Transportation Research Part C-Emerging Technologies最新文献

{"title":"Real-time train regulation with passenger flow control in urban rail systems","authors":"Yotam Yatziv,&nbsp;Jack Haddad","doi":"10.1016/j.trc.2025.105223","DOIUrl":"10.1016/j.trc.2025.105223","url":null,"abstract":"<div><div>Passenger flow control is a critical aspect of urban rail system operations. In congested conditions, passenger demand can exceed the available train capacity, leaving some passengers at stations unable to board. This paper aims to enhance rail system performance under such disturbed scenarios. First, a model for train traffic and passenger dynamics is presented using a “discrete-event” approach. Discrete-event traffic models assess train departures from stations as events, without considering the time span between these events. A coupled model is formulated that integrates the relationship between train dwell times at stations and passenger accumulation at platforms, proposing control actions for both train traffic and station facilities.</div><div>A discrete-event model predictive control (DE-MPC) strategy is developed with a regulatory objective function and constraints related to safety, feasibility, and the limited capacities of trains and platforms. The objective function also accounts for the number of passengers at platforms to ensure effective flow management during the control period. However, implementing real-time control requires application on a “time-based” system. To bridge this gap, a new method using a virtual discrete-event system is introduced, allowing real-time measurements in a time-based system to be used for evaluating discrete-event states. This enables the application of virtual discrete-event model predictive control (VDE-MPC) on the time-based system, facilitating real-time regulation of passenger flow and train traffic.</div><div>Numerical examples demonstrate the effectiveness of the proposed control methods in both discrete-event and time-based frameworks.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105223"},"PeriodicalIF":7.6,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing last-mile delivery through crowdshipping on public transportation networks","authors":"Mikele Gajda ,&nbsp;Olivier Gallay ,&nbsp;Renata Mansini ,&nbsp;Filippo Ranza","doi":"10.1016/j.trc.2025.105250","DOIUrl":"10.1016/j.trc.2025.105250","url":null,"abstract":"<div><div>In this paper, we explore an innovative last-mile delivery paradigm that leverages commuters on public transportation (PT) networks as crowdshippers, creating a low-impact delivery model that minimizes environmental footprint while taking advantage of technological advancements, improved infrastructure, and the widespread use of electronic devices. At the beginning of each delivery service period, parcels are routed to selected PT stations by a delivery company, and assigned to a set of crowdshippers (commuters). These crowdshippers collect and deliver the parcels as part of their regular journeys through the PT network, without deviating from their usual routes. The delivery company ensures, through a backup service, the final delivery of parcels that do not reach their final destination. The problem looks for the optimal schedule and route for each parcel while minimizing overall delivery expenses. We call this problem the Public Transportation-based Crowdshipping Problem (PTCP).</div><div>We propose a compact Mixed Integer Linear Programming formulation strengthened with valid inequalities and develop an Adaptive Large Neighborhood Search to address large-scale instances. The experimental analysis, conducted on a large set of instances, shows the effectiveness of the proposed heuristic method when compared to the exact model solution. Sensitivity analysis reveals that crowdshipping and backup delivery costs significantly influence the total system cost.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105250"},"PeriodicalIF":7.6,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated mobile inventory and fleet management for an on-demand delivery system","authors":"C. Yang ,&nbsp;M.Y. Maknoon ,&nbsp;H. Jiang ,&nbsp;Sh. Sharif Azadeh","doi":"10.1016/j.trc.2025.105264","DOIUrl":"10.1016/j.trc.2025.105264","url":null,"abstract":"<div><div>This study introduces an optimization framework for deploying Mobile Fleet Inventories (MFIs) to address operational inefficiencies in on-demand delivery systems. Traditionally, these systems rely on stationary facilities to organize operations and manage resources. While stationary facilities provide stability and structured coverage, they are inherently rigid and struggle to adapt to the spatial and temporal fluctuations characteristic of urban service demand. By leveraging urban waterways, MFIs act as dynamic, mobile facilities, enabling real-time resource redistribution and offering greater flexibility to meet evolving demand patterns efficiently.</div><div>We formulate the problem as a mixed-integer linear programming model to optimize MFI deployment, minimizing total system costs. The model incorporates both capital investments (e.g., MFI leasing and docking infrastructure) and operational expenses (e.g., rider idle time). Key decisions include determining the optimal number, placement of MFIs, and fleet size. To validate the approach, we apply it to a meal delivery platform in Amsterdam, demonstrating its practicality and scalability. Results show that implementing MFIs reduces overall system costs by 17% and decreases rider idle time by 35% compared to stationary facility operations. These findings underscore the transformative potential of MFIs to enhance the efficiency, sustainability, and adaptability of on-demand delivery systems in urban settings.