Application of Deep Reinforcement Learning for Traffic Control of Road Intersection with Emergency Vehicles

The control of road intersection in presence of priority vehicles is central in terms of performance of the emergency scenarios optimal management. In this paper a study applying Deep Reinforcement Learning to the traffic light control of a road intersection is presented, also considering the presence of three classes of priority vehicles such as ambulances and police. A case study of a road intersection in the city of Bari is presented. The paper focuses on a high-level dynamics of traffic management, not considering low-level issues like communication and data transferring.