FUZZY-SYSTEMS AND NEURAL NETWORKS

Fuzzy systems are able to treat uncertain and imprecise information; t hey make use of knowledge in the form of linguistic rules. Their drawb acks are caused mainly by the difficulty of defining accurate membersh ip functions and lack of a systematic procedure for the transformation of expert knowledge into the rule base. Neural networks have the abil ity to learn but with some neural networks, knowledge representation a nd extraction are difficult. First, we consider a rule based fuzzy con troller and a learning procedure based on the stochastic approximation method. The Radial Basis Function neural network is then considered a nd it is shown that a modified form of this network is identical with the fuzzy controller, which may thus be considered as a neuro-fuzzy co ntroller. Numerical examples are presented to demonstrate the validity of the approach and it is shown that such an adaptive neuro-fuzzy sys tem is successful in the control of a mobile robot.