Transportation Research Part C-Emerging Technologies最新文献

{"title":"Communication-free Distributed Control Algorithm for autonomous vehicles at intersections","authors":"Alireza Soltani,&nbsp;David M. Levinson,&nbsp;Mohsen Ramezani","doi":"10.1016/j.trc.2025.105309","DOIUrl":"10.1016/j.trc.2025.105309","url":null,"abstract":"<div><div>This paper introduces a novel approach for managing autonomous vehicles at signal-free intersections through a <em>Communication-free Distributed Control Algorithm</em> (CfDCA). Unlike centralized systems or communication-based decentralized methods, CfDCA relies solely on onboard sensors and in-vehicle decision-making to ensure efficient and collision-free navigation. The algorithm formulates intersection management as a distributed optimization problem with demonstrated safety logics and robustness to measurement errors. The algorithm combines a dynamic resource acquisition graph with a refined priority function and an adaptive tolerance mechanism to ensure efficient performance under varying traffic conditions. A stochastic tie-breaking mechanism is proposed to handle rare cases of identical priorities, while deadlock prevention is guaranteed through strict priority ordering. Simulation experiments demonstrate that CfDCA reduces average delay and queue length and is able to achieve throughput higher than actuated signalized intersections and outperforms a first-come-first-served baseline in delay reduction. Additionally, the algorithm’s distributed design offers scalability and eliminates dependency on communication infrastructure.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105309"},"PeriodicalIF":7.6,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144913704","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":"Optimal pricing and vehicle routing of vehicle-to-vehicle charging platform with time windows","authors":"Xuekai Cen ,&nbsp;Xu Yang ,&nbsp;Kanghui Ren ,&nbsp;Wei Liu ,&nbsp;Enoch Lee","doi":"10.1016/j.trc.2025.105319","DOIUrl":"10.1016/j.trc.2025.105319","url":null,"abstract":"<div><div>This study optimizes the pricing and vehicle routing for a Vehicle-to-Vehicle (V2V) charging platform, which pairs Charging Vehicles (CVs) with Discharging Vehicles (DVs), where CV owners pay for the service and DV owners are compensated. A Vehicle Routing Problem of V2V charging platform with Zone-based Pricing and Time Window (VRPTW-V2V-ZP) is formulated, that optimizes zonal electricity rates, wage rates, and routing strategies to maximize platform profitability, taking into account the engagement levels of both CV and DV owners. The zone-based pricing allows for differential pricing across various zones, optimizing profit margins in response to localized EV charging demands and the presence of competing Charging Infrastructures (CIs). To address the computational challenges of large-scale problems, a customized Variable Neighborhood Search (VNS) algorithm is proposed, demonstrating excellent performance in terms of solution quality and efficiency. Using a real-world network in Changsha, China, the zone-based pricing strategy improved the V2V platform profitability compared to the unified pricing strategy. Moreover, increasing the number of CVs and DVs on the platform reduces the average charging cost for CVs and improves platform profitability. This creates a virtuous cycle that enhances service quality and attracts additional users, thereby contributing to sustainable transportation and the growth of the V2V charging ecosystem.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105319"},"PeriodicalIF":7.6,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895230","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":"Distributed dynamic route guidance via passenger information display systems for subway disruption management","authors":"Xueqin Wang ,&nbsp;Xinyue Xu ,&nbsp;Melvin Wong ,&nbsp;Jun Liu","doi":"10.1016/j.trc.2025.105316","DOIUrl":"10.1016/j.trc.2025.105316","url":null,"abstract":"<div><div>Passenger information display systems (PIDS) play a critical role in travel guidance during subway disruptions, but their potential for offering prescriptive route suggestions remains underutilized. Addressing this gap, this study introduces a PIDS-based route guidance framework that employs a distributed guidance approach to manage subway disruptions. This framework leverages the diversion capacity of multiple transfer stations, thereby facilitating network-wide route guidance and mitigating localized congestion. The implementation of the framework involves constructing an evacuation network, where alternative route information is released at evacuation start stations and guides passengers to detour towards evacuation end stations. Only specific transfer stations are selected as these evacuation stations according to an analysis of historical passenger flow distributions. This targeted selection process narrows the optimization space for information release. A dynamic information release optimization problem is formulated, where each pair of evacuation start and end stations is used as a decision variable, with the dual objectives of minimizing travel cost and the number of passengers in the subway. This problem is solved using the asynchronous advantage actor-critic algorithm, which is adept at handling the high-dimensional action and state spaces in a large-scale subway network. This study is the first to integrate PIDS-based route guidance with deep reinforcement learning for optimizing dynamic information dissemination in subway systems. The performance of the proposed framework is validated with data from a subway operation experiencing disruptions. Compared to localized guidance, the proposed framework achieves a 10.87% reduction in total travel cost, a 50.57% greater increase in completed trips, and a 43.83% reduction in peak passenger volume at stations adjacent to the disrupted area.