Interval type-2 beta fuzzy neural network for wheeled mobile robots obstacles avoidance

Abstract

Navigation of mobile robots in dynamic and unknown environments is usually cluttered with noise and errors. In the literature, several solutions have been proposed. Recently, type-2 fuzzy logic have showed having the ability to handle uncertainties, imprecise and incomplete data. Since, it has been constituted a new hopeful and promising technique for further improve control of mobile robots in real time applications. In elaborating fuzzy controllers, the most used membership functions in existing works, are the Gaussian, trapezoidal or triangular. In this paper, we propose a new Interval Type-2 Beta Fuzzy Neural Network (IT2BFNN) for obstacles Avoidance task for wheeled mobile robots. The main and novel idea is to involve type-2 beta fuzzy sets in the design process of a fuzzy network for the navigation process. The proposed architecture controller is based on beta type-2 fuzzy sets in the antecedent part, while the consequent part performed the TSK (Takagi-Sugeno-Kang) fuzzy output strategy.