Image Technology for Camera-Based Automatic Guided Vehicle

This paper describes image technology using a neural network system for an automatic guided vehicle to follow a lane. Without complicated image processing from the image of a lane to the vehicle-centered representation of a bird's eye view in conventional studies, the proposed system transfers the input of image information into the output of a steering angle directly. The neural network system replaces the nonlinear relation of image information to a steering angle of vehicle on the real ground. For image information, the vanishing point and vanishing line of lane on a camera image are used. In a straight and curved lane, the driving performances by the proposed technology are measured in simulation and experimental test.