Transportation Research Part C-Emerging Technologies最新文献

{"title":"Learning the on-demand adaptable matching range with a reinforcement learning","authors":"Yuhan Liu ,&nbsp;Siyuan Feng ,&nbsp;Yue Bao ,&nbsp;Hai Yang","doi":"10.1016/j.trc.2025.105018","DOIUrl":"10.1016/j.trc.2025.105018","url":null,"abstract":"<div><div>Ride-sourcing services have reshaped urban transportation, providing greater convenience and efficiency for city commuters. At the core of these services is the matching process, which directly impacts service efficiency, passenger satisfaction, and overall platform profitability. Consequently, developing highly effective matching algorithms, especially under imbalanced supply–demand conditions, is of utmost importance. In existing matching algorithms, the matching range is a key factor. A larger matching range can result in longer pickup waiting times, potentially leading passengers to abandon their requests. Conversely, a smaller matching range may shorten waiting times but can also reduce the overall matching rate. Previous research on optimizing the matching range has often overlooked future information, leading to short-term improvements. In this paper, we propose a generalized, on-demand adaptable matching range technique based on reinforcement learning framework, designed to optimize decision-making from a long-term perspective while accounting for future information. Additionally, we develop a flexible framework adaptable to different kinds of matching modes. To evaluate the effectiveness of our approach, we implement our strategy with real-world supply and demand data and conduct a series of sensitivity analyses. The experimental results demonstrate that our method can achieve improvements in terms of the platform’s revenue and passengers’ satisfaction simultaneously compared with benchmark algorithms.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105018"},"PeriodicalIF":7.6,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377511","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":"The multi-visit vehicle routing problem with multiple heterogeneous drones","authors":"Yu Jiang ,&nbsp;Mengmeng Liu ,&nbsp;Xibei Jia ,&nbsp;Qingwen Xue","doi":"10.1016/j.trc.2025.105026","DOIUrl":"10.1016/j.trc.2025.105026","url":null,"abstract":"<div><div>The integration of drones into last-mile delivery logistics offers a promising avenue for enhancing delivery efficiency. This advancement has garnered considerable interest in the truck−drone cooperative delivery problem. In response, this study delves into the multi-visit vehicle routing problem with multiple heterogeneous drones (MV-VRP-MHD), focused on addressing its feasibility and scalability in real-world, large-scale settings. By considering essential factors such as drones’ ability for multiple deliveries, varied energy consumption patterns, and the employment of heterogeneous drone fleets, our model aims to minimize the overall completion time. To address the challenge of tackling large-scale instances, we introduce a hybrid algorithm that combines variable neighborhood search and simulated annealing (VNS-SA). This algorithm applies a two-phased approach to construct an initial solution and further refines it through the implementation of four unique neighborhood operators. Finally, to confirm the effectiveness of MV-VRP-MHD and VNS-SA, a comprehensive series of computational experiments was carried out. The experiments demonstrated that MV-VRP-MHD significantly enhances the efficiency of last-mile delivery. The analysis results indicate that the heterogeneous drone fleet effectively handles large-area deliveries. It also found that while improvements in drone speed, payload capacity, and battery life were beneficial, incremental enhancements in these areas yielded limited effects when applied individually. Operator experiments revealed that the drone route generation operator was the most effective among the four neighborhood operators. Finally, we discuss the impact of uncertainties in the delivery process on the model results.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105026"},"PeriodicalIF":7.6,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372048","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 knowledge-driven, generalizable decision-making framework for autonomous driving via cognitive representation alignment","authors":"Hongliang Lu ,&nbsp;Junjie Yang ,&nbsp;Meixin Zhu ,&nbsp;Chao Lu ,&nbsp;Xianda Chen ,&nbsp;Xinhu Zheng ,&nbsp;Hai Yang","doi":"10.1016/j.trc.2025.105030","DOIUrl":"10.1016/j.trc.2025.105030","url":null,"abstract":"<div><div>With the boom of machine learning (ML), knowledge-driven autonomous driving (AD) holds great promise for improving its performance and reliability in future practical applications. To endow AD with better generalization ability like that of human drivers, knowledge transfer has gathered increasing attention in recent years. For knowledge transfer, determining what acts as knowledge and how knowledge can be transferred, as well as which knowledge should be transferred, plays a crucial role in its actualization and reliability. In this paper, we propose a knowledge-driven, generalizable decision-making framework for AD, called cognitive representation alignment. Specifically, the cognitively plausible predictive map serves as a basic knowledge-driven foundation (addressing ‘What’ and ‘How’), and a representation alignment scheme based on graph representation and shortest path graph kernel is developed to serve as the knowledge matching criteria to enable more reliable knowledge transfer (addressing ‘Which’). We pre-establish several kinds of typical driving scenarios (feature scenarios) and extract the knowledge from them to construct a knowledge reservoir. For validation, CommonRoad, a real-world logs-driven simulation benchmark, is used to test the effectiveness of our framework. Empirical results from 500 testing scenarios demonstrate that the proposed framework can not only enhance decision-making performance but also further improve driving safety, navigability, and generalization ability, fueling the futuristic development of a knowledge-driven AD paradigm.