Navigation of an outdoor robot using a fuzzy logic controller

Abstract

This paper describes a design of an outdoor autonomous vehicle to compete in the 13th Annual Intelligent Ground Vehicle Competition at Traverse City, Michigan. In order to be successful in the competition, the mobile vehicle has to be able to go through the pre-defined waypoints without colliding with any obstacles. A commercially available GPS system is used to provide GPS signals. The vehicle is also mounted with several ultrasonic rangers. Two DC motors drive the rear left and right wheels. A fuzzy approach to the navigation control of the robot is adopted to represent the mapping between the sensor input space and mobile robot action space. The fuzzy controller receives input data from the sensors and GPS receiver, determines the steering angle and velocity of the vehicle for the next time step. The experimental results are satisfying; the developed vehicle can follow the pre-defined path successfully with the error range of 3 meters, while avoiding obstacles along the way