Journal of Transportation Engineering and Information

[Background] Existing methods for setting tidal lanes mainly focus on flat citiesanddo not specifically consider the complex terrain of mountainous cities. Moreover, most studies concentrate on optimizing single-lane control, with insufficient exploration of the collaborative control of multiple tidal lanes.[Objective] Propose a method for establishing tidal lanes in mountainous cities,aiming to alleviate the one-way traffic congestion caused by tidal phenomena by optimizing lane position selection, lane number allocation, and collaborative control. [Methods] Candidate sections for tidal lane settings were identified based on constraints related to road conditions and traffic flow characteristics. A bi-level programming model was developed to minimize the total network operational cost and optimize traffic flow distribution. The genetic algorithms and Frank-Wolfe algorithms were used to solve the model and determine tidal lanes location and allocation. Furthermore, a tidal lane correlation partitioning model was established by quantifying the degree of path correlation between adjacent intersections, thereby achieving collaborative control of tidal lanes.[Results] Simulation analyses of a road network in a specific area of Chongqing showedthat after the implementation of tidal lanes, the directional imbalance coefficient is reduced by 3.04%, and the saturation is reduced by 4.19%, effectively alleviating the congestion caused by tidal traffic.[Application] The proposed method provides support for traffic management of tidal lanes in mountainous cities and offers guidance for optimizing network operation efficiency.

Issue 02 ,2025 v.23 ;
[Downloads: 203 ] [Citations: 0 ] [Reads: 5 ] PDF Cite this article

Effect of built environment considering interaction effect on spatiotem poral differentiation of online car-hailing trips

MAO Xinbo;GAO Ge;LI Tian;CHEN Rong;PAN Fahui;LIU Shuo;

[Objective] To investigate the interactive effects of different built-environment factors on online ride-hailing trips and to clarify the effects of significant factors on the spatial heterogeneity of online ride-hailing trips. [Data] Didi travel data and multisource geospatial data(worldpop population data, road network data, grid GDP(Gross Domestic Product) data, and POI(Point of Interest) data) from Haikou are used to construct the built-environment indicators from six dimensions: density,design, diversity, distance to transit, destination accessibility, and socioeconomic attributes. [Methods] First, an optimal parameter geographic detector model(OPGD) is used to analyze the independent and interactive effects of factors on online ride-hailing trips. Subsequently, spatial autocorrelation and multiscale geographically weighted regression(MGWR) models are used to identify the spatiotemporal heterogeneity of the built environment on online ride-hailing trips during different periods on weekdays and weekends. [Conclusions] The OPGD model shows that mixed-land use and per capita GDP minimally affect online ride-hailing trips, and that the interaction between catering,residential areas, and other factors can significantly improve the explanatory power of the effect on online ride-hailing trips. The MGWR model identifies significant influencing factors that exhibit clear spatial heterogeneity in their effect on online ride-hailing trips. [Application] The results can provide suggestions for urban management and planners and support the optimization of online ridehailing travel.

Issue 02 ,2025 v.23 ;
[Downloads: 327 ] [Citations: 0 ] [Reads: 3 ] PDF Cite this article

Evaluation method for accessibility of public transport stations from the full chain perspective of residential travel

LU Xiaolin;PAN Shuliang;YAN Shuang;

[Background] The rationality of the spatial layout of public transport stations is of great significance for improving the quality of urban public services and enhancing the residents' quality of life.However, existing methods rarely analyze the temporal characteristics of station accessibility from the perspective of the full chain of residential travel. [Objective] This study aimed to investigate an evaluation method for public transport station accessibility from the perspective of residential travel, considering multiple travel periods and travel time thresholds for station area and inter-station connections. [Methods] First, a public transport travel cumulative opportunity model was established under scenarios of multiple travel periods and travel time thresholds to quantitatively evaluate origin-based and destination-based accessibility of stations at both station area and inter-station levels. Second, a station attraction indexcalculation method was designed to represent the accessibility characteristics of public transport stations across multiple travel periods and multilevel travel time thresholds. The station attraction index was introduced into the residential travel station selection probability formula, and the 3-Step Floating Catchment Area method(3SFCA) was improved to conduct a multiscale analysis of the dynamic spatial-temporal accessibility distribution characteristics of public transport stations. [Data] Taking public transport stations on the Binhai Middle Road in Yantai City as a case study, multiperiod public transport travel data were obtained using theAmap.[Results](1) Under different travel periods and travel time threshold conditions, significant differences exist in the spatial-temporal distribution of accessibility at stations on Binhai Middle Road,which generally present a T-shaped distribution extending east-west along the coastline, with strong connections between the middle section and stations in the direction of Laishan District;(2) In terms of spatial-temporal distribution characteristics, all accessibility indicators for public transport stations exhibit a clear distribution pattern of higher accessibility during morning and evening peak hours,with strong dependence on station service capacity;(3) The results of spatial accessibility based on the perspective of supply-demand balance reveal an overall imbalance between station supply and residents' demand, with localized imbalances mainly concentrated in the eastern section, where public transport resources are relatively scarce.

