Steering Control of Autonomous Vehicles by Neural Networks

This paper describes how neural networks can be used to control the steering of an autonomous vehicle. It is assumed that the vehicle is equipped with passive or active sensors providing the range and heading angle information. Most of the developed autonomous vehicles rely on a path planning module to obtain appropriate steering commands. In contrast to path planning, a human driver bypasses the computation of a path trajectory and turns the steering wheel in direct reaction to an observed heading angle and range. In this paper, we present a neural network scheme to emulate human driving in order to eliminate the difficulties associated with path planning. Backpropogation and functional-link networks have been studied in terms of training and recall capabilities. The networks are trained by real data obtained from vehicle-tracking live test runs.