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105316"},"PeriodicalIF":7.6,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890468","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":"Multiscale geographical random forest: A novel spatial ML approach for traffic safety modeling integrating street-view semantic visual features","authors":"Pengfei Cui ,&nbsp;Mohamed Abdel-Aty ,&nbsp;Lei Han ,&nbsp;Xiaobao Yang","doi":"10.1016/j.trc.2025.105299","DOIUrl":"10.1016/j.trc.2025.105299","url":null,"abstract":"<div><div>Macro-level traffic safety modeling aims to identify critical risk factors to reginal crashes, providing essential basis for effective countermeasures by traffic managers. Previous work mainly incorporated macro and static socio-demographic and infrastructure features, overlooking drivers’ visual perception of environment, which crucially influences their driving behavior and thus safety. Moreover, spatial machine learning (ML) has gained prominence for its strong crash prediction performance. However, existing spatial ML typically apply spatial effects at a fixed or homogeneous scale (e.g., specific Euclidean distances), limiting their ability to capture the multiscale spatial heterogeneity of features. To address these gaps, emerging image semantic segmentation technique is employed to extract visual environment features (e.g., buildings, trees) from Google Street View (GSV) images. A novel spatial ML method, Multiscale Geographical Random Forest (MGRF), is proposed to overcome fixed-spatial scale constraints to adaptive multiscale spatial modeling. Empirical experiments on Southeast Florida show that the inclusion of visual environment features from 228,352 street view images leads to notably improved crash prediction. Compared to traditional models (e.g., multiscale geographically weighted regression), MGRF fits optimal spatial bandwidths for each sample, achieving improvements of 30.31%, 9.98%, and 5.53% in MSE, MAE, and R², respectively. By incorporating SHapley Additive exPlanations, MGRF identified key risk features for each region and quantified their spatial heterogeneity. The Results reveal that in urban core areas, the proportion of cars in GSV, which reflects road traffic condition, is the most critical feature contributing positively to increase in crashes. In contrast, for suburban regions, lower road density and abundant green spaces are associated with a reduction in crashes. This study highlights the significant potential of integrating street-view semantic visual features with multiscale spatial ML to enhance traffic safety analysis.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105299"},"PeriodicalIF":7.6,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886912","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":"Assessing how ride-hailing rebalancing strategies improve the resilience of multi-modal transportation systems","authors":"Euntak Lee,&nbsp;Rim Slama,&nbsp;Ludovic Leclercq","doi":"10.1016/j.trc.2025.105300","DOIUrl":"10.1016/j.trc.2025.105300","url":null,"abstract":"<div><div>The global ride-hailing (RH) industry plays an essential role in multi-modal transportation systems by improving user mobility, particularly as first- and last-mile solutions. However, the flexibility of on-demand mobility services can lead to local supply–demand imbalances. While many RH rebalancing studies focus on nominal scenarios with regular demand patterns, it is crucial to consider disruptions – such as train line interruptions – that negatively impact operational efficiency, resulting in longer travel times, higher costs, increased transfers, and service delays. This study examines how RH rebalancing strategies can strengthen the resilience of multi-modal transportation systems against such disruptions. We incorporate RH services into systems where users choose and transfer transportation modes based on their preferences, accounting for uncertainties in demand predictions that reflect discrepancies between forecasts and actual conditions. To address the stochastic supply–demand dynamics in large-scale networks, we propose a multi-agent reinforcement learning (MARL) strategy, specifically utilizing a multi-agent deep deterministic policy gradient (MADDPG) approach. The proposed framework is particularly well-suited for this problem due to its ability to handle continuous action spaces, which are prevalent in real-world transportation systems, and its capacity to enable effective coordination among multiple agents operating in dynamic and decentralized environments. Through a 900 <span><math><msup><mrow><mtext>km</mtext></mrow><mrow><mn>2</mn></mrow></msup></math></span> multi-modal traffic simulation, we evaluate the proposed model’s performance against four existing RH rebalancing strategies, focusing on its ability to enhance system resilience. The results demonstrate significant improvements in key performance indicators, including user waiting time, resilience metrics, total travel time, and travel distance.