Informed Traffic Signal Preemption for Emergency Vehicles

Auteurs-es

  • Ioana Silaghi Florida Institute of Technology
  • Zobaida Alssadi
  • Marius Silaghi

DOI :

https://doi.org/10.32473/flairs.37.1.135261

Mots-clés :

intelligent traffic control

Résumé

Emergency vehicle traffic light preemption systems are extended by using more detailed predicted trajectories to provide favorable changes of signals. The location of the emergency vehicle is tracked and traffic signals on the requested travel route are contacted and switched to become green in time, before the emergency vehicle reaches the selected intersection. The resulting time to destination obtained by our simulation is compared to a control simulation without preemption. In simulations, when an emergency vehicle reaches a red light, a delay of five seconds is considered to happen naturally to the vehicle’s journey due to preventive driving. The switching of colors requires an eight second green light warning, also for reasons of safety. According to the improvements shown by our simulations, given the number of seconds gained from the knowledge of trajectory details and information passing with the traffic lights, from the 356,000 out-of-hospital cardiac arrests in the United States per year, approximately 3,000 lives would be saved. This gain can also significantly decrease the anxiety and improve the mental health of surrounding involved participants including family, health workers, and other bystanders thereby improving the quality of services that health workers can provide. The change of lights exploits knowledge of compatibility between paths allowed by current default light combination and the path of the emergency vehicle to save essential security buffer seconds.

Téléchargements

Publié-e

2024-05-13

Comment citer

Silaghi, I., Alssadi, Z., & Silaghi, M. (2024). Informed Traffic Signal Preemption for Emergency Vehicles. The International FLAIRS Conference Proceedings, 37(1). https://doi.org/10.32473/flairs.37.1.135261

Numéro

Rubrique

Special Track: AI for Urban Traffic Control and Mobility