First Results from Experiments in Fuzzy Classifier System Architectures for Mobile Robotics

We present first results from a comparison between a Fuzzy Classifier System operating at the level of whole rule-bases, and three variants of one that operates at the level of individual rules. The application domain is mobile robotics, and the problem is autonomous acquisition of an "investigative" obstacle avoidance competency. The Fuzzy Classifier Systems operate on the rules of fuzzy controllers with pre-defined fuzzy membership functions. Generally, all of the methods used were capable of producing fuzzy controllers with competencies that exceeded that of a simple hand-coded fuzzy controller that we had devised. The approach operating at the level of whole rule-bases yielded more robust and stable convergence on high performance solutions than any other architecture presented here. It is clear from the results that more work needs to be done to unravel the disappointing convergence dynamics of the algorithms operating at the level of individual rules.

[1]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[2]  Alexandre Parodi,et al.  A New Approach to Fuzzy Classifier Systems , 1993, ICGA.

[3]  Stephen F. Smith,et al.  A learning system based on genetic adaptive algorithms , 1980 .

[4]  Anthony G. Pipe,et al.  Autonomous Acquisition of Fuzzy Rules for Mobile Robot Control: First Results from two Evolutionary Computation Approaches , 2000, GECCO.

[5]  Manuel Valenzuela-Rendón,et al.  The Fuzzy Classifier System: A Classifier System for Continuously Varying Variables , 1991, ICGA.

[6]  Andreas Geyer-Schulz,et al.  Fuzzy Rule-Based Expert Systems and Genetic Machine Learning , 1996 .

[7]  Manuel Valenzuela-Rendón.  The Fuzzy Classifier System: Motivations and first Results , 1990, PPSN.

[8]  Anthony G. Pipe,et al.  X-FCS: a fuzzy classifier system using accuracy based fitness - first results , 2001, EUSFLAT Conf..

[9]  Andrea Bonarini,et al.  An Introduction to Learning Fuzzy Classifier Systems , 1999, Learning Classifier Systems.

[10]  Andrea Bonarini,et al.  Learning to compose fuzzy behaviors for autonomous agents , 1997, Int. J. Approx. Reason..

[11]  Andrea Bonarini,et al.  An approach to the design of reinforcement functions in real world, agent-based applications , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[12]  Andrea Bonarini,et al.  Anytime Learning and Adaptation of Structured Fuzzy Behaviors , 1997, Adapt. Behav..

[13]  Witold Pedrycz,et al.  Fuzzy evolutionary computation , 1997 .

[14]  Andrea Bonarini,et al.  Fuzzy and Crisp Representations of Real-Valued Input for Learning Classifier Systems , 1999, Learning Classifier Systems.

[15]  Chia-Ju Wu,et al.  Design of fuzzy logic controllers using genetic algorithms , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[16]  Stewart W. Wilson,et al.  Learning Classifier Systems, From Foundations to Applications , 2000 .

[17]  D.E. Goldberg,et al.  Classifier Systems and Genetic Algorithms , 1989, Artif. Intell..

[18]  Alistair Munro,et al.  Evolving fuzzy rule based controllers using genetic algorithms , 1996, Fuzzy Sets Syst..