Development of simulation-based lane change control system for autonomous vehicles

Abstract

Originally, decision and control of the lane change of the vehicle was on the human driver. In previous studies, the decision-making of lane-changing of human driver was mainly used to increase the individual ’s benefit. However, the lane-changing behavior of these human drivers can sometimes have a bad influence on the overall traffic flow. As technology for autonomous vehicles develops, lane changing action as well as lane changing decision making fall within the control category of autonomous vehicles. However, since many of current lane-changing decision algorithms of autonomous vehicles are based on the human driver model, it is hard to know the potential traffic impact of such lane change. Therefore, in this study, we focused on decision making of lane change considering traffic flow, and accordingly, we study lane change control system considering whole traffic flow. In this research, the lane change control system predicts the future traffic situation through the cell transition model, one of the most popular macroscopic traffic simulation model, and determines the change probability of each lane that minimizes the total time delay through the genetic algorithm. The lane change control system then conveys the change probability to this vehicle. In the macroscopic simulation result, the proposed control system reduced the overall travel time delay. The proposed system is applied to microscopic traffic simulation, the oversaturated freeway traffic flow algorithm (OFFA), to evaluate the potential performance when it is applied to the actual traffic system. In the traffic flow - density, the maximum traffic flow has been shown to be increased, and the points in the congestion area has also been greatly reduced. Overall, the time required for individual vehicles was reduced.