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105030"},"PeriodicalIF":7.6,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349809","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":"Network-wide critical routes identification and coordinated control based on automatic vehicle identification data","authors":"Peng Chen ,&nbsp;Jiaming Xu ,&nbsp;Yu Mei ,&nbsp;Lei Wei","doi":"10.1016/j.trc.2025.105019","DOIUrl":"10.1016/j.trc.2025.105019","url":null,"abstract":"<div><div>Coordinated signal control is an effective way to improve traffic efficiency in urban road networks. This study presents a network-wide coordinated signal control method based on the identification of critical routes and the partitioning of coordinated intersection groups using automatic vehicle identification (AVI) data. A movement-level network representation model is first proposed to identify critical routes by analyzing the fully sampled paths of individual vehicles extracted from the network’s AVI data. Then, the optimization of the entire road network is divided into multiple coordinated intersection groups and potential isolated intersections by minimizing total delay, accounting for the interactions between cycle length and delay at intersections along all critical routes. Based on the ring-and-barrier scheme, the signal control problem for each coordinated intersection group is formulated as a mixed integer linear programming (MILP) model aimed at maximizing the bandwidth allocated to critical route bands. Utilizing real AVI data collected from the network of Baoding City, China, the experimental results demonstrate that the proposed partitioning method outperforms static clustering methods that rely on traffic state, e.g., density, for control purposes, particularly in coordinated intersection groups. In comparison to state-of-the-art studies, the analyses indicate that the comprehensive framework, which ranges from critical routes identification and network partition to traffic signal control based on AVI data, significantly enhances network performance by reducing the queue length and average delay at intersections.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105019"},"PeriodicalIF":7.6,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349332","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":"Novel pavement crack detection sensor using coordinated mobile robots","authors":"Mohammad Alkhedher ,&nbsp;Abdullah Alsit ,&nbsp;Marah Alhalabi ,&nbsp;Sharaf AlKheder ,&nbsp;Abdalla Gad ,&nbsp;Mohammed Ghazal","doi":"10.1016/j.trc.2025.105021","DOIUrl":"10.1016/j.trc.2025.105021","url":null,"abstract":"<div><div>This paper proposes a novel pavement crack detection sensor using coordinated mobile robots. The comfort of drivers and the economic efficiency are negatively affected by pavement deterioration due to weather and constant vehicle use. Our proposed system consists of a drone and an unmanned ground robot that checks the quality of roads and shows where cracks and other problems are by measuring and reporting all kinds of irregularities in road surfaces in an autonomous manner. The design of our system is a one-of-a-kind dual-cart unmanned ground vehicle, with its first cart being a drone-mounting body. The drone is equipped with a high-resolution camera for the inspection of roads, cracks, and anomalies remotely using image processing and artificial intelligence. In the event that a crack is identified, a signal is sent to the robot, instructing it to carry out a more comprehensive crack inspection. This inspection involves the use of close-range laser depth and thermal cameras to generate the pavement cracks’ depth maps accurately. We incorporate a drone into our proposed coordinated mobile robots system to enable cheaper operations and provide aerial coverage, preventing traffic congestion. Our novel pavement crack detection sensor can be incorporated with governmental agencies such as the Ministry of Transportation, the Municipality, and Civil Defence entities. Pavement and road health surveys can be completed in over fifty percent less time using our coordinated mobile robots system.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105021"},"PeriodicalIF":7.6,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust lane change decision for autonomous vehicles in mixed traffic: A safety-aware multi-agent adversarial reinforcement learning approach","authors":"Tao Wang ,&nbsp;Minghui Ma ,&nbsp;Shidong Liang ,&nbsp;Jufen Yang ,&nbsp;Yansong Wang","doi":"10.1016/j.trc.2025.105005","DOIUrl":"10.1016/j.trc.2025.105005","url":null,"abstract":"<div><div>As autonomous driving technology advances, scenarios where autonomous vehicles coexist with human-driven vehicles will become increasingly common. However, existing lane-changing decision models often overlook the vulnerability to adversarial attacks and the complexity of traffic scenarios, leading to the risk of erroneous decisions in mixed traffic flows, which could result in catastrophic consequences. To address these issues, this paper proposes a novel dual-layer lane-changing decision-making algorithm to enhance the safety and reliability of autonomous vehicles in complex environments. The upper layer of the algorithm is based on a Multi-Agent framework, where adversarial learning is used to optimize decision strategies, allowing vehicles to adapt to various interferences and obstacles. The lower layer introduces a collision avoidance mechanism based on the principles of yielding and action masking, effectively reducing the risk of collisions. Experimental results under various traffic densities and disturbance conditions demonstrate that the proposed algorithm significantly improves the robustness of system, safety, and driving efficiency in complex conditions.