Multiple Intelligent Control Strategies for Travel-Time Reduction of Connected Emergency Vehicles

Travel-time reduction is a primary objective for managing connected emergency vehicles (CEVs) to save people's lives or put out a fire. With the integrity of internet of things (IoT) and connected autonomous vehicles (CAVs), it has been a research challenge to find a safe, reliable, and optimal strategy that not only minimizes the CEV's travel time but also lessens the undesirable side-effects on other road users. This article introduces multiple intelligent control strategies in one framework to boost the potential of CEVs traveling via multiple traffic intersections. The framework includes a path-planning mechanism adapting to sudden traffic delays, traffic signal preemption controller adapting to the urgency level associated with the emergency event, and a deep-learning model for CAVs to predict the time required for giving way to the CEV. All modules are implemented through a microscopic traffic simulation environment (PTV-VISSIM). This article holds significant implications for various scenarios involving CEVs and intelligent transportation systems (ITS). The path planning approach showcased notable improvements, reducing average path travel time by 9% when compared to existing benchmarks. The regression error for predicting the merging time of CAVs is minimized to be 0.4 second. Furthermore, the signal preemption controller demonstrated an important trade-off analysis between the level of intrusive preemption signal control and the undesired impacts on the traffic network. This finding enables traffic management authorities to make informed decisions regarding signal preemption strategies, considering both the travel time optimization for CEVs and the potential network-wide traffic impacts.