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105264"},"PeriodicalIF":7.6,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond vision: A unified transformer with bidirectional attention for predicting driver perceived risk from multi-modal data","authors":"Dongjie Liu ,&nbsp;Dawei Li ,&nbsp;Hongliang Ding ,&nbsp;Yang Cao ,&nbsp;Kun Gao","doi":"10.1016/j.trc.2025.105270","DOIUrl":"10.1016/j.trc.2025.105270","url":null,"abstract":"<div><div>Modeling driver perceived risk (or subjective risk) plays a critical role in improving driving safety, as different drivers often perceive varying levels of risk under identical conditions, prompting adjustments in their driving behavior. Driving is a complex activity involving multiple cognitive and perceptual processes, such as visual information, driver feedback, vehicle dynamics, and traffic and environmental conditions. However, existing models for subjective risk perception have yet to fully address the need for integrating multi-modal data. To address this gap, we present a Transformer-based model aimed at processing multimodal inputs in a unified manner to enhance the prediction of subjective risk perception. Unlike existing methodologies that extract features specific to each modality, it employs embedding layers to transform images, unstructured, and structured fields into visual and text tokens. Subsequently, bi-directional multimodal attention blocks with inter-modal and intra-modal attention mechanisms capture comprehensive representations of traffic scene images, unstructured traffic scene descriptions, structured traffic data, environmental statistics, and demographics. Experimental results show that the proposed unified model achieves superior predictive performance over existing benchmarks while maintaining reasonable interpretability. Furthermore, the model is generalizable, making it applicable to various multi-modal prediction tasks across different transportation contexts.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105270"},"PeriodicalIF":7.6,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A learning based pedestrian flow prediction approach with diffusion behavior","authors":"Weiming Mai,&nbsp;Dorine Duives,&nbsp;Serge Hoogendoorn","doi":"10.1016/j.trc.2025.105243","DOIUrl":"10.1016/j.trc.2025.105243","url":null,"abstract":"<div><div>In public spaces such as city centers, train stations, airports, shopping malls, and multi-modal hubs, accurately predicting pedestrian flow is crucial for effective crowd management e.g. congestion prevention and evacuation planning. Traditional microscopic simulation models offer fine-grained insights by simulating each pedestrian individually, but they are computationally intensive and typically used at the planning and design stage, making them unsuitable for real-time interventions in high-demand scenarios. Macroscopic models, on the other hand, reduce computational cost by aggregating pedestrian behavior and solving partial differential equations, but they typically require estimates of traffic states such as density and speed — quantities that are difficult to measure accurately in practice. Additionally, as the complexity of these physics-based models increases, their computational feasibility for real-time use becomes even more limited. Data-driven (machine learning) models provide a computationally efficient alternative, enhancing real-time prediction capabilities. However, they often require large historical datasets to generalize well, and their performance can degrade under out-of-distribution (OOD) conditions. Moreover, most black-box learning models lack interpretability and domain-specific insights, limiting their practical adoption. In this paper, we propose a novel pedestrian flow prediction model based on the theory of crowd diffusion. Our method estimates flow rates directly from sensor-observed data and infers both Origin–Destination (OD) demand and route choice probabilities to support real-time operations. To address the OOD challenge, we incorporate an online learning mechanism that continuously calibrates model parameters based on incoming observations.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105243"},"PeriodicalIF":7.6,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive safety performance testing for autonomous vehicles with adaptive importance sampling","authors":"Jingxuan Yang ,&nbsp;Zihang Wang ,&nbsp;Daihan Wang ,&nbsp;Yi Zhang ,&nbsp;Qiujing Lu ,&nbsp;Shuo Feng","doi":"10.1016/j.trc.2025.105256","DOIUrl":"10.1016/j.trc.2025.105256","url":null,"abstract":"<div><div>Efficient and accurate safety testing and evaluation are crucial for autonomous vehicles (AVs). Recent studies have utilized prior information, such as surrogate models, to enhance testing efficiency by deliberately generating safety-critical scenarios. However, discrepancies between this prior knowledge and actual AV performance can undermine their effectiveness. To address this challenge, adaptive testing methods dynamically adjust testing policies