Autonomous Intersection Management by Using Reinforcement Learning

被引:4
|
作者
Karthikeyan, P. [1 ]
Chen, Wei-Lun [1 ]
Hsiung, Pao-Ann [1 ]
机构
[1] Natl Chung Cheng Univ, Dept Comp Sci & Informat Engn, Chiayi 621301, Taiwan
关键词
reinforcement learning; autonomous vehicles; traffic control; intersection; DRLAIM;
D O I
10.3390/a15090326
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Developing a safer and more effective intersection-control system is essential given the trends of rising populations and vehicle numbers. Additionally, as vehicle communication and self-driving technologies evolve, we may create a more intelligent control system to reduce traffic accidents. We recommend deep reinforcement learning-inspired autonomous intersection management (DRLAIM) to improve traffic environment efficiency and safety. The three primary models used in this methodology are the priority assignment model, the intersection-control model learning, and safe brake control. The brake-safe control module is utilized to make sure that each vehicle travels safely, and we train the system to acquire an effective model by using reinforcement learning. We have simulated our proposed method by using a simulation of urban mobility tools. Experimental results show that our approach outperforms the traditional method.
引用
下载
收藏
页数:22
相关论文
共 50 条
  • [1] Real-Time Intelligent Autonomous Intersection Management Using Reinforcement Learning
    Gunarathna, Udesh
    Karunasekera, Shanika
    Borovica-Gajic, Renata
    Tanin, Egemen
    2022 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2022, : 135 - 144
  • [2] Multi-Intersection Management for Connected Autonomous Vehicles by Reinforcement Learning
    Jin, Haiming
    Wei, Yifei
    Yang, Zhaoxing
    Liu, Zirui
    Fan, Guiyun
    2023 IEEE 43RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, ICDCS, 2023, : 649 - 659
  • [3] Fine-grained acceleration control for autonomous intersection management using deep reinforcement learning
    Mirzaei, Hamid
    Givargis, Tony
    2017 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTED, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI), 2017,
  • [4] Concurrent Optimization of Safety and Traffic Flow using Deep Reinforcement Learning for Autonomous Intersection Management
    Muthugama, Lakmal
    Xie, Hairuo
    Tanin, Egemen
    Karunasekera, Shanika
    Gunarathna, Udesh
    30TH ACM SIGSPATIAL INTERNATIONAL CONFERENCE ON ADVANCES IN GEOGRAPHIC INFORMATION SYSTEMS, ACM SIGSPATIAL GIS 2022, 2022, : 572 - 583
  • [5] Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning
    Wu, Yuanyuan
    Wang, David Z. W.
    Zhu, Feng
    TRANSPORTMETRICA A-TRANSPORT SCIENCE, 2023,
  • [6] A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios
    Liu, Yuqi
    Zhang, Qichao
    Zhao, Dongbin
    2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021), 2021,
  • [7] Achieving Autonomous Power Management Using Reinforcement Learning
    Shen, Hao
    Tan, Ying
    Lu, Jun
    Wu, Qing
    Qiu, Qinru
    ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2013, 18 (02)
  • [8] Intersection Crossing for Autonomous Vehicles based on Deep Reinforcement Learning
    Chen, Wei-Lun
    Lee, Kwan-Hung
    Hsiung, Pao-Ann
    2019 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW), 2019,
  • [9] Autonomous Household Energy Management Using Deep Reinforcement Learning
    Tsang, Nathan
    Cao, Collin
    Wu, Serena
    Yan, Zilin
    Yousefi, Ashkan
    Fred-Ojala, Alexander
    Sidhu, Ikhlaq
    2019 IEEE INTERNATIONAL CONFERENCE ON ENGINEERING, TECHNOLOGY AND INNOVATION (ICE/ITMC), 2019,
  • [10] Autonomous Delay Tolerant Network Management Using Reinforcement Learning
    Buzzi, Pau Garcia
    Selva, Daniel
    Net, Marc Sanchez
    JOURNAL OF AEROSPACE INFORMATION SYSTEMS, 2021, 18 (07): : 404 - 416