Citation

Ghoul T, Sayed T. Accid. Anal. Prev. 2021; 162: e106389.

Copyright

(Copyright © 2021, Elsevier Publishing)

DOI

10.1016/j.aap.2021.106389

PMID

unavailable

Abstract

The proliferation of Connected Vehicles and their ability to collect a large amount of data presents an opportunity for the real-time safety optimization of traffic networks. At intersections, Adaptive Traffic Signal Control (ATSC) systems and dynamic speed advisories are among the proactive real-time safety interventions that can assist in preventing rear-end collisions. This study proposes a Signal-Vehicle Coupled Control (SVCC) system incorporating ATSC and speed advisories to optimize safety in real-time. By applying a rule-based approach in conjunction with a Soft-Actor Critic RL framework, the system assigns speed advisories to platoons of vehicles on each approach and extends the current signal time accordingly. Dynamic traffic parameters are collected in real-time and are used to estimate the current conflict rate at the intersection, which is then used both as an input to the model and to evaluate performance. The system was tested on two different intersections modeled using real-world data through the simulation platform VISSIM. Traffic conflicts were reduced by 41-55%, and vehicle delay was reduced by 21-24%. The results also show that the system functions at lower levels of market penetration, with diminishing returns beyond 50% MPR. The proposed system presents an SVCC framework that is both effective and low in computational intensity to optimize safety at signalized intersections.

Language: en

Keywords

Adaptive traffic signal control; Connected vehicles; Reinforcement learning; Signal-vehicle coupled control; Speed advisory; Trajectory optimization