A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data

Ramp metering that uses traffic signals to regulate vehicle flows from the on-ramps has been widely implemented to improve vehicle mobility of the freeway. Previous studies generally update signal timings in real-time based on predefined traffic measurements collected by point detectors, such as tra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bing Liu, Yu Tang, Yuxiong Ji, Yu Shen, Yuchuan Du
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Transportation engineering TA1001-1280 Transportation and communications HE1-9990
Acceso en línea:	https://doaj.org/article/0baf461d79f44bb9a8d2b843de871cb9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0baf461d79f44bb9a8d2b843de871cb9
record_format	dspace
spelling	oai:doaj.org-article:0baf461d79f44bb9a8d2b843de871cb92021-11-08T02:36:32ZA Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data2042-319510.1155/2021/6669028https://doaj.org/article/0baf461d79f44bb9a8d2b843de871cb92021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6669028https://doaj.org/toc/2042-3195Ramp metering that uses traffic signals to regulate vehicle flows from the on-ramps has been widely implemented to improve vehicle mobility of the freeway. Previous studies generally update signal timings in real-time based on predefined traffic measurements collected by point detectors, such as traffic volumes and occupancies. Comparing with point detectors, traffic cameras—which have been increasingly deployed on road networks—could cover larger areas and provide more detailed traffic information. In this work, we propose a deep reinforcement learning (DRL) method to explore the potential of traffic video data in improving the efficiency of ramp metering. Vehicle locations are extracted from the traffic video frames and are reformed as position matrices. The proposed method takes the preprocessed video data as inputs and learns the optimal control strategies directly from the high-dimensional inputs. A series of simulation experiments based on real-world traffic data are conducted to evaluate the proposed approach. The results demonstrate that, in comparison with a state-of-the-practice method, the proposed DRL method results in (1) lower travel times in the mainline, (2) shorter vehicle queues at the on-ramp, and (3) higher traffic flows downstream of the merging area. The results suggest that the proposed method is able to extract useful information from the video data for better ramp metering controls.Bing LiuYu TangYuxiong JiYu ShenYuchuan DuHindawi-WileyarticleTransportation engineeringTA1001-1280Transportation and communicationsHE1-9990ENJournal of Advanced Transportation, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Transportation engineering TA1001-1280 Transportation and communications HE1-9990
spellingShingle	Transportation engineering TA1001-1280 Transportation and communications HE1-9990 Bing Liu Yu Tang Yuxiong Ji Yu Shen Yuchuan Du A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
description	Ramp metering that uses traffic signals to regulate vehicle flows from the on-ramps has been widely implemented to improve vehicle mobility of the freeway. Previous studies generally update signal timings in real-time based on predefined traffic measurements collected by point detectors, such as traffic volumes and occupancies. Comparing with point detectors, traffic cameras—which have been increasingly deployed on road networks—could cover larger areas and provide more detailed traffic information. In this work, we propose a deep reinforcement learning (DRL) method to explore the potential of traffic video data in improving the efficiency of ramp metering. Vehicle locations are extracted from the traffic video frames and are reformed as position matrices. The proposed method takes the preprocessed video data as inputs and learns the optimal control strategies directly from the high-dimensional inputs. A series of simulation experiments based on real-world traffic data are conducted to evaluate the proposed approach. The results demonstrate that, in comparison with a state-of-the-practice method, the proposed DRL method results in (1) lower travel times in the mainline, (2) shorter vehicle queues at the on-ramp, and (3) higher traffic flows downstream of the merging area. The results suggest that the proposed method is able to extract useful information from the video data for better ramp metering controls.
format	article
author	Bing Liu Yu Tang Yuxiong Ji Yu Shen Yuchuan Du
author_facet	Bing Liu Yu Tang Yuxiong Ji Yu Shen Yuchuan Du
author_sort	Bing Liu
title	A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
title_short	A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
title_full	A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
title_fullStr	A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
title_full_unstemmed	A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
title_sort	deep reinforcement learning approach for ramp metering based on traffic video data
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/0baf461d79f44bb9a8d2b843de871cb9
work_keys_str_mv	AT bingliu adeepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yutang adeepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yuxiongji adeepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yushen adeepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yuchuandu adeepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT bingliu deepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yutang deepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yuxiongji deepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yushen deepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata AT yuchuandu deepreinforcementlearningapproachforrampmeteringbasedontrafficvideodata
_version_	1718443066439761920

A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data

Ejemplares similares