Self-Tuning Self-Organizing Fuzzy Robot Control

Abstract The paper describes the idea of self-tuning self-organising fuzzy control. Simple fuzzy controller, introduced at the beginning of seventies as a rule-based controller, had two main disadvantages: difficulty with definition of good control rules and problems with tuning of controller parameters. Self-organising controller was developed to overcome the first problem. In this paper we propose a self-tuning procedure to overcome the second problem. That procedure is based on expert knowledge about the influence of the tuning parameters on the system response. Theoretical results are illustrated and tested by simulation a two link robot manipulator.

[1]  Ebrahim H. Mamdani,et al.  A linguistic self-organizing process controller , 1979, Autom..

[2]  Ebrahim Mamdani,et al.  Applications of fuzzy algorithms for control of a simple dynamic plant , 1974 .

[3]  Yosef S. Sherif,et al.  Applications of fuzzy set theory , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  C. S. George Lee,et al.  Robot Arm Kinematics, Dynamics, and Control , 1982, Computer.

[5]  William Pferd,et al.  Special Feature: Interactive Graphics Teleconferencing , 1979, Computer.

[6]  M. Jamshidi,et al.  Expert self-learning controller for robot manipulator , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.