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105300"},"PeriodicalIF":7.6,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886913","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 train car passenger load via platform escalator directions: an iterative backpropagation framework for computational efficiency","authors":"Qiru Ma ,&nbsp;Enoch Lee ,&nbsp;Kejun Du ,&nbsp;Zhiya Su ,&nbsp;May Mei Shan Tso ,&nbsp;Ho Wing Chan ,&nbsp;Hong K. Lo ,&nbsp;S.W. Ricky Lee","doi":"10.1016/j.trc.2025.105261","DOIUrl":"10.1016/j.trc.2025.105261","url":null,"abstract":"<div><div>Uneven train load in urban rail transit systems reduces line capacity and operational efficiency, often resulting in denied boarding and unnecessary crowding. To address this challenge, we introduce a novel and cost-effective strategy of optimizing the directions of existing escalators across multiple stations on a metro line to systematically redistribute passengers among train cars. This paper proposes a comprehensive framework, comprising four key components: (1) a heterogeneous passenger behavior model that categorizes passengers as either origin-inclined or destination-inclined based on their car selection preferences; (2) a passenger behavior model calibration approach that aligns behavior model output with observed train load; (3) an Iterative Backpropagation (IB) computational framework for efficient model calibration, which casts the passenger behavior model into a computational graph, utilizes automatic differentiation to derive the analytical gradient, and iteratively refines model parameters; and (4) an optimization model that employs the calibrated behavior parameters to determine escalator configurations that minimize inter-car load imbalances in both service directions. The proposed framework is applied to Hong Kong’s Mass Transit Railway during the morning rush hour, collectively optimizing escalator directions across eight sequential stations. The implementation yields a notable 42.25 % reduction in train load variance, demonstrating the effectiveness and scalability of our proposed strategy in promoting balanced passenger distribution with minimal infrastructure change.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105261"},"PeriodicalIF":7.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878391","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 sequential matching and routing approach for efficient and eco-friendly freight logistics","authors":"Elham Haji Sami ,&nbsp;Ahmad Shahnejat Bushehri ,&nbsp;Ashkan Amirnia ,&nbsp;Asad Yarahmadi ,&nbsp;Samira Keivanpour","doi":"10.1016/j.trc.2025.105290","DOIUrl":"10.1016/j.trc.2025.105290","url":null,"abstract":"<div><div>Integrating smart technologies into freight operations is essential for achieving efficiency, sustainability, and cost-effectiveness in modern logistics. This research presents a novel smart freight platform to optimize matching and routing in freight logistics. The platform incorporates sequential matching and a dynamic bidding mechanism, including Pre-filter matching, Main matching, and Non-Contracted Shippers (NCS) matching models. It utilizes the Vehicle Routing Problem with Time Windows (VRPTW) model to align delivery schedules with shippers’ time windows. The proposed platform reduces resource consumption by minimizing empty truck routes through NCS alignment with en-route trucks. In particular, empty truck routes were reduced by %39, while gas emissions decreased by over nine tons daily. Therefore, the proposed platform not only improves freight efficiency but also contributes to environmental sustainability.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105290"},"PeriodicalIF":7.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878392","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":"Ramp metering for lane-free traffic of automated vehicles via ramp vehicle speed control","authors":"Milad Malekzadeh ,&nbsp;Ioannis Papamichail ,&nbsp;Markos Papageorgiou ,&nbsp;Klaus Bogenberger","doi":"10.1016/j.trc.2025.105302","DOIUrl":"10.1016/j.trc.2025.105302","url":null,"abstract":"<div><div>A new ramp metering method for Connected and Automated Vehicles (CAVs) driving in a lane-free environment is developed and tested at the microscopic operational level. CAVs drive on the mainstream, on the on-ramp and in the merge area according to an ad-hoc movement strategy that takes inspiration from adaptive cruise control, with notable extensions made to accommodate lane-free driving and vehicle nudging. Appropriate settings enable seamless and safe merging from the on-ramp onto the highway. A new approach for ramp metering is proposed to effectively avoid the capacity drop occurring in merge areas due to merge congestion. The approach is based on zone separation of the on-ramp and vehicle speed control in each zone as key components for CAV ramp metering, instead of