based on posterior information of AVs, such as testing results. Most existing approaches focus on adaptively optimizing testing policies during pre-tests, yet neglecting how to adapt the testing policies in the large-scale testing process that is required for unbiased safety performance evaluation. To fill this gap, we propose an adaptive testing framework that continuously optimizes testing policies throughout large-scale testing. Our approach iteratively learns AV dynamics through deep learning and optimizes testing policies based on the learned dynamics using reinforcement learning. To tackle the challenge posed by the rarity of safety-critical events, our method focuses exclusively on learning safety-critical states in both the dynamics learning and the policy optimization processes. Additionally, we enhance evaluation robustness by integrating multiple pre-trained testing policies and optimizing their combination coefficients. To accurately assess safety performance, we evaluate testing results obtained from various testing policies using adaptive importance sampling. Experimental validation in overtaking and unprotected left-turn scenarios demonstrates the significant evaluation efficiency of our method.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105256"},"PeriodicalIF":7.6,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hierarchical cooperative merging control strategy for the mixed traffic of CAVs and HDVs","authors":"Dian Jing ,&nbsp;Rongsheng Chen ,&nbsp;Enjian Yao ,&nbsp;Monica Menendez","doi":"10.1016/j.trc.2025.105230","DOIUrl":"10.1016/j.trc.2025.105230","url":null,"abstract":"<div><div>The interactions between vehicles in freeway merging zones can lead to traffic congestion and potential collision risks, resulting in economic loss and environmental pollution. With the development of connected and automated vehicle (CAV) technologies, it is expected to address these issues through trajectory-level vehicular control. However, due to the large number of human-driven vehicles (HDVs) currently in operation, achieving a pure CAV environment will take time. This motivates us to explore the merging control strategies that can deal with a mixed traffic environment involving both CAVs and HDVs. To accomplish this goal, this study proposes a hierarchical cooperative control strategy consisting of a merging sequencing layer and a motion planning layer to facilitate the smooth merging of CAVs in freeway merging zones. First, the globally optimal merging sequence is determined considering traffic efficiency, safety, and driving comfort using the real-time information collected by roadside units. A zero–one integer programming model is built to convert merging sequencing into a shortest-path search problem, enhancing the solving efficiency. Next, a consensus controller with communication delays is proposed considering the state error of all vehicles in the platoon to deal with the future mixed-traffic environment. The local and string stability conditions are derived to establish parameter-setting criteria. Finally, several experiments are conducted to evaluate the performance of the proposed consensus controller and to analyze the impact of CAVs equipped with the proposed controller on traffic flow. The results show that (1) a more reasonable merging sequence can be provided by the proposed algorithm to reduce potential conflicts and help CAVs merge efficiently, and (2) increasing the penetration rates of CAVs can improve the anti-disturbance performance, robustness, and stability of traffic flow in the merging zone. The related algorithms and findings can be adopted in future autonomous driving systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105230"},"PeriodicalIF":7.6,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid transit system for transit metropolis: Is “spatiotemporal” hybrid structure better?","authors":"Kunzheng Wang ,&nbsp;Sida Luo ,&nbsp;Zexing Yang ,&nbsp;Qian Ye ,&nbsp;Chunfu Shao","doi":"10.1016/j.trc.2025.105232","DOIUrl":"10.1016/j.trc.2025.105232","url":null,"abstract":"<div><div>This paper proposes a Hybrid Transit System for Transit Metropolis (HTS-TM) over a grid of streets which considers a cross-shaped urban development area, enabling a “spatiotemporal” hybrid network structure. The system divides an urban area into the central area and periphery which adopts different transit line spacing (i.e. spatially hybrid) and headway (i.e. temporally hybrid), while a grid transit network is employed citywide. The proportion of the central area and periphery can be optimized, and the flexible network structure can accommodate a centripetal demand pattern that has a large proportion of trips destinating for the central business district. We build a strategic planning model for HTS-TM to provide evidence for futuristic urban expansion from the perspective of transit development, or to serve as indicators for transit metropolis assessment. Specifically, we decompose the spatially heterogeneous demand into two layers and adopt a parsimonious continuum approach, computing the user and agency costs based on the layers. By striking a balance between the user and agency costs, the strategic planning problem is formulated as a mixed integer program with only a few decision variables. Our numerical experiments indicate that, on the one hand, a cross-shaped strategy is often more advantageous for urban expansion than a square shape. On the other hand, the “spatiotemporal” hybrid structure has great flexibility, and HTS-TM delivers outstanding performances in most scenarios tested (the benefit of HTS-TM can reach more than 10% compared with the state-of-the art transit systems). Even in low demand areas with a more or less uniform demand pattern, HTS-TM demonstrates that in the city periphery, a grid may not be worse than a hub-and-spoke network for transit.