Leveraging autonomous vehicles in mixed-autonomy traffic networks with reinforcement learning-controlled intersections

Development of new approaches to adaptive traffic signal control has received significant attention; an example is the reinforcement learning (RL), where training and implementation of an RL agent can allow adaptive signal control in real time, considering the agent’s past experiences. Furthermore, autonomous vehicle (AV) technology has shown promise to enhancing the traffic mobility at highways and intersections. In this paper, delayed action deep Q-learning is developed for a vehicle network with signalized intersections to control the signal phase. A model predictive control (MPC) scheme is proposed to allow AVs to adapt their speed. Several case studies that consider mixed autonomy are examined aiming at reducing network traffic and fuel consumption in the traffic network with multiple intersections. Simulation studies reveal that even with a few AVs in the network, the waiting time, fuel consumption, and the number of stop-and-go movements are significantly reduced, while the travel time is increased.