Self-Organisation Theory Based Trajectory Optimisation Method for CAVs in Diverging Area

The highway diverging area is a crucial zone for highway traffic management. This study proposes an evaluation method for traffic flow operations in the diverging area within an Intelligent and Connected Environment (ICE), where the application of Connected and Automated Vehicles (CAVs) provides essential technical support. The diverging area is first divided into three road sections, and a discrete state transition model is constructed based on the discrete dynamic traffic flow model of these sections to represent traffic flow operations in the diverging area under ICE conditions. Next, an evaluation method for the self-organization degree of traffic flow is developed using the Extended Entropy Chaos Degree (EECD) and the discrete state transition model. Utilizing this evaluation method and the Deep Q-Network (DQN) algorithm, a short-term vehicle behavior optimization method is proposed, which, when applied continuously, leads to a vehicle trajectory optimization method for the diverging area over longer periods. Simulation results using the SUMO traffic simulation platform demonstrate that the proposed EECD indicator effectively replaces the Lyapunov Exponent (LE) as a measure of chaos in the diverging area. The optimization method based on this indicator reduces the degree of chaos in the traffic flow from 2.972 to 2.685 over time, resulting in smoother and more self-organized traffic flow. Additionally, the optimization improves average speed stability for some vehicles and reduces lane-changing behavior in the diverging area compared to outcomes without the optimization method.