Human‐centric multimodal deep (HMD) traffic signal control
Abstract Reinforcement learning (RL)‐based models have been widely studied for traffic signal control with objectives, such as minimizing vehicle delay and queue length, maximizing vehicle throughput, and improving road safety, through tailored reward designs. Despite the advancements in RL‐based si...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-04-01
|
Series: | IET Intelligent Transport Systems |
Subjects: | |
Online Access: | https://doi.org/10.1049/itr2.12300 |
_version_ | 1797852191216631808 |
---|---|
author | Leizhen Wang Zhenliang Ma Changyin Dong Hao Wang |
author_facet | Leizhen Wang Zhenliang Ma Changyin Dong Hao Wang |
author_sort | Leizhen Wang |
collection | DOAJ |
description | Abstract Reinforcement learning (RL)‐based models have been widely studied for traffic signal control with objectives, such as minimizing vehicle delay and queue length, maximizing vehicle throughput, and improving road safety, through tailored reward designs. Despite the advancements in RL‐based signal control models for car traffic, limited research focused on multimodal traffic (e.g. car, bus, pedestrian). The simplified environment of unimodal traffic restrains these models from applications in real‐world cases. In this paper, the authors propose an RL‐based human‐centric multimodal deep (HMD) traffic signal control method to coordinate multimodal traffic at an intersection, with the objective of minimizing the waiting time per capita for multiple traffic modes by taking consideration of the mode capacity to ensure social equity. The method is validated in the simulation of urban mobility (SUMO) simulation environment using real traffic data. The results show the superior performance of HMD over vehicle‐centric (VC) RL‐based methods and traditional signal control schemes. HMD reduces the waiting time per capita by up to 19.2% and 6.3% compared with the fixed timing and VC RL‐based methods. In addition, the experiment results show that the HMD method assigns a higher priority to public transport over low‐occupancy travel modes in passing through intersections compared with unimodal traffic signal control strategies. |
first_indexed | 2024-04-09T19:29:45Z |
format | Article |
id | doaj.art-42b3bb2612c74a70a826ef629d8574c9 |
institution | Directory Open Access Journal |
issn | 1751-956X 1751-9578 |
language | English |
last_indexed | 2024-04-09T19:29:45Z |
publishDate | 2023-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Intelligent Transport Systems |
spelling | doaj.art-42b3bb2612c74a70a826ef629d8574c92023-04-05T04:22:13ZengWileyIET Intelligent Transport Systems1751-956X1751-95782023-04-0117474475310.1049/itr2.12300Human‐centric multimodal deep (HMD) traffic signal controlLeizhen Wang0Zhenliang Ma1Changyin Dong2Hao Wang3Jiangsu Key Laboratory of Urban ITS Southeast University 2 Si Pai Lou Nanjing P. R. ChinaCivil and Architectural Engineering Department KTH Royal Institute of Technology Brinellvägen 23 Stockholm SwedenJiangsu Key Laboratory of Urban ITS Southeast University 2 Si Pai Lou Nanjing P. R. ChinaJiangsu Key Laboratory of Urban ITS Southeast University 2 Si Pai Lou Nanjing P. R. ChinaAbstract Reinforcement learning (RL)‐based models have been widely studied for traffic signal control with objectives, such as minimizing vehicle delay and queue length, maximizing vehicle throughput, and improving road safety, through tailored reward designs. Despite the advancements in RL‐based signal control models for car traffic, limited research focused on multimodal traffic (e.g. car, bus, pedestrian). The simplified environment of unimodal traffic restrains these models from applications in real‐world cases. In this paper, the authors propose an RL‐based human‐centric multimodal deep (HMD) traffic signal control method to coordinate multimodal traffic at an intersection, with the objective of minimizing the waiting time per capita for multiple traffic modes by taking consideration of the mode capacity to ensure social equity. The method is validated in the simulation of urban mobility (SUMO) simulation environment using real traffic data. The results show the superior performance of HMD over vehicle‐centric (VC) RL‐based methods and traditional signal control schemes. HMD reduces the waiting time per capita by up to 19.2% and 6.3% compared with the fixed timing and VC RL‐based methods. In addition, the experiment results show that the HMD method assigns a higher priority to public transport over low‐occupancy travel modes in passing through intersections compared with unimodal traffic signal control strategies.https://doi.org/10.1049/itr2.12300human‐centric controlmultimodal trafficreinforcement learningtraffic signal control |
spellingShingle | Leizhen Wang Zhenliang Ma Changyin Dong Hao Wang Human‐centric multimodal deep (HMD) traffic signal control IET Intelligent Transport Systems human‐centric control multimodal traffic reinforcement learning traffic signal control |
title | Human‐centric multimodal deep (HMD) traffic signal control |
title_full | Human‐centric multimodal deep (HMD) traffic signal control |
title_fullStr | Human‐centric multimodal deep (HMD) traffic signal control |
title_full_unstemmed | Human‐centric multimodal deep (HMD) traffic signal control |
title_short | Human‐centric multimodal deep (HMD) traffic signal control |
title_sort | human centric multimodal deep hmd traffic signal control |
topic | human‐centric control multimodal traffic reinforcement learning traffic signal control |
url | https://doi.org/10.1049/itr2.12300 |
work_keys_str_mv | AT leizhenwang humancentricmultimodaldeephmdtrafficsignalcontrol AT zhenliangma humancentricmultimodaldeephmdtrafficsignalcontrol AT changyindong humancentricmultimodaldeephmdtrafficsignalcontrol AT haowang humancentricmultimodaldeephmdtrafficsignalcontrol |