Reinforcement learning in transportation research: Frontiers and future directions

The development of reinforcement learning (RL) provides innovative solutions for various decision-making problems in transportation, often pertaining to integrating advanced vehicular technologies such as connected and autonomous vehicles and electric vehicles. This paper reviews transportation rese...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiongfei Lai, Zhenyu Yang, Jiaohong Xie, Yang Liu
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Multimodal Transportation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772586324000455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846137606013714432
author Xiongfei Lai
Zhenyu Yang
Jiaohong Xie
Yang Liu
author_facet Xiongfei Lai
Zhenyu Yang
Jiaohong Xie
Yang Liu
author_sort Xiongfei Lai
collection DOAJ
description The development of reinforcement learning (RL) provides innovative solutions for various decision-making problems in transportation, often pertaining to integrating advanced vehicular technologies such as connected and autonomous vehicles and electric vehicles. This paper reviews transportation research with RL-based methods over the recent decades. We start with a bibliometric analysis through extensive literature retrieval of 1030 papers from 1996 to 2023. We identify different research areas of RL in transportation, summarizing the most visited research problems. We find that, at the vehicle level, motion and route planning and energy-efficient driving problems have attracted the most attention. Meanwhile, adaptive traffic signal control and management have been the most visited problems at the network level. We discuss several potential future directions, including the migration of RL models from simulations to real-world cases, designing tailored control architectures for complex transportation systems, exploring explainable RL in transportation research to ensure transparency and accountability in decision-making processes, and integrating people and vehicles into transportation systems in a sustainable and equitable manner.
format Article
id doaj-art-c5a6cfa2996e417ab676766296abc3ad
institution Kabale University
issn 2772-5863
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Multimodal Transportation
spelling doaj-art-c5a6cfa2996e417ab676766296abc3ad2024-12-08T06:13:31ZengElsevierMultimodal Transportation2772-58632024-12-0134100164Reinforcement learning in transportation research: Frontiers and future directionsXiongfei Lai0Zhenyu Yang1Jiaohong Xie2Yang Liu3Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore, 117576, SingaporeDepartment of Industrial Systems Engineering and Management, National University of Singapore, Singapore, 117576, Singapore; Urban Transport Systems Laboratory (LUTS), Ecole Polytechnique F´ed´erale de, Lausanne (EPFL), Lausanne, CH-1015, SwitzerlandDepartment of Industrial Systems Engineering and Management, National University of Singapore, Singapore, 117576, SingaporeDepartment of Industrial Systems Engineering and Management, National University of Singapore, Singapore, 117576, Singapore; Department of Civil and Environmental Engineering, National University of Singapore, Singapore, 117576, Singapore; Corresponding author.The development of reinforcement learning (RL) provides innovative solutions for various decision-making problems in transportation, often pertaining to integrating advanced vehicular technologies such as connected and autonomous vehicles and electric vehicles. This paper reviews transportation research with RL-based methods over the recent decades. We start with a bibliometric analysis through extensive literature retrieval of 1030 papers from 1996 to 2023. We identify different research areas of RL in transportation, summarizing the most visited research problems. We find that, at the vehicle level, motion and route planning and energy-efficient driving problems have attracted the most attention. Meanwhile, adaptive traffic signal control and management have been the most visited problems at the network level. We discuss several potential future directions, including the migration of RL models from simulations to real-world cases, designing tailored control architectures for complex transportation systems, exploring explainable RL in transportation research to ensure transparency and accountability in decision-making processes, and integrating people and vehicles into transportation systems in a sustainable and equitable manner.http://www.sciencedirect.com/science/article/pii/S2772586324000455Reinforcement learningTransportation research frontiersLiterature reviewEmerging technologiesFuture applications
spellingShingle Xiongfei Lai
Zhenyu Yang
Jiaohong Xie
Yang Liu
Reinforcement learning in transportation research: Frontiers and future directions
Multimodal Transportation
Reinforcement learning
Transportation research frontiers
Literature review
Emerging technologies
Future applications
title Reinforcement learning in transportation research: Frontiers and future directions
title_full Reinforcement learning in transportation research: Frontiers and future directions
title_fullStr Reinforcement learning in transportation research: Frontiers and future directions
title_full_unstemmed Reinforcement learning in transportation research: Frontiers and future directions
title_short Reinforcement learning in transportation research: Frontiers and future directions
title_sort reinforcement learning in transportation research frontiers and future directions
topic Reinforcement learning
Transportation research frontiers
Literature review
Emerging technologies
Future applications
url http://www.sciencedirect.com/science/article/pii/S2772586324000455
work_keys_str_mv AT xiongfeilai reinforcementlearningintransportationresearchfrontiersandfuturedirections
AT zhenyuyang reinforcementlearningintransportationresearchfrontiersandfuturedirections
AT jiaohongxie reinforcementlearningintransportationresearchfrontiersandfuturedirections
AT yangliu reinforcementlearningintransportationresearchfrontiersandfuturedirections