Application of Fuzzy Neural Networks in data fusion for mobile robot wall-following

Abstract

This paper presents a multi-sensor data fusion algorithm based on Fuzzy Neural Networks. And then, this algorithm is applied on wall-following of a robot. By using back propagation Neural network as the base, fuzzy logic and neural networks can be used together to form a fuzzy neural networks. Its calculating model combines the wall-following rules of three sorts of wall in unknown environment and back propagation neural network. So, fuzzy neural networks can auto pick up the fuzzy rules and build the subordinate function to decide mobile robotpsilas motion. The training and simulation result shows that the method which was used in wall-following of mobile robot is practicable and effective.