Q_EDQ: Efficient path planning in multimodal travel scenarios based on reinforcement learning

IF 5.1 2区 工程技术 Q1 TRANSPORTATION Travel Behaviour and Society Pub Date : 2024-11-05 DOI:10.1016/j.tbs.2024.100943
{"title":"Q_EDQ: Efficient path planning in multimodal travel scenarios based on reinforcement learning","authors":"","doi":"10.1016/j.tbs.2024.100943","DOIUrl":null,"url":null,"abstract":"<div><div>Recently, Mobility as a Service (MaaS) has garnered increasing attention by integrating various modes of transportation to provide users with a unified travel solution. However, In multimodal transportation planning, we primarily face three challenges: Firstly, a multimodal travel network is constructed that covers multiple travel modes and is highly scalable. Secondly, the routing algorithm fully considers the dynamic and real-time nature of the multimodal travel process. Finally, a generalized travel cost objective function is constructed that considers the psychological burden of transfers on passengers in multimodal travel scenarios. In this study, we firstly constructed an integrated multimodal transport network based on graph theory, which covers four transport modes, namely, the metro, the bus, the car-sharing and the walking. Subsequently, by introducing a double-Q learning mechanism and an optimized dynamic exploration strategy, we propose a new algorithm, Q_EDQ, the algorithm aims to learn the globally optimal path as efficiently as possible, with faster convergence speed and improved stability. Experiments utilizing real bus and metro data from Xi’an, Shaanxi Province, were conducted to compare the Q_EDQ algorithm with traditional genetic algorithms. In the conducted four experiments, compared to the optimal paths planned by traditional genetic algorithms, the improved Q-algorithm achieved a minimum efficiency increase of 12.52% and a maximum of 35%. These results demonstrate the enhanced capability of the improved Q-algorithm to learn globally optimal paths in complex multimodal transportation networks. Compared to the classical Q algorithm, the algorithmic model in this study shows an average performance improvement of 10% to 30% in global optimal path search, as well as convergence performance including loss and reward values.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Travel Behaviour and Society","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214367X24002060","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 0

Abstract

Recently, Mobility as a Service (MaaS) has garnered increasing attention by integrating various modes of transportation to provide users with a unified travel solution. However, In multimodal transportation planning, we primarily face three challenges: Firstly, a multimodal travel network is constructed that covers multiple travel modes and is highly scalable. Secondly, the routing algorithm fully considers the dynamic and real-time nature of the multimodal travel process. Finally, a generalized travel cost objective function is constructed that considers the psychological burden of transfers on passengers in multimodal travel scenarios. In this study, we firstly constructed an integrated multimodal transport network based on graph theory, which covers four transport modes, namely, the metro, the bus, the car-sharing and the walking. Subsequently, by introducing a double-Q learning mechanism and an optimized dynamic exploration strategy, we propose a new algorithm, Q_EDQ, the algorithm aims to learn the globally optimal path as efficiently as possible, with faster convergence speed and improved stability. Experiments utilizing real bus and metro data from Xi’an, Shaanxi Province, were conducted to compare the Q_EDQ algorithm with traditional genetic algorithms. In the conducted four experiments, compared to the optimal paths planned by traditional genetic algorithms, the improved Q-algorithm achieved a minimum efficiency increase of 12.52% and a maximum of 35%. These results demonstrate the enhanced capability of the improved Q-algorithm to learn globally optimal paths in complex multimodal transportation networks. Compared to the classical Q algorithm, the algorithmic model in this study shows an average performance improvement of 10% to 30% in global optimal path search, as well as convergence performance including loss and reward values.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Q_EDQ:基于强化学习的多模式旅行场景中的高效路径规划
最近,"移动即服务"(MaaS)通过整合各种交通方式,为用户提供统一的出行解决方案,受到越来越多的关注。然而,在多模式交通规划中,我们主要面临三个挑战:首先,构建一个涵盖多种出行方式且具有高度可扩展性的多模式出行网络。其次,路由算法要充分考虑多模式出行过程的动态性和实时性。最后,构建了广义的出行成本目标函数,考虑了多式联运出行场景中换乘给乘客带来的心理负担。在本研究中,我们首先基于图论构建了一个综合多式联运网络,涵盖了地铁、公交、共享汽车和步行四种交通方式。随后,通过引入双 Q 学习机制和优化的动态探索策略,我们提出了一种新算法 Q_EDQ,该算法旨在尽可能高效地学习全局最优路径,具有更快的收敛速度和更高的稳定性。我们利用陕西省西安市的真实公交和地铁数据进行了实验,将 Q_EDQ 算法与传统遗传算法进行了比较。在所进行的四次实验中,与传统遗传算法规划的最优路径相比,改进的 Q 算法的效率最低提高了 12.52%,最高提高了 35%。这些结果表明,改进型 Q 算法在复杂的多式联运网络中学习全局最优路径的能力得到了增强。与经典 Q 算法相比,本研究中的算法模型在全局最优路径搜索以及包括损失和奖励值在内的收敛性能方面平均提高了 10% 至 30%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
9.80
自引率
7.70%
发文量
109
期刊介绍: Travel Behaviour and Society is an interdisciplinary journal publishing high-quality original papers which report leading edge research in theories, methodologies and applications concerning transportation issues and challenges which involve the social and spatial dimensions. In particular, it provides a discussion forum for major research in travel behaviour, transportation infrastructure, transportation and environmental issues, mobility and social sustainability, transportation geographic information systems (TGIS), transportation and quality of life, transportation data collection and analysis, etc.
期刊最新文献
Latent class approach to classify e-scooter non-users: A comparative study of Helsinki and Tokyo Q_EDQ: Efficient path planning in multimodal travel scenarios based on reinforcement learning Analysis of emotions of online car-hailing drivers under different driving conditions and scenarios Augmenting last-mile connectivity with multimodal transport: Do choice riders favor integrated bike taxi-bus service in metro cities? New insights into factors affecting the severity of autonomous vehicle crashes from two sources of AV incident records
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1