Issue 02 ,2025 v.23 ;
[Downloads: 720 ] [Citations: 0 ] [Reads: 3 ] PDF Cite this article

Allocation of shared berths in rolling time domain considering heterogeneity of supply and demand

ZHUO Yunfeng;SHI Chaofeng;ZHANG Xi;

[Background] Existing information platforms for shared berth allocation cannot respond to dynamic random demands in real time and rarely allocate berths based on user requirements. Additionally, the platform's income can be further optimized. [Objective] To construct and solve a rolling time-domain allocation model for shared berths while considering the heterogeneity of supply and demand to optimize the allocation of parking resources and maximize total social benefits.[Methods] Based on the classical shared-berth allocation model framework, this study comprehensively considers the heterogeneity of parking supply and demand as well as low-carbon benefits. An“on-demand rental”strategy is devised and an artificial fish shoal-genetic algorithm is developed.Numerical simulation experiments are conducted using Matlab. [Data] The total number of parking spaces, the number of available berths, and the temporal and spatial characteristics of parking lots in the Good City Time residential district of Longhu City, Shapingba District, Chongqing, are investigated on-site. [Conclusions] The model achieves a berth turnover rate of approximately 80%, a user acceptance rate and a request period acceptance rate of approximately 90%, and a low-carbon income ratio of approximately 6.56%. Compared with the classical model, it reduces the parking-space rental cost significantly and offers more system benefits. Moreover, its turnover rate is similar to that of the classical parking-allocation model. Finally, a sensitivity-analysis experiment is performed,and the result shows that as demand increases, the revenue first increases and then decreases, the berth turnover rate changes from abrupt to stable, and the decline in the user acceptance rate and request-period acceptance rate increases gradually. [Applications] The findings of this study provide a theoretical reference for parking allocation and management decisions on shared platforms.

Issue 02 ,2025 v.23 ;
[Downloads: 198 ] [Citations: 0 ] [Reads: 3 ] PDF Cite this article

Long-term evolution of carpooling decisions and irrational behaviors based on interactive experiments

FU Quanlu;XIAO Lin;TIAN Ye;SUN Jian;

[Objective] This study aims to accurately depict the long-term carpooling decision-making behaviors of travelers in real-world scenarios, identify irrational psychological traits, and optimize incentive mechanisms and their effects. [Methods] An experimental framework and incentive mechanism based on a bottleneck model are developed. Additionally, long-term interactive experiments are conducted using prospect theory to analyze the evolution of carpooling decisions and irrational behaviors under differentiated incentive strategies. [Results] In incentive-based carpooling services, most travelers exhibit greater decision fluctuations when encountering potential losses, thus highlighting loss-aversion psychology, particularly among women with one to three years of driving experience, high income, fewer commuting days, and greater awareness of the incentive mechanism.By contrast, groups such as high-frequency commuters and highly educated, low-income individuals show no significant traits. Introducing a compensation mechanism for carpooling-matching failures further increases carpooling rates. [Conclusion] The findings confirm loss-and risk-averse behaviors in avoiding carpooling to mitigate potential costs(e. g., time delays and additional expenses).[Applications] Considering the heterogeneous irrational characteristics of travelers, refined adjustments to incentive strategies, including personalized incentive amounts, introduction of compensation mechanisms, improved feedback content, and enhanced matching algorithms, can be proposed to provide theoretical support and practical guidance for designing precise and effective carpooling incentive strategies.

