Transportation Research Part C-Emerging Technologies最新文献

{"title":"Corrigendum to “The container drayage problem for electric trucks with charging resource constraints” [Transp. Res. Part C 174 (2025) 105100]","authors":"Liyang Xiao , Luxian Chen , Peng Sun , Gilbert Laporte , Roberto Baldacci","doi":"10.1016/j.trc.2025.105167","DOIUrl":"10.1016/j.trc.2025.105167","url":null,"abstract":"","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105167"},"PeriodicalIF":7.6,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115203","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-agent reinforcement learning with causal communication for ride-sourcing pricing in mixed autonomy mobility","authors":"Ningke Xie ,&nbsp;Yong Chen ,&nbsp;Wei Tang ,&nbsp;Xiqun (Michael) Chen","doi":"10.1016/j.trc.2025.105164","DOIUrl":"10.1016/j.trc.2025.105164","url":null,"abstract":"<div><div>The burgeoning self-driving technology has provided a solid impetus for the ride-sourcing market and new demand and supply management challenges. Under the context of a long-haul mixed operation of autonomous vehicles and human-driven vehicles, this paper focuses on profit-maximizing pricing for both demand and supply sides, in which the prices are differentiated by service type, time, and location. Diverging from most studies limited to centralized control for small-scale problems, we align with distributed and scalable requirements in practice and tackle the coordination challenge from a causal communication perspective. Based on the spatial supply–demand interdependencies inherent in the ride-sourcing market, operation areas are modeled as collaborative intelligent agents. The pricing problem is formulated as a decentralized partially observable Markov game augmented with neighborhood communication. Then a multi-agent reinforcement learning with causal communication method is developed to jointly optimize pricing policy and communication mechanism through end-to-end learning. The bidirectional communication mechanism is ensured to be effective and succinct by maximizing the causal effect of the communication message. Leveraging theoretical analysis, the proposed method is proven to cope with partial observability and non-stationary environments through collaborative communication. Besides, an agent-based simulator for mixed autonomy mobility is established on a real-world large-scale network, emulating the causal communication process among decentralized areas, as well as the heterogeneity, elasticity, and uncertainty of ride-sourcing demand and supply. Two representative scenarios are designed to demonstrate the dynamic evolutions of mixed autonomy mobility: (a) smaller-sized autonomous vehicles and conservative passenger acceptance (conservative stage), and (b) larger-sized autonomous vehicles and liberal passenger acceptance (liberal stage). The results highlight that incorporating the causal communication mechanism can speed up the learning process and guide informed pricing decisions. Furthermore, the proposed method gains managerial insights into proactively regulating pricing schemes for a smooth transformation into fully autonomous ride-sourcing services.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105164"},"PeriodicalIF":7.6,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070728","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":"Can AV crash datasets provide more insight if missing information is supplemented? Employing Generative Adversarial Imputation Networks to Tackle Data Quality Issues","authors":"Hongliang Ding ,&nbsp;Zhuo Liu ,&nbsp;Hanlong Fu ,&nbsp;Xiaowen Fu ,&nbsp;Tiantian Chen ,&nbsp;Jinhua Zhao","doi":"10.1016/j.trc.2025.105154","DOIUrl":"10.1016/j.trc.2025.105154","url":null,"abstract":"<div><div>The growing prevalence of autonomous vehicles (AVs) offers new opportunities for enhancing traffic efficiency. However, AVs still face significant challenges that impact their safety and effectiveness in preventing accidents. Real-world operational data is therefore essential to identifying the factors contributing to AV crashes. Despite this, the analysis of AV crashes is still hampered by a lack of data, missing information, and underreporting, which negatively impacts its accuracy and comprehensiveness. To address this challenge, a method based on Generative Adversarial Networks (GANs) was used for data imputation, leveraging their advantage in handling heterogeneous data. An evaluation of the performance of our proposed data imputation approach was performed by comparing it with two established methods, namely conventional case deletion and Random Forest (RF) imputation. Synthetic data obtained from these three methods were modelled using the random parameters logit model with heterogeneity in means. Data from the California Department of Motor Vehicles (DMV) and the National Highway Traffic Safety Administration (NHTSA) covering 2021–2023 were used. Our results showed that the model based on Generative Adversarial Imputation Networks (GAIN)- processing data outperformed other candidate methods in terms of fitting, predictive accuracy, and factor interpretation. Our results suggest that factors including speed limit, roadway types, head-on crashes, and takeover of ADAS-equipped vehicles are positively associated with serious injury crashes. On the other hand, ADS engagement and crashes with fixed objects exhibit a negative association with serious injury crashes. Additionally, heterogeneous effects of posted speed limits and ADS engagement on AV crash severity were captured to provide a deeper insight into implications.