Tactical Decision Making for Emergency Vehicles Based on a Combinational Learning Method

An increase in the response time of emergency vehicles (EVs) could lead to a loss of property and life. On this account, tactical decision making for EVs’ microscopic control remains an issue to be improved. In this paper, a rule-based avoiding strategy (AS) is devised, that common vehicles (CVs) in the prioritized zone ahead of EV should accelerate or change their lane to avoid it. A novel DQN method with speed-adaptive compact state space (SC-DQN) is put forward to fit in EVs’ high-speed features and in various road topologies. The execution of AS feedback and the input of SC-DQN are used as a combinational method. The following approach reveals that deep reinforcement learning (DRL) could complement rule-based AS in generalization and the rule-based AS could complement the stability of DRL. The combination could lead to less response time, lower collision rate, and smoother trajectory.