs artificial brain (CAM-Brain) project: A sample of what individual CoDi-1Bit model evolved neural net modules can do,' Proceedings of International Conference on Artificial Life and Robotics, Japan, 1999
  3. G.-B. Song AND S.-B. Cho, 'Incremental evolution of CAM-Brain,' Proceedings of International Conference on Artificial Life and Robotics, PP. 297-300, Beppu, Japan, 1999
  4. S.-B. Cho and G.-B. Song, 'Evolving CAM-Brain to control a mobile robot,' Applied Mathematics and Computation, Vol. 111, pp. 147-162, 2000 https://doi.org/10.1016/S0096-3003(99)00160-5
  5. G.-B. Song and S.-B. Cho, 'Combining incrementally evolved neural networks based on cellular automata for complex adaptive behaviors,' The First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks, pp. 121-129, May 2000 https://doi.org/10.1109/ECNN.2000.886227
  6. 김경준, 조성배, '다수의 CAM-Brain 모듈을 이용한 행동생성 방법론,' 인지과학회 춘계학술발표대회, pp. 63-66, 2001
  7. Khepera Simulator Homepage, http://diwww.epfl.ch/lami/team/michel/khep-sim/
  8. D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Publishing Company, 1989
  9. R. A. Brooks, 'A robust layered control system for a mobile robot,' IEEE Journal of Robotics and Automation, Vol. 2, zNo. 1, pp. 14-23, March 1986 https://doi.org/10.1109/JRA.1986.1087032
  10. P. Maes and R. Brooks, 'Learning to coordinate behaviors,' The American Conference on Artificial Intelligence, pp. 796-802, August, 1990
  11. P. Pirjanian, 'Behavior coordination mechanism-state-of-the-art,' Tech-report IRIS-99-375, Institute for Robotics and Intelligent Systems, School of Engineering, University of Southern California, Oct, 1999
  12. P. Maes, 'How to do the right thing,' Connection Science Journal, Vol 1, No. 3, pp. 291-323, 1989 https://doi.org/10.1080/09540098908915643
  13. M. Nicolescu and M. J. Mataric, 'Learning and interacting in human-robot domains', to appear in Special Issue of IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans. 2001 https://doi.org/10.1109/3468.952716
  14. Monica Nicolescu, Maja J Mataric, 'Extending behavior-based systems capabilities using an abstract behavior representation', Working Notes of the AAAI Fall Symposium on Parallel Cognition, pp. 27-34, North Falmouth, MA, Nov 3-5, 2000
  15. Klaus Dorer, 'Behavior networks for continuous domains using situation-dependent motivations,' International Joint Conference on Artificial Intelligence (IJCAI'99), pp. 1233-1238, 1999
  16. T. Tyrrell, 'An evaluation of Maes's bottom-up mechanism for behavior selection,' Adaptive Behavior, Vol. 2, pp. 307-348, 1994 https://doi.org/10.1177/105971239400200401
  17. E. Aguirre and A. Gonzalez, 'Fuzzy behaviors for mobile robot navigation: Design, coordination and fusion,' International Journal of Approximate Reasoning, Vol. 25, pp. 255-289, 2000 https://doi.org/10.1016/S0888-613X(00)00056-6
  18. G.-B. Song and S.-B. Cho, 'Rule-based integration of multiple neural networks evolved based on cellular automata,' FUZZ-IEEE'99, pp. 791-796, August 1999 https://doi.org/10.1109/FUZZY.1999.793049