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105154"},"PeriodicalIF":7.6,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070729","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":"Online prediction-assisted safe reinforcement learning for electric vehicle charging station recommendation in dynamically coupled transportation-power systems","authors":"Qionghua Liao ,&nbsp;Guilong Li ,&nbsp;Jiajie Yu ,&nbsp;Ziyuan Gu ,&nbsp;Wei Ma","doi":"10.1016/j.trc.2025.105155","DOIUrl":"10.1016/j.trc.2025.105155","url":null,"abstract":"<div><div>With the proliferation of electric vehicles (EVs), the transportation network and power grid become increasingly interdependent and coupled via charging stations. The concomitant growth in charging demand has posed challenges for both networks, highlighting the importance of charging coordination. However, existing literature largely overlooks the interactions between power grid security and traffic efficiency, where the deterioration of grid security also leads to a decrease in traffic efficiency. In view of this, we study the en-route charging station (CS) recommendation problem for EVs in dynamically coupled transportation-power systems. The system-level objective is to maximize the overall traffic efficiency while enhancing the safety of the power grid. This problem is for the first time formulated as a constrained Markov decision process (CMDP), and an online prediction-assisted safe reinforcement learning (OP-SRL) method is proposed to learn the optimal and secure policy. To be specific, we mainly address two challenges. First, the constrained optimization problem is converted into an equivalent unconstrained optimization problem by applying the Lagrangian method, and then the Proximal Policy Optimization (PPO) method is extended to incorporate the constraint in the sequential decision process through the inclusions of cost critic and Lagrangian multiplier. Second, to account for the uncertain long-time delay between performing charging station recommendation and commencing charging, we put forward an online sequence-to-sequence (Seq2Seq) predictor for state augmentation, offering foresightful information to guide the agent in making forward-thinking decisions. Finally, we conduct comprehensive experimental studies based on the Nguyen-Dupuis network and a large-scale real-world road network, coupled with IEEE 33-bus and IEEE 69-bus distribution systems, respectively. Results demonstrate that the proposed method outperforms baselines in terms of road network efficiency, power grid safety, and EV user satisfaction. The case study on the real-world network also illustrates the applicability in the practical context.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105155"},"PeriodicalIF":7.6,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070730","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":"Vessel arrival time to port prediction via a stacked ensemble approach: Fusing port call records and AIS data","authors":"Zhong Chu ,&nbsp;Ran Yan ,&nbsp;Shuaian Wang","doi":"10.1016/j.trc.2025.105128","DOIUrl":"10.1016/j.trc.2025.105128","url":null,"abstract":"<div><div>Accurate prediction of vessel arrival time (VAT) to port is essential for optimizing port operations, particularly given the common discrepancies between the vessel-reported estimated time of arrival (ETA) and its actual time of arrival (ATA). Traditional VAT prediction models predominantly rely on either static port call data (e.g., ETA and ATA) or dynamic automatic identification system (AIS) data, with limited integration of both sources to comprehensively address forecasting needs and biased forecasting results. To address these limitations, this study introduces a framework that, for the first time, integrates static port call data with dynamic vessel AIS data using a time-based comparative interpolation method to enhance VAT prediction accuracy. By synchronizing scheduled operations with real-time vessel movements, our approach captures nuanced temporal variations, significantly enhancing VAT prediction accuracy. Based on a tree-based stacking model and real-world vessel arrival data from Hong Kong Port (HKP), the proposed framework leverages the strengths of tree-based methods in handling tabular data and demonstrates substantial improvements in VAT prediction accuracy. Our results show an 54.53% reduction in mean absolute error (MAE) (from 6.84 to 3.11 h) and an 50.14% reduction in root mean squared error (RMSE) (from 10.61 to 5.29 h) compared to vessel-reported ETAs. Key features such as vessel-reported ETA, vessel sailing speed, vessel physical features, and spatiotemporal AIS data contribute to these improvements. This research addresses a critical gap by providing a unified approach that leverages both static and dynamic data sources, offering port authorities a more reliable and robust tool for vessel arrival forecasting and the subsequent informed port resource planning.