Issue 02 ,2025 v.23 ;
[Downloads: 198 ] [Citations: 0 ] [Reads: 2 ] PDF Cite this article

Current issue statistical data more>>

Evaluation of the substitution potential of metro-integrated multimodal travel in the MaaS environment

LI Wenxiang;LIU Bo;YUAN Xuanyu;SHEN Ruitao;CHEN Peiyan;

[Background] An integrated Mobility-as-a-Service (MaaS) platform enables seamless connections between metro systems and other travel modes， significantly improving the accessibility and convenience of metro-integrated multimodal travel. This enhancement offers the potential to reduce reliance on private cars and thereby alleviate urban traffic congestion. [Objective] Using ride-hailing trips as a benchmark， this study assesses the substitution potential of metro-integrated multimodal travel under the MaaS environment and identifies the key factors influencing this substitution. [Method] First， based on the MaaS platform， the metro system is integrated with green travel modes such as conventional buses， shared bicycles， and ridesplitting to design ten types of metro-integrated multimodal travel substitution schemes， which are then matched to ride-hailing trips according to connection distances. Next， a comprehensive benefit evaluation method is proposed， incorporating economic gains， carbon reduction benefits， and time costs， to assess the substitution potential of metro-integrated multimodal travel. Finally， a CatBoost machine learning model is developed to predict the substitutability of ride-hailing trips under different conditions， and accumulated local effect plots (ALE) are used to explore the nonlinear effects of influencing factors. [Data] An empirical analysis is conducted using ride-hailing order data from Shanghai. [Results] The results show that approximately 56% of ride-hailing trips can be substituted by metro-integrated multimodal travel schemes， with the highest substitutability observed in central urban areas， exceeding 80%. Key factors affecting ride-hailing substitutability include ride-hailing travel distance， proportion of travel delay， substitution scheme type， distance of the metro-integrated multimodal trip， and built environment characteristics around origins and destinations. [Conclusions] The study confirms the substantial potential of metro-integrated multimodal travel to reduce dependence on private cars under the MaaS environment. It also provides evidence-based insights for policymakers to optimize MaaS systems and promote a higher share of urban public transportation.

Issue ;
[Downloads: 63 ] [Citations: 0 ] [Reads: 0 ] HTML PDF Cite this article

Analysis and modeling the factors of trust in human-machine interaction for intelligent and connected vehicles

LYU Nengchao;WANG Xinpeng;HUANG Jun;

[Background] The trust level in human-machine interaction (HMI) of intelligent connected vehicles (ICVs) is crucial for human-machine collaboration. Developing and designing a reasonable trust measurement scale and validating its effectiveness have become key focuses in subjective trust measurement research. [Objective] To develop a context-specific trust measurement scale， establish a structural equation model for trust， and explore the influencing factors of trust. [Method] By introducing the Technology Acceptance Model (TAM) and Situational Awareness Theory， the influencing factors of trust are categorized into five dimensions: human interaction object， human-machine interaction content， human-machine interaction method， system transparency， and system technical capability， and a model is constructed. Each dimension is further decomposed into 41 observable variables， and the model is empirically tested using AMOS 28 software. [Results] The results indicate that the model effectively reflects the impact paths of various factors on driver trust. [Conclusion] System technical capability and system transparency are the most direct and significant influencing factors of trust in ICVs. Additionally， system technical capability and human-machine interaction content influence trust through system transparency as a mediating variable. There are correlations among human interaction object， human-machine interaction method， and human-machine interaction content.

