For the emergency response, every second counts. Intersections are prone to congestion, which greatly hinders the fast response of emergency vehicles. Although emergency vehicles possess the privilege to run a red light, it can be unsafe, and a congested intersection will prevent the exercise of this privilege. When an emergency vehicle arrives, the greedy preemption scheme offers a green signal promptly until it leaves the intersection. This guarantees a fast emergency response in most cases. However, this scheme will lead to an adverse impact on vehicles of conflicting directions and may not work when there are other emergency vehicles traveling from conflicting directions simultaneously. Employing deep reinforcement learning techniques, recent studies have shown promising results for traffic signal control. In this work, we deliver an early attempt to control the traffic signal for emergency vehicles through deep reinforcement learning, which ensures an expeditious emergency response in various scenarios and alleviates the negative influence on the traffic efficiency of conflicting directions. We conduct realistic simulations using traffic data in a real-world network with multiple intersections on different testing parameters. The results verify the feasibility and effectiveness of our model and indicate that our method notably outperforms the other five baseline methods in terms of various performance metrics.
Read full abstract