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105128"},"PeriodicalIF":7.6,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068153","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":"Energy-efficient multi-curve optimization in urban rail transit: Stability enhancement under operational uncertainties and curve adjustments","authors":"Deheng Lian ,&nbsp;Zebin Chen ,&nbsp;Pengli Mo ,&nbsp;Ziyou Gao ,&nbsp;Andrea D’Ariano ,&nbsp;Lixing Yang","doi":"10.1016/j.trc.2025.105148","DOIUrl":"10.1016/j.trc.2025.105148","url":null,"abstract":"<div><div>The multi-curve optimization problem involves selecting train speed curves for nominal timetables and configuring candidate curves embedded in the Automatic Train Operation (ATO) system for train rescheduling. In practice, train speed curves planned under nominal conditions are frequently disrupted by uncertainties such as delays and fluctuations in passenger flow, which may require rescheduling, where the actual speed curves can only be selected from the candidate train speed curves. This rescheduling process leads to deviations between rescheduled (actual) and nominal energy performance. Existing research has not fully addressed the impact of rescheduling on energy consumption from a planning perspective, a critical gap for improving the efficiency of energy-efficient timetables under uncertainty. To fill this gap, we define the stability of energy-efficient train timetables as a quantifiable metric, assessing deviations in terms of both energy reduction and delay control. To minimize actual energy consumption, this study incorporates stability-based constraints into a two-stage stochastic programming model, combining an energy-efficient scheduling stage with a bi-level programming stage for speed curve rescheduling, which introduces nonlinear complexities. Two logic-based Benders decomposition algorithms, including a novel multi-scenario dynamic programming method, solve the model. Using actual data from the Beijing Yizhuang Line, we conducted two sets of numerical experiments to validate the performance of the model and algorithms. Compared to a benchmark two-stage model without optimizing the candidate train speed curves, our approach achieves average stability improvements of 2.74% for in-sample tests and 2.40% for out-of-sample tests, with gains surpassing 4.00% under more challenging delay scenarios, alongside reductions in energy consumption.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105148"},"PeriodicalIF":7.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068154","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 gentle introduction and tutorial on Deep Generative Models in transportation research","authors":"Seongjin Choi ,&nbsp;Zhixiong Jin ,&nbsp;Seung Woo Ham ,&nbsp;Jiwon Kim ,&nbsp;Lijun Sun","doi":"10.1016/j.trc.2025.105145","DOIUrl":"10.1016/j.trc.2025.105145","url":null,"abstract":"<div><div>Deep Generative Models (DGMs) have rapidly advanced in recent years, becoming essential tools in various fields due to their ability to learn data distributions and generate synthetic data. Their importance in transportation research is increasingly recognized, particularly for applications like traffic data generation, prediction, and feature extraction. This paper offers a comprehensive introduction and tutorial on DGMs, with a focus on their applications in transportation. It begins with an overview of generative models, followed by detailed explanations of fundamental models, a systematic review of the literature, and practical tutorial code to aid implementation. The paper also discusses current challenges and opportunities, highlighting how these models can be effectively utilized and further developed in transportation research. This paper serves as a valuable reference, guiding researchers and practitioners from foundational knowledge to advanced applications of DGMs in transportation research.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105145"},"PeriodicalIF":7.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068152","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":"Real-time lane-changing crash prediction model at the individual vehicle level using real-world trajectories prior to crashes","authors":"Kequan Chen ,&nbsp;Zhibin Li ,&nbsp;Pan Liu ,&nbsp;Chengcheng Xu ,&nbsp;Yuxuan Wang","doi":"10.1016/j.trc.2025.105171","DOIUrl":"10.1016/j.trc.2025.105171","url":null,"abstract":"<div><div>This study aims to develop a real-time crash prediction model for individual lane-changing (LC) maneuvers by considering interactions between the LC vehicle and surrounding vehicles. Vehicle trajectories prior to real-world LC crashes are extracted for modeling. Risky events are identified based on the remaining distance between vehicles to develop Generalized Extreme Value (GEV) distributions. Driving-related factors, such as the relative distance, speed, and acceleration between vehicles during the LC maneuver, are considered to address the non-stationary issue. A real-time LC crash prediction model is established by quantifying the differences between non-stationary GEV distributions under LC crash and non-crash conditions. The results show that incorporating driving-related factors significantly improves the goodness-of-fit of GEV distribution. Our model shows satisfactory LC crash prediction performance, with the Area Under the Curve (AUC) values ranging from 0.92 to 0.98. The proposed model improves by an average of 75% over traditional Time-to-Collision (TTC), and 49% over Two-Dimensional TTC.