Study on Obstacle Avoidance of AGV based on Fuzzy Neural Network

Abstract

As a kind of intelligent car, automated guided vehicle (AGV) belongs to the application direction of wheeled robots and has been widely used in various industrial fields. Because of complex and unpredictable working environment, the obstacle avoidance of AGV has attracted much attention. In this paper, multi-sensor information fusion technology based on back propagation (BP) fuzzy neural network is applied to AGV vehicle obstacle avoidance. Five combinations of infrared sensor and ultrasonic sensor are used to detect the distance of obstacles and one laser sensor is used to scan the direction of targets. The collected data of multiple sensors are fused twice. The simulation results of MATLAB demonstrate the effectiveness of the proposed method.