Predictive lane-keeping system for an autonomous vehicle

摘要

In this paper, a model predictive control lanekeeping system of an autonomous vehicle is proposed. The control algorithm was tested experimentally on a laboratory scaled model of the vehicle. The desired trajectory during the experiment was determined by computer vision. Using image processing the middle of the driving lane and the horizontal profile of the driving lane was recognized. The control algorithm on the vehicle model was implemented in Python and solved using OSQP mathematical programming solver.