Cooperative control of self-learning traffic signal and connected automated vehicles for safety and efficiency optimization at intersections.

Cooperative control of intersection signals and connected automated vehicles (CAVs) possess the potential for safety enhancement and congestion alleviation, facilitating the integration of CAVs into urban intelligent transportation systems. This research proposes an innovative deep reinforcement learning-based (DRL) cooperative control framework, including signal and speed modules, to dynamically adapt signal timing and CAV velocities for traffic safety and efficiency optimization. Among the DRL-based signal modules, a traffic state prediction model is merged with the current state to augment characteristics and the agent-learning process. A multi-objective reward function is designed to evaluate safety and efficiency using a traffic conflict prediction model and vehicle waiting time. The double deep Q network (DDQN) model is used to design the agent observing the traffic state, learning the optimal signal control policy, and then inputting the signal phase into the speed module. Based on the green duration analysis and constraints of mixed traffic flow of CAVs and human-driven vehicles, a speed planning model is constructed to optimize CAVs' speed and alter traffic state, which in turn affects the agent's next signal decisions. The proposed framework is tested at isolated intersections simulated by two real-world intersections in Changsha, China. The results reveal the superiority of the proposed method over DRL-based traffic signal control (DRL-TSC) in terms of coverage speed and computation time. Compared to actuated signal control, adaptive traffic signal control, and DRL-TSC, the proposed method significantly optimizes traffic safety and efficiency across diverse intersections, temporal spans, and traffic demands. Furthermore, the advantage of the proposed method substantially amplifies with the increased CAV penetration, regardless of the intersection types.