Evolving type-2 fuzzy logic controllers for autonomous mobile robots

Autonomous mobile robots navigating in changing and dynamic unstructured environments like the outdoor environments need to cope with large amounts of uncertainties that are inherent in natural environments. The traditional type-1 Fuzzy Logic Controller (FLC) using precise type-1 fuzzy sets cannot fully handle such uncertainties. A type-2 FLC using type-2 fuzzy sets can handle such uncertainties to produce a better performance. However, manually designing the type-2 Membership Functions (MFs) for an interval type-2 FLC is a difficult task. This paper will present a Genetic Algorithm (GA) based architecture to evolve the type-2 MFs of interval type-2 FLCs used for mobile robots. The GA based system converges after a small number of iterations to type-2 MFs which gave very good performance. We have performed various experiments in which the evolved type-2 FLC dealt with the uncertainties and resulted in a very good performance that has outperformed its type-1 counterpart as well as the manually designed type-2 FLC.