Decision Making for Autonomous Vehicle at Single-Lane Road Under Uncertainties

Every year, the negligence of drivers leads to many accidents. According to World Health Organization, approximately 1.3 million people die each year due to road traffic crashes. Safety is the main factor driving the growth of demand for autonomous vehicles. When vehicles go on the road, decision-making plays a crucial role in the autonomous driving system. This paper proposes an approach based on the value-iteration for Markov Decision Process to train the autonomous car to drive appropriately on the single-track road. By following the optimal policy from value-iteration, the simulation on CARLO shows the results of decision-making for autonomous vehicles under a single-track road scenario. This work makes a contribution on decision-making for cars at single-lane road.