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105232"},"PeriodicalIF":7.6,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the robotic uncertainty of fully autonomous traffic: From stochastic car-following to mobility–safety trade-offs","authors":"Hangyu Li ,&nbsp;Xiaotong Sun ,&nbsp;Chenglin Zhuang ,&nbsp;Xiaopeng Li","doi":"10.1016/j.trc.2025.105254","DOIUrl":"10.1016/j.trc.2025.105254","url":null,"abstract":"<div><div>Recent transportation research highlights the potential of autonomous vehicles (AV) to improve traffic flow mobility as they are able to maintain smaller car-following distances. However, as a unique class of ground robots, AVs are susceptible to robotic errors, particularly in their perception and control modules with imperfect sensors and actuators, leading to uncertainties in their movements and an increased risk of collisions. Consequently, conservative operational strategies, such as larger headway and slower speeds, are implemented to prioritize safety over mobility in real-world operations. To reconcile the inconsistency, this paper presents an analytical model framework that delineates the endogenous reciprocity between traffic safety and mobility that arises from AVs’ robotic uncertainties. Using both realistic car-following data and a stochastic intelligent driving model (IDM), the stochastic car-following distance is derived as a key parameter, enabling analysis of single-lane capacity and collision probability. A semi-Markov process is then employed to model the dynamics of the lane capacity, and the resulting collision-inclusive capacity, representing expected lane capacity under stationary conditions, serves as the primary performance metric for fully autonomous traffic. The analytical results are further utilized to investigate the impacts of critical parameters in AV and roadway designs on traffic performance, as well as the properties of optimal speed and headway under mobility-targeted or safety-dominated management objectives. Extensions to scenarios involving multiple non-independent collisions or multi-lane traffic scenarios are also discussed, which demonstrates the robustness of the theoretical results and their practical applications.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"178 ","pages":"Article 105254"},"PeriodicalIF":7.6,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144588545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-class within-day dynamic traffic equilibrium with simultaneous path-and-departure-time choices and strategic travel time information","authors":"Xiaoyu Ma ,&nbsp;Xiaozheng He","doi":"10.1016/j.trc.2025.105269","DOIUrl":"10.1016/j.trc.2025.105269","url":null,"abstract":"<div><div>Most research on within-day dynamic traffic equilibrium with information provision <em>implicitly</em> considers travel time information, often assuming information to be perfect or imperfect based on travelers’ perception error. However, lacking explicit formulation of information limits insightful analysis of information impact on dynamic traffic equilibrium and the potential benefits of leveraging information provision to improve system-level performance. To address this gap, this paper proposes a within-day dynamic traffic equilibrium model that <em>explicitly</em> formulates strategic information provision as an endogenous element. The proposed model considers travelers’ reactions to the information, creating an interdependent relationship between provided information and traffic dynamics. In this framework, two classes of travelers receive different types of travel time information: one class receives instantaneous travel time reflecting the prevailing traffic conditions, while the other class receives strategic forecasts of travel times, generated by accounting for travelers’ reactions to instantaneous information based on strategic thinking from behavioral game theory. The resulting multi-class within-day dynamic equilibrium differs from existing models by explicitly modeling information provision and consideration of information consistency. The inherent dynamics of real-time updated traffic information, traffic conditions, and travelers’ choice behaviors are analytically modeled, with the resulting dynamic equilibrium formulated as a fixed-point problem. The theoretical propositions and numerical findings offer rich insights into the impact of information on the traffic network, strategic forecast information penetration, the relationship between the proposed equilibrium and traditional dynamic traffic equilibria, and information accuracy. This research contributes to a deeper understanding of the interplay between information and traffic dynamics, paving the way for more effective traffic management strategies.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"178 ","pages":"Article 105269"},"PeriodicalIF":7.6,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}