TY - GEN
T1 - Real-time traffic signal control using deep Q network in V2X environment
AU - Jung, Sangchul
AU - Lee, Seungjae
AU - Na, Sungyong
AU - Ku, Dongkyun
AU - Kim, Jooyoung
N1 - Publisher Copyright:
© 2018 Transportation Systems in the Connected Era - Proceedings of the 23rd International Conference of Hong Kong Society for Transportation Studies, HKSTS 2018. All rights reserved.
PY - 2018
Y1 - 2018
N2 - In urban networks which mainly controlled by the traditional fixed signal control system, it would be impossible to manage real-time traffic situations properly. Furthermore, the autonomous vehicles would be impossible to exhibit its own maximum performance in this traditionally controlled intersection. In this point, more efficient traffic management could be possible through the AI traffic signal controller based on the real-time information. In this paper, on the premise of V2X technology, the Python algorithm was developed which controls the traffic signal in real-time by learning the traffic flow information of a single intersection. In the reinforcement learning, a particular signal light is displayed based on the information of each flow movement iteratively. The reward corresponding to changes in the network situation is given, and the learning proceeds. Through this study, it is expected to be foundation for achieving the system optimal in complex urban transportation networks.
AB - In urban networks which mainly controlled by the traditional fixed signal control system, it would be impossible to manage real-time traffic situations properly. Furthermore, the autonomous vehicles would be impossible to exhibit its own maximum performance in this traditionally controlled intersection. In this point, more efficient traffic management could be possible through the AI traffic signal controller based on the real-time information. In this paper, on the premise of V2X technology, the Python algorithm was developed which controls the traffic signal in real-time by learning the traffic flow information of a single intersection. In the reinforcement learning, a particular signal light is displayed based on the information of each flow movement iteratively. The reward corresponding to changes in the network situation is given, and the learning proceeds. Through this study, it is expected to be foundation for achieving the system optimal in complex urban transportation networks.
KW - Artificial intelligence
KW - Reinforcement learning
KW - System optimum
KW - Traffic signal control
KW - V2x
UR - http://www.scopus.com/inward/record.url?scp=85064690721&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85064690721
T3 - Transportation Systems in the Connected Era - Proceedings of the 23rd International Conference of Hong Kong Society for Transportation Studies, HKSTS 2018
SP - 481
EP - 488
BT - Transportation Systems in the Connected Era - Proceedings of the 23rd International Conference of Hong Kong Society for Transportation Studies, HKSTS 2018
A2 - Gu, Weihua
A2 - Wang, Shuaian
PB - Hong Kong Society for Transportation Studies Limited
T2 - 23rd International Conference of Hong Kong Society for Transportation Studies: Transportation Systems in the Connected Era, HKSTS 2018
Y2 - 8 December 2018 through 10 December 2018
ER -