Issue ;
[Downloads: 243 ] [Citations: 0 ] [Reads: 0 ] HTML PDF Cite this article

Transit riders’ behavior status identification and evolution sequence prediction of the multimodal public transit systems

YU Chengcheng;LIN Haocheng;XU Lei;DONG Wentao;YANG Chao;

[Background] With the proliferation of private vehicles， the rise of shared mobility， and the evolving competition and cooperation dynamics within multimodal public transit systems， China’s urban public transit systems have faced critical challenges of declining ridership over the past decade. More concerningly， transit ridership decline risk evaluation methods and targeted rider churning prevention incentive strategies are still insufficient. Existing single-mode behavioral analysis frameworks are difficult to use to reveal the evolutionary patterns of multimodal transit user behavior. [Objective] This study has proposed an individual-level multimodal transit user behavior status evolution path prediction model to accurately identify early behavioral pattern transition signals， thereby providing decision-making support for transit service optimization. [Method] A multi-view attributed graph model (MAGM) is constructed to characterize individual multimodal trip chains， and consensus graph learning is employed to extract unified cross-modal behavioral representations. A deep embedding clustering module is designed to identify behavioral statuses， while a masked Transformer-based bidirectional encoder predicts individual-level behavioral evolution trajectories. [Data] The dataset includes 2.13 million travel records from 19 929 users in Shanghai’s multimodal transit platform (2023—2024)， augmented with spatiotemporal behavioral features derived from a two-stage alighting point inference algorithm and POI data. [Conclusions] Experiments demonstrate that the proposed model achieves an accuracy of 84.0%， outperforming traditional methods by 12.3%. The study reveals the phased characteristics of user attrition paths in multimodal transit behavior evolution， notably the “travel frequency decline-regularity reduction” sequence， and identifies “travel mode transitions” as a preceding signal to this attrition process. These findings provide a framework for high-risk user identification and evidence for optimizing multimodal collaborative intervention strategies in urban transit systems.

Issue ;
[Downloads: 55 ] [Citations: 0 ] [Reads: 0 ] HTML PDF Cite this article

Spatiotemporal impact analysis of lane changing: perspectives on traffic safety， efficiency， and fuel consumption

[Background] Lane-changing， as a crucial micro-level behavior in vehicle operation， plays a significant role in traffic flow. Understanding its spatiotemporal impact is essential for effective traffic management optimization. However， existing studies primarily focus on the instantaneous effects of lane-changing， neglecting its sustained influence over time and space， resulting in incomplete quantification of its impact on traffic flow. [Objective] This study aims to reveal the multidimensional impacts of discretionary lane-changing on the safety， efficiency， and fuel consumption of upstream traffic in both the original and target lanes， providing a theoretical foundation for optimizing driver lane-changing decisions and traffic management strategies. [Method] A framework of "data processing—spatiotemporal impact definition—construction of multidimensional evaluation metrics—statistical analysis" is used. Combining metrics such as Time Exposed Time-to-Collision (TET)， fuel consumption， and Edie's generalized flow， the study quantitatively analyzes the spatiotemporal impact of a single lane change. [Data] Empirical analysis is conducted using the open-source Zen Traffic Data (ZTD) dataset， which includes 16 hours of vehicle trajectory data from three typical highway two-lane segments: Ikeda Route 11， Wangan Route 4， and Higashiosaka Route 13 in Japan. Vehicles follow the keep-left traffic rule. The right lane is the passing lane and the left lane is the driving lane. [Conclusions] The study shows that lane changes have different impacts depending on lane type (left vs. right) and target lane. Lane changes from the right to the left cause a significantly higher safety impact on upstream vehicles in the original lane compared to lane changes from the left to the right， while lane changes from the left to the right pose higher safety risks to upstream vehicles in the target lane than lane changes from the right to the left. Additionally， lane changes from the right to the left demonstrate a greater potential for reducing fuel consumption than lane changes from the left to the right. Moreover， despite the safety risks， lane changes exhibit a flow gain effect， increasing the flow rates by 2.51% and 5.17% in the original and target lanes. Regarding fuel consumption， most lane change behaviors contribute to reducing fuel consumption for upstream vehicles both in the original and target lanes. [Application] The proposed method for quantifying the spatiotemporal impacts of lane-changing can support autonomous vehicle lane-changing decision algorithms. By predicting the real-time effects of lane changes on surrounding vehicles， autonomous vehicles can make more rational lane-changing decisions that minimize disruptions while optimizing traffic flow.

