Proactive Longitudinal Control to Manage Disruptive Lane Changes of Human-Driven Vehicles in Mixed-Flow Traffic

Abstract

Connected and autonomous vehicles (CAVs) can be leveraged to enable cooperative platooning control to alleviate traffic oscillations. However, in the near future, CAVs and human-driven vehicles (HDVs) will coexist on roads, creating a mixed-flow traffic environment. In mixed-flow traffic, CAV platoons would inevitably encounter lane changes by HDVs in adjacent lanes. These lane changes can generate disturbances and oscillations upstream, jeopardizing the performance of platooning control. Hence, it is necessary to explore the interactions between CAVs and HDVs in the lane-change process, to analyze how CAVs can be used to manage disruptive lane changes of HDVs in mixed-flow traffic. This study proposes deep reinforcement learning-based proactive longitudinal control for CAVs to counteract disruptive HDV lane-change behaviors that can induce disturbances, such that the smoothness of traffic flow can be preserved in the platooning control process. Results from numerical experiments suggest that CAVs controlled by the proposed control strategy can effectively reduce the occurrence of disruptive lane-change maneuvers of HDVs to improve string stability performance in mixed-flow traffic. Further, the reliability of the proposed control strategy for different HDV driver types is illustrated.