Poster: Can Traffic Lights and CAV Work Together using Deep Reinforcement Learning?

Guo, Jiaying; Shen, Wang

doi:10.1109/vnc52810.2021.9644681

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The information exchanged requires less than 100 Kbps transmission rate, which can be well handled using Vehicle-To-Vehicle (V2V) and Vehicle-To-Infrastructure (V2I) communication infrastructure, as their IEEE 802.11p standard supports a bandwidth of 3 Mbps to 20 Mbps [14]. This paper extends our previous work [15] with the following improvements: 1) CoTV is more scalable as the number of its controlled CAVs is significantly reduced. 2) The state and reward of CoTV DRL agents are simplified, thus leading to more efficient agent communication for easy deployment.…”

Section: Introductionmentioning

confidence: 74%

CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles Using Deep Reinforcement Learning

Guo

Cheng

Wang

2023

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

The target of reducing travel time only is insufficient to support the development of future smart transportation systems. To align with the United Nations Sustainable Development Goals (UN-SDG), a further reduction of fuel and emissions, improvements of traffic safety, and the ease of infrastructure deployment and maintenance should also be considered. Different from existing work focusing on optimizing the control in either traffic light signal (to improve the intersection throughput), or vehicle speed (to stabilize the traffic), this paper presents a multi-agent Deep Reinforcement Learning (DRL) system called CoTV, which Cooperatively controls both Traffic light signals and Connected Autonomous Vehicles (CAV). Therefore, our CoTV can well balance the reduction of travel time, fuel, and emissions. CoTV is also scalable to complex urban scenarios by cooperating with only one CAV that is nearest to the traffic light controller on each incoming road. This avoids costly coordination between traffic light controllers and all possible CAVs, thus leading to the stable convergence of training CoTV under the large-scale multi-agent scenario. We describe the system design of CoTV and demonstrate its effectiveness in a simulation study using SUMO under various grid maps and realistic urban scenarios with mixed-autonomy traffic.

show abstract

Section: Introductionmentioning

confidence: 74%