Special issue on genetic fuzzy systems for control and robotics— Preface

Abstract

This special issue encompases selected papers presented at the Sixth International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU'96) that was held in Granada, Spain, July 1-5, 1996. The present issue is devoted to genetic fuzzy systems. The idea of a genetic fuzzy system is that of a fuzzy system design process which incorporates genetic techniques to achieve the automatic generation or modification of its knowledge base (or a part of it). This generation or modification usually involves a tuning/ learning process. The objective of this process is optimization, that is, to maximize or minimize a certain functional representing or describing the behavior of the system. Genetic algorithms have been shown to be an effective tool and demonstrate their potential through the solutions that they provide. Their advantages have extended the use of genetic algorithms in the development of a wide range of approaches for designing fuzzy systems. The present issue includes some of these approaches. The papers may be classified into two groups. They will be briefly reviewed in the following two paragraphs. The first group of papers presents genetic learning processes for obtaining fuzzy logic control knowledge bases. Genetic fuzzy systems applied to learn the rule base and the gain and sensitivity (by means of the scaling functions) of the controller related to each input and output variable are