Issue ;
[Downloads: 79 ] [Citations: 0 ] [Reads: 0 ] HTML PDF Cite this article

Behavioural models of travel mode choice integrating the impact of the walking environment

DENG Ying;CHEN Jian;GAO Jianjie;WANG Yongxuan;CHEN Qi;

【 Objective 】 The behavior model of travel mode choice is an important tool for understanding and predicting residents' travel decisions. As an important component of urban transportation systems， the quality of pedestrian environment directly affects residents' travel experience and the choice of conventional public transportation， rail transit and other modes. The aim is to analyze the impact mechanism of pedestrian environment on urban residents' travel mode choice. However， existing research has not fully considered the quantitative impact of pedestrian environment on residents' travel intentions， and the quantification of pedestrian environment lacks a common representation of subjective and objective indicators. 【 Method 】 By introducing 9 latent variables such as subjective norms， attitudes， and walking environment to more accurately depict the psychological decision-making process of different travel mode choice behaviors， innovative image recognition technology and personal subjective perception indicators are applied to jointly characterize the walking environment variables. Structural equation modeling is used to characterize the interrelationships between various psychological latent variables， as well as the relationships between the 9 latent variables and their corresponding measurement variables. A mixed model of travel mode choice behavior that integrates the influence of walking environment is constructed to improve the predictive accuracy and explanatory power of the model on travelers' decision-making behavior. 【 Results 】 Taking travelers in the central urban area of Chongqing as an example， the results showed that the walking environment had the greatest impact on the choice of walking mode (0.665)， followed by the impact on conventional public transportation (0.663)， rail transit (0.384)， and cars (0.304). In addition， the goodness of fit of the SEM-MNL model considering latent variables such as walking environment increased from 0.2752 to 0.4544， indicating that the model incorporating walking environment has stronger interpretability. The research results can deepen the understanding and grasp of urban residents' travel mode choice behavior， improve the urban walking environment， and lay a good theoretical foundation for enhancing residents' green travel willingness.

Issue ;
[Downloads: 107 ] [Citations: 0 ] [Reads: 0 ] HTML PDF Cite this article

more>>

Optimization Model of Reverse Logistics Network Design for Remanufacturing

MA Zu-jun1 ZHANG Dian-ye1 DAI Ying2 \ 1.College of Traffic and Transportation; \ 2.College of Economics and Management; \ Southwest Jiaotong University, Chengdu 610031, China

Based on presenting the functions of logistics systems for remanufacturing, the topology of logistics networks for remanufacturing is analyzed. An optimization model relying on mixed integer linear programming (MILP) is proposed for designing reverse logistics networks for remanufacturing by extending an existing distribution network. The objective is to minimize the sum of investment and operational costs of various logistics facilities for remanufacturing as well as transportation costs of returned products among the facilities.

Issue 02 ,2004 ;
[Downloads: 1,521 ] [Citations: 208 ] [Reads: 33 ] HTML PDF Cite this article

Relationship Between Information Quantum of Traffic Guide Sign and Its Cognition

LIN Yu1,2 PAN Xiao-dong1 FANG Shou-en1 1.Key Laboratory of Road and Traffic Engineering at Tongji University,Ministry of Education, Shanghai 200092,China; 2.Department of Civil Engineering, Anhui University of Science and Technology, Huainan 232001,Anhui,China

Resorting to large numbers of indoor experiments applying EMR-8B as experimental apparatus, and getting the cognition time of traffic signs with different information quantum through recording the residence time of the object’s eye mark on traffic signs played by projection, the paper develops the quantitive relationship between the information quantum of traffic guide sign and its cognition time. The increase tendency of cognition time can keep balance with the characters of road name under 17 and the number of road names under 6. Traffic guide sign designing should accord with such norm(characters of road name under 17 and number of road name under 6).

Issue 03 ,2005 ;
[Downloads: 1,263 ] [Citations: 158 ] [Reads: 28 ] HTML PDF Cite this article

Study on the Urban Land Use Pattern Based on Transit Oriented Development(TOD)

LIN Yan DENG Wei GE Liang Transportation College, Southeast University,Nanjing 210096,China

TOD is considered as a rational strategy for urban land use and transportation development, which is the best annotation about how to integrate the land use with transport. Connotation of TOD, such as, its planning idea and implement principles, is presented in detail. The transport demand prediction model of TOD is founded, and a suitable land use pattern based on TOD is proposed.

