Navigation and Control for Obstacle Avoidance of an Unmanned Vehicle

The main theme of this thesis is to develop an integrated navigation and control system for an unmanned vehicle. This system consists of three parts which are main- station, reference-station, and unmanned vehicle. There are various sensors on the vehicle such as GPS receiver, the electronic compass, the camera and six ultrasonic sensors. The vehicle uses camera to detect lanemarkers, ultrasonic sensors to detect the distance between the vehicle and the obstacle, electronic compass to measure the vehicle’s posture and GPS information to determine the vehicle’s position. The data exchange mechanism between sub-systems is set up through wireless network.
The task of tracking is performed such that the vehicle can track along a lanemarker specified in advance and avoid collision with obstacle. The concept of template correlation is used to identify existing lanemarkers in vision. The techniques of Sobel Edge Detention and Randomized Hough Transform are then applied to obtain the parameters of the lanemarker. The operation of six ultrasonic sensors is designed by VHDL language and implemented by FPGA. The KGPS or DGPS is used to set the vehicle’s position. The several fuzzy controllers receive input data from the vision and the ultrasonic sensors, determine the steering angle and velocity of the vehicle. Experimental results show the effectiveness of our proposed navigation and control methodology.