Intersections are essential road infrastructures for traffic in modern metropolises; however, they can also be the bottleneck of traffic flows due to traffic incidents or the absence of traffic coordination mechanisms such as traffic lights. Thus, various control and coordination mechanisms that are beyond traditional control methods have been proposed to improve the efficiency of intersection traffic. Amongst these methods, the control of foreseeable hybrid traffic that consists of human-driven vehicles (HVs) and robot vehicles (RVs) has recently emerged.
We propose a decentralized reinforcement learning approach for the control and coordination of hybrid traffic at real-world, complex intersections--a topic that has not been previously explored. Comprehensive experiments are conducted to show the effectiveness of our approach. In particular, we show that using 5% RVs, we can prevent congestion formation inside the intersection under the actual traffic demand of 700 vehicles per hour. In contrast, without RVs, congestion starts to develop when the traffic demand reaches as low as 200 vehicles per hour. Further performance gains (reduced waiting time of vehicles at the intersection) are obtained as the RV penetration rate increases. When there exist more than 60% RVs in traffic, our method starts to outperform traffic signals on the average waiting time of all vehicles at the intersection. Our method is also robust against both blackout events and sudden RV percentage drops, and enjoys excellent generalizablility, which is illustrated by its successful deployment in two unseen intersections.
We reconstruct the intersection traffic in SUMO using the traffic data provided by the city of Colorado Springs, CO, USA.
LEFT: Congestion forms rapidly in traffic without RVs when the traffic lights are not working
RIGHT: Normal traffic flow coordinated by traffic lights.
BOTTOM: Traffic flow regulated with 50% RVs does not result in congestion.
Our policy is deployed without refinement on the unseen three-way intersection (RIGHT) and unseen four-way intersection (LEFT)
The result shows that, despite never having encountered this intersection topology and its traffic demand, our policy coordinates traffic well and prevents congestion.
@article{wang2023intersection,
title={Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections},
author={Wang, Dawei and Li, Weizi and Zhu, Lei and Pan, Jia},
journal={arXiv preprint arXiv:2301.05294},
year={2023}
}