Issue 04 ,2004 ;
[Downloads: 3,702 ] [Citations: 135 ] [Reads: 22 ] HTML PDF Cite this article

Research Progress of Short Term Traffic Flow Prediction Methods

LU Hai-ting ZHANG Ning HUANG Wei XIA Jing-xin Intelligent Transportation System Engineering Research Centre,the Ministry of Education of China,Southeast University,Nanjing 210096,China

Real-time,accurate and efficiency short term traffic flow prediction is one of the key technologies to realize traffic flow guidance and traffic control,which has being widely concerned in the domain of ITS during recent years.Firstly,the attributes and requirements of traffic flow were introduced in this paper.Then,the prediction methods were fallen into 4 categories:linear,nonlinear,hybrid,and traffic flow based.The present forecasting models' advantages and disadvantages were summarized and commented at the same time.Subsequently,the hot topics in the field of traffic flow prediction were also discussed.Finally,the future research direction is pointed out.

Issue 04 ,2009 v.7;No.26 ;
[Downloads: 1,742 ] [Citations: 121 ] [Reads: 20 ] HTML PDF Cite this article

Architecture Analysis of Common Information Platform for Intelligent Trasportation Systems (ITS) and Its Construction Means

SHI Qi-xin ZHENG Wei-zhong Institute of Transportation Engineering, Tsinghua University, Beijing 100084,China

This paper proposes a basic architecture of ITS common information platform based on information processing and data mining, and analyses its function structure, construction means and key technology in the platform construction process. According to the integrated target of ITS common information platform, this paper not only presentsa whole architecture design of ITS common information platform, its function structure and the function requirement, but also analyses some key technology in constructing process, such as, link design of information resource, the information standard, GIS platform, middle ware system based on the CORBA technology, data mining and data warehousetechnology, users service software development and security, and so on.

Issue 01 ,2003 ;
[Downloads: 989 ] [Citations: 102 ] [Reads: 23 ] HTML PDF Cite this article

more>>

Discussion of the Gravity Center Method for the Selection of Logistics Distribution Center Location

CHENG Heng1 MOU rui-fang1 School of Traffic and Transportation,Southwest Jiaotong University,Chengdu 610031,China

Selection of logistics distribution center location is one important link in modern logistics system planning.Among site selection methods,the most common is the gravity center method.But,there are some neglected problems in using this method,one is how to introduce the gravity center method;the other is whether the final iteration scheme is the best? In this paper the introduction and the derivation of the formula were discussed in detail,the corresponding improvement was made for the previous iterative scheme.

Issue 01 ,2013 v.11;No.39 ;
[Downloads: 4,154 ] [Citations: 63 ] [Reads: 26 ] HTML PDF Cite this article

Study on the Urban Land Use Pattern Based on Transit Oriented Development(TOD)

LIN Yan DENG Wei GE Liang Transportation College, Southeast University,Nanjing 210096,China

Issue 04 ,2004 ;
[Downloads: 3,702 ] [Citations: 135 ] [Reads: 22 ] HTML PDF Cite this article

Review of autonomous vehicle simulators: capabilities, challenges,and development directions

ZHANG Kunpeng;CHANG Cheng;WANG Shipu;ZHANG Zuo;LI Li;Department of Automation, Tsinghua University;College of Electrical Engineering,Henan University of Technology;

Simulators play a crucial role in the research, development, and validation of autonomous vehicle(AV) systems. This review systematically explores the current status of AV simulators both domestically and internationally, focusing on their capabilities, challenges, and future development trends. First, the development history of AV simulators is reviewed and the current state of related research at home and abroad is elaborated. second, a comprehensive evaluation of various simulators is conducted based on technical, functional, performance, and commercial indicators, while discussing their applicability in different research and development tasks. In addition, this review delves into the challenges and constraints faced by AV simulators. Combining the development of advanced technologies such as deep learning and artificial intelligence, targeted solutions are proposed. A series of forward-looking solutions are presented to overcome the limitations of AV simulators in complex environments and diverse scenarios. Consequently, this review emphasizes the opportunities and emerging trends in future research, which will lay the foundation for the development of the next generation of simulators. Finally, this review aims to provide valuable guidance for researchers, developers,and industry stakeholders, helping them choose the tools that best suit their needs and stimulate the innovation potential of the autonomous driving field. The content of this review contributes to the promotion of AV simulators in autonomous driving research and practical applications, thereby providing a safer, more convenient, and efficient travel experience for humanity.