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105171"},"PeriodicalIF":7.6,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946828","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":"Electric vehicle routing problem considering traffic conditions and real-time loads","authors":"Jingyi Zhao ,&nbsp;Zirong Zeng ,&nbsp;Yang Liu","doi":"10.1016/j.trc.2025.105150","DOIUrl":"10.1016/j.trc.2025.105150","url":null,"abstract":"<div><div>Eco-driving strategies aim to reduce energy consumption (EC), greenhouse gas (GHG) emissions, and accident rates, and to promote environmental benefits. One of the efficient ways to reduce GHG emissions is using electric vehicles (EV) to replace fuel ones. Inspired by these, in this paper, we study an electric vehicle routing problem (EVRP) with the objective of minimizing the total EC of the vehicles during transportation. Specifically, we consider segmented linear speed functions that simulate traffic conditions and take into account the impact of real-time load and acceleration of EVs on energy consumption. The speed model accurately captures gradual changes in vehicle speed, reflecting real-world road conditions more realistically. We define this problem as a time and load-dependent EVRP (TLD-EVRP). This problem is difficult to solve not only because it considers both real-time vehicle speed and load conditions but also because the problem is modeled as nonlinear (with quadratic and cubic terms of vehicle speed). The goal is to minimize the EC of the electric vehicle, and this integration will improve energy efficiency and environmental benefits. To tackle this TLD-EVRP, a meta-heuristic algorithm is developed, combining a Large Neighborhood Search (LNS) with a Local Search (LS) procedure and a split algorithm for efficient route segmentation for individual EVs. The set partitioning problem (SPP) is used to recombine the routes. The goal of the algorithm is to develop a robust tool to address the complexity of TLD-EVRPs with different sizes and distributions. The proposed approach is evaluated using a small-scale real-world test case and extensive experiments are then conducted on randomly generated large-scale data. The evaluation results show that our algorithm can handle large-scale instances of up to 1000 customers and exhibits robustness on large data. By promoting energy-efficient practices in the transportation sector, the proposed methodology contributes to the achievement of green and low-carbon goals.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105150"},"PeriodicalIF":7.6,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937005","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":"Mechanism design for coordinating vehicle-based mobile sensing tasks within the ride-hailing platform","authors":"Shenglin Liu ,&nbsp;Qian Ge ,&nbsp;Ke Han ,&nbsp;Daisuke Fukuda ,&nbsp;Takao Dantsuji","doi":"10.1016/j.trc.2025.105151","DOIUrl":"10.1016/j.trc.2025.105151","url":null,"abstract":"<div><div>This paper evaluates the benefit of integrating vehicle-based mobile crowd-sensing tasks into the ride-hailing system through the collaboration between the data user and the ride-hailing platform. In such a system, the ride-hailing platform commissions high-valued sensing tasks to idle drivers who can undertake either ride-hailing or sensing requests. Considering the different service requirements and time windows between sensing and ride-hailing requests, we design a staggered operation strategy for ride-hailing order matching and the sensing task assignment. The auction-based mechanisms are employed to minimize costs while incentivizing driver participation in mobile sensing. To address the budget deficit problem of the primal VCG (Vickrey–Clarke–Groves)-based task assignment mechanism, we refine the driver selection approach and tailor the payment rule by imposing additional budget constraints. We demonstrate the benefits of our proposed mechanism through a series of numerical experiments using the NYC Taxi data. Experimental results reveal the potential of the mechanism for achieving high completion rates of sensing tasks at low social costs without degrading ride-hailing services. Furthermore, drivers who participate in both mobile sensing tasks and ride-hailing requests may gain higher income, but this advantage may diminish with an increasing number of such drivers and higher demand for ride-hailing services.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105151"},"PeriodicalIF":7.6,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937006","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}