Framework for simulation-based lane change control for autonomous vehicles

Abstract

Originally, decision and control of the lane change of the vehicle is on the human driver. It is mainly used to increase the individual's benefit such as decreasing travel time. However, the selfish decision on the lane-changing behavior can sometimes make a negative impact on the overall traffic flow. As autonomous vehicle technology develops, modeling lane changing action as well as lane changing decision making falls within the control category of autonomous vehicles. In this study, we focused on decision making of lane change for autonomous vehicles considering traffic flow, and accordingly, we propose a lane change control system considering whole traffic flow. The lane change control system predicts the future traffic situation using Cell Transmission Model and determines the lane change probability for each lane that minimizes the total time delay through the genetic algorithm. The lane change control system then provides the lane change probability to the vehicles. Performance evaluation of the proposed system in macroscopic simulation shows reduction in the overall travel time delay. The performance of proposed system is also evaluated in microscopic traffic simulation, evaluating the potential performance when it is applied to the actual traffic system: The maximum traffic flow was increased, and the congestion area was greatly reduced and the time required for individual vehicles was reduced.