A Reinforcement Learning Based Adaptive Traffic Signal Control for Vehicular Networks

被引：0

作者：

Krishnendhu, S. P. ^{[1
]}

Reddy, Mainampati Vigneshwari ^{[1
]}

Basumatary, Thulunga ^{[1
]}

Mohandas, Prabu ^{[1
]}

机构：

[1] Natl Inst Technol, Intelligent Comp Lab, Dept CSE, Calicut, Kerala, India

来源：

PERVASIVE COMPUTING AND SOCIAL NETWORKING, ICPCSN 2022 | 2023年 / 475卷

关键词：

Adaptive traffic signal control; Safety optimization; Reinforcement learning; Traffic simulation; Multi objective reinforcement learning; Single objective reinforcement learning;

D O I：

10.1007/978-981-19-2840-6_42

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The congestion of urban traffic is becoming one of the serious issues with the increase in vehicles and population in cities. The static time traffic controlling system fails to manage traffic and leads to heavy congestion and crashes on roads. To improve traffic safety and efficiency proactively, this study proposes a Adaptive Traffic Signal Control (ATSC) algorithm to optimize efficiency and safety simultaneously. The ATSC works by learning the Optimal Control policy via Double Dueling Deep Q Network (3DQN). The proposed algorithm was trained and evaluated on simulated isolated intersection Simulation of Urban Mobility (SUMO). The results showed that the algorithm improves both traffic efficiency and safety compared with static time traffic control technique by 42%.

引用

页码：547 / 561

页数：15

共 50 条

[21] Evaluating reinforcement learning state representations for adaptive traffic signal control
Genders, Wade
Razavi, Saiedeh
9TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT 2018) / THE 8TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2018) / AFFILIATED WORKSHOPS, 2018, 130 : 26 - 33
[22] Multiobjective Reinforcement Learning for Traffic Signal Control Using Vehicular Ad Hoc Network
Duan Houli
Li Zhiheng
Zhang Yi
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2010,
[23] Multiobjective Reinforcement Learning for Traffic Signal Control Using Vehicular Ad Hoc Network
Duan Houli
Li Zhiheng
Zhang Yi
EURASIP Journal on Advances in Signal Processing, 2010
[24] Switching Policies based on Multi-Objective Reinforcement Learning for Adaptive Traffic Signal Control
Saiki, Takumi
Arai, Sachiyo
2022 61ST ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS (SICE), 2022, : 488 - 493
[25] Digital-Twin-Based Deep Reinforcement Learning Approach for Adaptive Traffic Signal Control
Kamal, Hani
Yanez, Wendy
Hassan, Sara
Sobhy, Dalia
IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (12): : 21946 - 21953
[26] Reinforcement Learning for Platooning Control in Vehicular Networks
Gomides, Thiago S.
Kranakis, Evangelos
Lambadaris, Ioannis
Viniotis, Yannis
IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 6856 - 6861
[27] Iterative learning based adaptive traffic signal control
Zheng, Yichen
Zhang, Yi
Hu, Jianming
Journal of Transportation Systems Engineering and Information Technology, 2010, 10 (06) : 34 - 40
[28] Deep Learning vs. Discrete Reinforcement Learning for Adaptive Traffic Signal Control
Shabestary, Soheil Mohamad Alizadeh
Abdulhai, Baher
2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2018, : 286 - 293
[29] Deep Reinforcement Learning-based Traffic Signal Control
Ruan, Junyun
Tang, Jinzhuo
Gao, Ge
Shi, Tianyu
Khamis, Alaa
2023 IEEE INTERNATIONAL CONFERENCE ON SMART MOBILITY, SM, 2023, : 21 - 26
[30] Traffic signal control method based on deep reinforcement learning
Liu Z.-M.
Ye B.-L.
Zhu Y.-D.
Yao Q.
Wu W.-M.
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2022, 56 (06): : 1249 - 1256

← 1 2 3 4 5 →