Evolutionary fuzzy system for architecture control in a constructive neural network

This work describes an evolutionary system to control the growth of a constructive neural network for autonomous navigation. A classifier system generates Takagi-Sugeno fuzzy rules and controls the architecture of a constructive neural network. The performance of the mobile robot guides the evolutionary learning mechanism. Experiments show the efficiency of the classifier fuzzy system for analyzing if it is worth inserting a new neuron into the architecture.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  Marco Colombetti,et al.  Behavior analysis and training-a methodology for behavior engineering , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[3]  Jie Cheng,et al.  PASS: a program for automatic structure search , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[4]  Qiangfu Zhao.  A co-evolutionary algorithm for neural network learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[5]  R. Reder Cazangi,et al.  Simultaneous emergence of conflicting basic behaviors and their coordination in an evolutionary autonomous navigation system , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[6]  F.J. Von Zuben,et al.  A hierarchical neuro-fuzzy approach to autonomous navigation , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[7]  M. Figueiredo,et al.  Reinforcement learning for hierarchical and modular neural network in autonomous robot navigation , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[8]  Yunhui Liu,et al.  Adaptive categorization of ART networks in robot behavior learning using game-theoretic formulation , 2003, Neural Networks.

[9]  Albert-Jan Baerveldt,et al.  Intelligent autonomous navigation for mobile robots: spatial concept acquisition and object discrimination , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.