A fuzzy-Gaussian neural network and its application to mobile robot control

Abstract

A fuzzy-Gaussian neural network (FGNN) controller is described by applying a Gaussian function as an activation function. A specialized learning architecture is used so that membership function can be tuned without using expert's manipulated data. As an example of the application, a tracking control problem for the speed and azimuth of a mobile robot driven by two independent wheels is solved by using the FGNN controller. To simplify the implementation of the FGNN controller for the two-input/two-output controlled system, a learning controller is utilized consisting of two FGNN's based on independent reasoning and a connection net with fixed weights. The effectiveness of the proposed method is illustrated by performing the simulation of a circular or square trajectory tracking control.