Issue 01 ,2024 v.22;No.83 ;
[Downloads: 3,428 ] [Citations: 11 ] [Reads: 31 ] HTML PDF Cite this article

Overview of Reinforcement Learning-based Urban Traffic Signal Control

XU Dong-wei;ZHOU Lei;WANG Da;DING Jia-li;WEI Chen-chen;

The conventional model-driven adaptive traffic signal control system has low flexibility and is difficult to meet the control requirements of the current complex and changeable traffic system. In recent years, the urban traffic signal control methods based on deep reinforcement have shown rapid developments with certain advantages compared to traditional methods. Traffic signal control plays a vital role in urban traffic management;hence, traffic signal control based on deep reinforcement learning has high research values and implications. This paper systematically presents the basic theory of deep reinforcement learning and its application in traffic signal control systems, including single-intersection independent control and multi-intersection coordinated control.The classification introduction and analysis of the advantages and disadvantages of existing models are outlined.The main body of the paper includes the models and research results for single-intersection signal control and multi-intersection coordinated control based on deep reinforcement learning and the simulation environment used to evaluate traffic signal control models. Finally, open problems of the traffic signal control system based on deep reinforcement learning and its practical application challenges are highlighted. The main future developmental directions of this field are proposed. The findings report in this paper can provide references for scholars in intelligent transportation and play positive roles in intelligent traffic signal control.

Issue 01 ,2022 v.20 ;
[Downloads: 3,311 ] [Citations: 58 ] [Reads: 19 ] HTML PDF Cite this article

Chinese public attitudes to and research prospects of autonomous mobility services——Comment on the world's largest“Apollo Go”experiment

QI Hang;WANG Guangchao;ZHANG Yunsheng;DUAN Honglei;SANG Jinyan;QIN Duan;HE Zhengbing;

Online public sentiment through social media has emerged as a data-driven research method. This study explores an approach to promoting scientific research through public-opinion analysis.Baidu's“Apollo Go”was launched as the world's largest fully driverless commercial operation in Wuhan, China, which sparked intense social-media discussion after a minor traffic incident on July7th. First, this paper outlines the commercialization process of the“Apollo Go”platform in Wuhan.Subsequently, using the Baidu Index, we analyze the evolution of public attention toward“Apollo Go autonomous driving”and“robotaxis.”Subsequently, we conducted a word-cloud analysis and topic modelling on 1809 popular comments from Sina Weibo and TikTok, from which we identified four key themes of public concern: technological advancement, service experience, socioeconomic impact, and market competition. Finally, based on these concerns, we propose research directions for improving the societal compatibility of autonomous driving, the structure of the ride-hailing market and government regulations, employment transformation and social security systems, legal frameworks, and local legislation. The findings will help academics understand Chinese public attitudes toward autonomous ride-hailing services and provide guidance for shaping research agendas corresponding to societal demands, promoting technological innovation, and facilitate proactive risk management. Consequently, the development of a conducive social environment for new productivity drivers will be supported, thereby enhancing China's competitive position in the global autonomous mobility service sector.

Issue 04 ,2024 v.22 ;
[Downloads: 3,251 ] [Citations: 5 ] [Reads: 25 ] HTML PDF Cite this article

more>>

Journal Information

Founded in 2003, Quarterly

Competent Authority：Ministry of Education of PRC

Sponsor：Southwest Jiaotong University

Editor in Chief： LIU Xiaobo; HE Zhengbing

E-mail：jtt@swjtu.edu.cn

ISSN ：1672-4747

CN ：51-1652/U

U-JIF:2.479

Indexed

CSTPCD

Scopus

RECCSE

JST

CSTJ

CNKI

COJ

Author LoginSubmission
Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Peer ReviewCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Office WorkOnline Review
Online Communication with the Editorial Department

Download

2024-01-08

Page Views

Page visits total: 7,891

请选择需要下载的pdf数据

Journal of Transportation Engineering and Information

交通运输工程与信息学报