A comparative study of vision-based lateral control strategies for autonomous highway driving

With the increasing speeds of modern microprocessors, it has become ever mo re common for computer-vision algorithms to find application in real-time c ontrol tasks. In this paper we present an analysis of the problem of steeri ng an autonomous vehicle along a highway based on the images obtained from a CCD camera mounted in the vehicle. We explore the effects of changing var ious important system parameters like the vehicle velocity, the look-ahead range of the vision sensor; and the processing delay associated with the pe rception and control systems. We also present the results of a series of experiments that were designed t o provide a systematic comparison of a number of control strategies. The co ntrol strategies that were explored include a lead-lag control law, a full- state linear controller and an input-output linearizing control law. Each o f these control strategies was implemented and tested at highway speeds on our experimental vehicle platform, a Honda Accord LX sedan.