Study of reinforcement learning based dynamic traffic control mechanism

Zheng Zhang; Seung Jun Baek; Duck Jin Lee; Kil To Chong

doi:10.1007/978-94-007-6738-6_129

Study of reinforcement learning based dynamic traffic control mechanism

Zheng Zhang
, Seung Jun Baek
, Duck Jin Lee
, Kil To Chong^*

^*Corresponding author for this work

Mechanical Design Engineering

Xi'an Jiaotong University
Jeonbuk National University

Research output: Contribution to conference › Conference paper › peer-review

1 Scopus citations

Abstract

A traffic signal control mechanism is proposed to improve the dynamic response performance of a traffic flow control system in an urban area. The necessary sensor networks are installed in the roads and on the roadside upon which reinforcement learning is adopted as the core algorithm for this mechanism. A traffic policy can be planned online according to the updated situations on the roads based on all the information from the vehicles and the roads. The optimum intersection signals can be learned automatically online. An intersection control system is studied as an example of the mechanism using Q-learning based algorithm and simulation results showed that the proposed mechanism can improve traffic efficiently more than a traditional signaling system.

Original language	English
Title of host publication	Multimedia and Ubiquitous Engineering, MUE 2013
Pages	1047-1056
Number of pages	10
DOIs	https://doi.org/10.1007/978-94-007-6738-6_129
State	Published - 2013
Event	FTRA 7th International Conference on Multimedia and Ubiquitous Engineering, MUE 2013 - Seoul, Korea, Republic of Duration: 2013.05.9 → 2013.05.11

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	240 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	FTRA 7th International Conference on Multimedia and Ubiquitous Engineering, MUE 2013
Country/Territory	Korea, Republic of
City	Seoul
Period	13.05.9 → 13.05.11

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Cooperative vehicle-highway systems
Intelligent transportation system
Intersection signal control
Reinforcement learning
Traffic control mechanism

Quacquarelli Symonds(QS) Subject Topics

Engineering - Mechanical

Access to Document

10.1007/978-94-007-6738-6_129

Cite this

@inproceedings{bf11a2b75c6f4e3394e4054bc70d3f78,

title = "Study of reinforcement learning based dynamic traffic control mechanism",

abstract = "A traffic signal control mechanism is proposed to improve the dynamic response performance of a traffic flow control system in an urban area. The necessary sensor networks are installed in the roads and on the roadside upon which reinforcement learning is adopted as the core algorithm for this mechanism. A traffic policy can be planned online according to the updated situations on the roads based on all the information from the vehicles and the roads. The optimum intersection signals can be learned automatically online. An intersection control system is studied as an example of the mechanism using Q-learning based algorithm and simulation results showed that the proposed mechanism can improve traffic efficiently more than a traditional signaling system.",

keywords = "Cooperative vehicle-highway systems, Intelligent transportation system, Intersection signal control, Reinforcement learning, Traffic control mechanism",

author = "Zheng Zhang and Baek, \{Seung Jun\} and Lee, \{Duck Jin\} and Chong, \{Kil To\}",

year = "2013",

doi = "10.1007/978-94-007-6738-6\_129",

language = "English",

isbn = "9789400767379",

series = "Lecture Notes in Electrical Engineering",

pages = "1047--1056",

booktitle = "Multimedia and Ubiquitous Engineering, MUE 2013",

note = "FTRA 7th International Conference on Multimedia and Ubiquitous Engineering, MUE 2013 ; Conference date: 09-05-2013 Through 11-05-2013",

}

Zhang, Z, Baek, SJ, Lee, DJ & Chong, KT 2013, Study of reinforcement learning based dynamic traffic control mechanism. in Multimedia and Ubiquitous Engineering, MUE 2013. Lecture Notes in Electrical Engineering, vol. 240 LNEE, pp. 1047-1056, FTRA 7th International Conference on Multimedia and Ubiquitous Engineering, MUE 2013, Seoul, Korea, Republic of, 13.05.9. https://doi.org/10.1007/978-94-007-6738-6_129

TY - GEN

T1 - Study of reinforcement learning based dynamic traffic control mechanism

AU - Zhang, Zheng

AU - Baek, Seung Jun

AU - Lee, Duck Jin

AU - Chong, Kil To

PY - 2013

Y1 - 2013

N2 - A traffic signal control mechanism is proposed to improve the dynamic response performance of a traffic flow control system in an urban area. The necessary sensor networks are installed in the roads and on the roadside upon which reinforcement learning is adopted as the core algorithm for this mechanism. A traffic policy can be planned online according to the updated situations on the roads based on all the information from the vehicles and the roads. The optimum intersection signals can be learned automatically online. An intersection control system is studied as an example of the mechanism using Q-learning based algorithm and simulation results showed that the proposed mechanism can improve traffic efficiently more than a traditional signaling system.

AB - A traffic signal control mechanism is proposed to improve the dynamic response performance of a traffic flow control system in an urban area. The necessary sensor networks are installed in the roads and on the roadside upon which reinforcement learning is adopted as the core algorithm for this mechanism. A traffic policy can be planned online according to the updated situations on the roads based on all the information from the vehicles and the roads. The optimum intersection signals can be learned automatically online. An intersection control system is studied as an example of the mechanism using Q-learning based algorithm and simulation results showed that the proposed mechanism can improve traffic efficiently more than a traditional signaling system.

KW - Cooperative vehicle-highway systems

KW - Intelligent transportation system

KW - Intersection signal control

KW - Reinforcement learning

KW - Traffic control mechanism

UR - https://www.scopus.com/pages/publications/84880749573

U2 - 10.1007/978-94-007-6738-6_129

DO - 10.1007/978-94-007-6738-6_129

M3 - Conference paper

AN - SCOPUS:84880749573

SN - 9789400767379

T3 - Lecture Notes in Electrical Engineering

SP - 1047

EP - 1056

BT - Multimedia and Ubiquitous Engineering, MUE 2013

T2 - FTRA 7th International Conference on Multimedia and Ubiquitous Engineering, MUE 2013

Y2 - 9 May 2013 through 11 May 2013

ER -

Study of reinforcement learning based dynamic traffic control mechanism

Abstract

Publication series

Conference

UN SDGs

Keywords

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this