Colight: Learning network-level cooperation for traffic signal control

Hua Wei, Nan Xu, Huichu Zhang, Guanjie Zheng, Xinshi Zang, Chacha Chen, Weinan Zhang, Yanmin Zhu, Kai Xu, Zhenhui Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Cooperation among the traffic signals enables vehicles to move through intersections more quickly. Conventional transportation approaches implement cooperation by pre-calculating the offsets between two intersections. Such pre-calculated offsets are not suitable for dynamic traffic environments. To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication. Specifically, for a target intersection in a network, CoLight can not only incorporate the temporal and spatial influences of neighboring intersections to the target intersection, but also build up index-free modeling of neighboring intersections. To the best of our knowledge, we are the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. In experiments, we demonstrate that by learning the communication, the proposed model can achieve superior performance against the state-of-the-art methods.

Original languageEnglish (US)
Title of host publicationCIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages1913-1922
Number of pages10
ISBN (Electronic)9781450369763
DOIs
StatePublished - Nov 3 2019
Event28th ACM International Conference on Information and Knowledge Management, CIKM 2019 - Beijing, China
Duration: Nov 3 2019Nov 7 2019

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference28th ACM International Conference on Information and Knowledge Management, CIKM 2019
CountryChina
CityBeijing
Period11/3/1911/7/19

Fingerprint

Learning networks
Communication
Graph
Experiment
Road network
Modeling
Reinforcement learning

All Science Journal Classification (ASJC) codes

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Wei, H., Xu, N., Zhang, H., Zheng, G., Zang, X., Chen, C., ... Li, Z. (2019). Colight: Learning network-level cooperation for traffic signal control. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 1913-1922). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3357384.3357902
Wei, Hua ; Xu, Nan ; Zhang, Huichu ; Zheng, Guanjie ; Zang, Xinshi ; Chen, Chacha ; Zhang, Weinan ; Zhu, Yanmin ; Xu, Kai ; Li, Zhenhui. / Colight : Learning network-level cooperation for traffic signal control. CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. pp. 1913-1922 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{7ce3f8ea7a5d4607acced4f1f668b641,
title = "Colight: Learning network-level cooperation for traffic signal control",
abstract = "Cooperation among the traffic signals enables vehicles to move through intersections more quickly. Conventional transportation approaches implement cooperation by pre-calculating the offsets between two intersections. Such pre-calculated offsets are not suitable for dynamic traffic environments. To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication. Specifically, for a target intersection in a network, CoLight can not only incorporate the temporal and spatial influences of neighboring intersections to the target intersection, but also build up index-free modeling of neighboring intersections. To the best of our knowledge, we are the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. In experiments, we demonstrate that by learning the communication, the proposed model can achieve superior performance against the state-of-the-art methods.",
author = "Hua Wei and Nan Xu and Huichu Zhang and Guanjie Zheng and Xinshi Zang and Chacha Chen and Weinan Zhang and Yanmin Zhu and Kai Xu and Zhenhui Li",
year = "2019",
month = "11",
day = "3",
doi = "10.1145/3357384.3357902",
language = "English (US)",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "1913--1922",
booktitle = "CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management",

}

Wei, H, Xu, N, Zhang, H, Zheng, G, Zang, X, Chen, C, Zhang, W, Zhu, Y, Xu, K & Li, Z 2019, Colight: Learning network-level cooperation for traffic signal control. in CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 1913-1922, 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, 11/3/19. https://doi.org/10.1145/3357384.3357902

Colight : Learning network-level cooperation for traffic signal control. / Wei, Hua; Xu, Nan; Zhang, Huichu; Zheng, Guanjie; Zang, Xinshi; Chen, Chacha; Zhang, Weinan; Zhu, Yanmin; Xu, Kai; Li, Zhenhui.

CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. p. 1913-1922 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Colight

T2 - Learning network-level cooperation for traffic signal control

AU - Wei, Hua

AU - Xu, Nan

AU - Zhang, Huichu

AU - Zheng, Guanjie

AU - Zang, Xinshi

AU - Chen, Chacha

AU - Zhang, Weinan

AU - Zhu, Yanmin

AU - Xu, Kai

AU - Li, Zhenhui

PY - 2019/11/3

Y1 - 2019/11/3

N2 - Cooperation among the traffic signals enables vehicles to move through intersections more quickly. Conventional transportation approaches implement cooperation by pre-calculating the offsets between two intersections. Such pre-calculated offsets are not suitable for dynamic traffic environments. To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication. Specifically, for a target intersection in a network, CoLight can not only incorporate the temporal and spatial influences of neighboring intersections to the target intersection, but also build up index-free modeling of neighboring intersections. To the best of our knowledge, we are the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. In experiments, we demonstrate that by learning the communication, the proposed model can achieve superior performance against the state-of-the-art methods.

AB - Cooperation among the traffic signals enables vehicles to move through intersections more quickly. Conventional transportation approaches implement cooperation by pre-calculating the offsets between two intersections. Such pre-calculated offsets are not suitable for dynamic traffic environments. To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication. Specifically, for a target intersection in a network, CoLight can not only incorporate the temporal and spatial influences of neighboring intersections to the target intersection, but also build up index-free modeling of neighboring intersections. To the best of our knowledge, we are the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. In experiments, we demonstrate that by learning the communication, the proposed model can achieve superior performance against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85075432975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075432975&partnerID=8YFLogxK

U2 - 10.1145/3357384.3357902

DO - 10.1145/3357384.3357902

M3 - Conference contribution

AN - SCOPUS:85075432975

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 1913

EP - 1922

BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -

Wei H, Xu N, Zhang H, Zheng G, Zang X, Chen C et al. Colight: Learning network-level cooperation for traffic signal control. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2019. p. 1913-1922. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/3357384.3357902