the conventional traffic signals, to avoid stop-and-go of queueing vehicles, thus mitigating fuel consumption and emissions. In this context, two feedback control strategies are introduced; the first one controlling the ramp flow and subsequently translating this into the desired speed of ramp vehicles; and the second one regulating directly the desired speed of vehicles in the ramp; both in response to the current mainstream density. The results achieved through TrafficFluid-Sim, a microscopic lane-free traffic simulation platform built on SUMO, provide evidence of the feasibility of the proposed ramp metering strategy, ensuring both smooth merging and capacity flow on the mainstream. It is also demonstrated that the introduced vehicle speed control reduces vehicle stops and emissions on the on-ramp, compared to conventional ramp metering with traffic signals.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105302"},"PeriodicalIF":7.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865599","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":"Resource allocation for an air-rail-integrated co-modality platform considering both demand and supply uncertainties","authors":"Xinyi Zhu ,&nbsp;Wei Liu ,&nbsp;Fangni Zhang","doi":"10.1016/j.trc.2025.105294","DOIUrl":"10.1016/j.trc.2025.105294","url":null,"abstract":"<div><div>The co-modal mode, i.e., passenger-and-freight mixed transportation, has received increasing interest, given the rapid growth of parcel volume and its potential to save transportation costs. This paper examines an air-rail-integrated co-modal mode that utilizes the excess capacity of passenger trains and flights considering uncertainties in both supply and demand. On the supply side, uncertainty arises from travel time delays of passenger trains and flights. On the demand side, while historical data on cargo orders are available, such as volume distribution between each origin and destination pair, the daily cargo orders/demands remain uncertain and will be revealed in real-time. We aim to dynamically allocate these resources (excess capacity of trains and flights) to serve cargo orders while effectively accommodating uncertainties. To address this problem, a two-stage stochastic programming model is developed to minimize the total costs associated with cargo transportation, holding, transshipment, delays, and ad-hoc service options (when the co-modal mode is unavailable). The sample average approximation solution approach, embedded with an adaptive large neighborhood search algorithm, is employed to solve the problem. The above model and algorithm are implemented in a rolling horizon framework to make time-dependent resource allocation decisions. The test instances are generated based on rail and air transportation data in Hong Kong (with Hong Kong West Kowloon Station and Hong Kong International Airport). Numerical studies and sensitivity analysis are conducted to evaluate (i) the benefits of the air-rail-integrated co-modality, (ii) the effectiveness of the proposed solution algorithm, and (iii) the impact of demand/supply characteristics on the air-rail-integrated co-modality operation.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105294"},"PeriodicalIF":7.6,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865597","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":"An integrated method for inferring multimodal travel mode choices using mobile network data","authors":"Yuhang Liu ,&nbsp;Feixiong Liao ,&nbsp;Wei Wang ,&nbsp;Yuchen Wang ,&nbsp;Jun Chen","doi":"10.1016/j.trc.2025.105305","DOIUrl":"10.1016/j.trc.2025.105305","url":null,"abstract":"<div><div>With the high coverage of mobile network data, the travel patterns of urban populations can be studied on a large scale at a relatively low cost. Existing research has primarily focused on inferring single modes of trips, ignoring the transitions between different transport modes within trips. This study integrates mobile signaling data with travel surveys, transport network data, and census data to infer multimodal travel choices. We first develop an adaptive distance-based clustering method to dynamically segment data into trips based on the surrounding built environment. Then, we utilize the Bayesian inference and hidden Markov models (HMM) with multiple observation sequences, effectively combining discrete and continuous observation states, to generate transport mode sequences throughout a day. We demonstrate the proposed integrated method through a case study in Nanjing, China for inferring trip chains of five transport modes. The inferred transport mode choices are extensively validated based on travel surveys, official statistical data, and smart card data at different spatial scales. From our results, we observe temporal and spatial patterns of travel for various transport modes. These findings confirm the performance of the integrated method in capturing multimodal travel patterns for an urban population. The inferred multimodal trip chains are useful for travel demand management and developing sustainable transport systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105305"},"PeriodicalIF":7.6,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865598","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}