A study for AGV steering control and identification using vision system

The authors experimented on an AGV driving test with a color CCD camera. This paper can be divided into two parts. One is the image processing part to measure the condition of the guideline and AGV. The other obtains the reference steering angle through using the image processing parts. First, the two dimensional information of image derived from the vision sensor is interpreted to 3 dimension information by the angle and position of the CCD camera. Through these processes, the AGV knows its driving conditions. Using this information, the AGV calculates the reference steering angle changed by its speed. In the case of low speed, it focuses on the left/right error values of the guideline. As the speed of the AGV increases, it focuses on the slope of the guideline. Lastly, the authors model the above descriptions to the type of PID controller and regulate the coefficient value of the AGV speed.