Visual control of an autonomous vehicle using neural networks

This paper describes a control scheme for on autonomous vehicle with visual sensors, which uses visual information to guide itself along roadways. The control system integrates visual data into the servo process directly, instead of subdividing the process by reconstructing three-dimensional shape from two-dimensional image data, and relying on geometric reasoning for a vehicle-centered representation of the road. An artificial neural network system is used for determining the steering angle required to move the vanishing point and vanishing line of the road to the desired position in the camera image. The validity and the effectiveness of the proposed control scheme are verified by a computer simulation of the autonomous vehicle's performance.