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105005"},"PeriodicalIF":7.6,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143140248","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 prediction models by considering different time granularity of features and target: Problem and solution","authors":"Ran Yan ,&nbsp;Shuo Jiang ,&nbsp;Kai Wang ,&nbsp;Shuaian Wang","doi":"10.1016/j.trc.2025.105002","DOIUrl":"10.1016/j.trc.2025.105002","url":null,"abstract":"<div><div>In many prediction tasks, a common characteristic of training datasets is that features are more frequently updated than target, or in other words, the time granularity, or granularity for short, of features is smaller than that of target. One typical example is predicting ship fuel consumption in maritime transport. <em>Current practice</em> usually ignores such characteristic when developing the prediction models, which may jeopardize prediction accuracy and reliability. However, this issue is neither systematically discussed nor addressed in existing literature. To bridge this gap, this study aims to formally discuss the differences in the granularity of features and target as an ubiquitous issue in prediction problems. Then, an innovative <em>two-stage tree-based approach</em> that considers such differences by maximizing the usage of more frequently updated features is developed. We then go a step further to extend the proposed <em>two-stage tree-based approach</em> to predict accumulative target considering monotonicity and data generation process. Extended numerical experiments using simulated and real datasets in maritime and urban transportation are conducted to verify the superiority of the <em>two-stage tree-based approach</em> and its extension.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"172 ","pages":"Article 105002"},"PeriodicalIF":7.6,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143140247","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":"MoMaS: Two-sided Mobility Market Simulation Framework for Modeling Platform Growth Trajectories","authors":"Farnoud Ghasemi,&nbsp;Rafal Kucharski","doi":"10.1016/j.trc.2024.104990","DOIUrl":"10.1016/j.trc.2024.104990","url":null,"abstract":"<div><div>Mobility platforms such as Uber and DiDi have been introduced in cities worldwide, each demonstrating varying degrees of success, employing diverse strategies, and exerting distinct impacts on urban mobility. We have observed various growth trajectories in two-sided mobility markets and understood the underlying mechanisms. However, to date, a realistic microscopic model of these markets including phenomena such as network effects has been missing. State-of-the-art methods well estimate the macroscopic equilibrium conditions in the market, but struggle to reproduce the individual human behavior behind and complex growth patterns sensitive to platform strategy and policies.</div><div>To bridge this gap, we introduce the <strong>MoMaS</strong> (two-sided Mobility Market Simulation) framework to represent growth mechanism in two-sided mobility markets based on the realistic behavior adjustment of drivers and travelers reactive to platform strategy. In the proposed framework, traveler and driver agents learn the platform utility from multiple channels: their own experience, peers’ word-of-mouth, and the platform’s marketing, all-together constituting the agent’s perceived utility of the platform. Each of these channels is modeled and updated by our S-shaped learning model day-to-day which stabilizes, and at the same time, remains sensitive to the system changes. The platform can simulate any strategy on five levers: trip fare, commission rate, discount rate, incentive rate, and marketing.</div><div>While detailed empirical data and actual strategies for platform growth remain largely unknown, MoMaS allows to reproduce series of plausible growth trajectories that were previously unattainable. The framework facilitates the modeling of individual-level behaviors such as reluctance, neutrality, and loyalty, alongside aggregate-level dynamics like critical mass, bandwagon effects, and both positive and negative cross-side network effects.</div><div>We illustrate the capabilities of MoMaS through an extensive set of real-world experiments. Our results demonstrate that once the platform acquires critical mass, it triggers a significant positive cross-side network effect, accelerating growth. However, this can be reversed if a negative cross-side network effect is triggered, leading to the collapse of the platform. MoMaS is applicable for real-sized problems and available on public repository along with reproducible experiments.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104990"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143104804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A composite transportation network design problem with land-air coordinated operations","authors":"Honggang Zhang ,&nbsp;Jinbiao Huo ,&nbsp;Churong Chen ,&nbsp;Zhiyuan Liu","doi":"10.1016/j.trc.2024.104967","DOIUrl":"10.1016/j.trc.2024.104967","url":null,"abstract":"<div><div>With the advent of electric vertical-takeoff-and-landing (eVTOL) vehicles, it becomes imperative to assess their impact on transportation network efficiency. Hence, this paper introduces a novel model for the composite transportation network design problem (CTNDP). Specifically, the model is designed to inform the planning of composite transportation networks by considering travel behaviors of land-air coordinated mobility. This innovative model is formulated as a bi-level programming problem, in which the upper-level model focuses on strategically planning vertiport locations and capacities, thereby reducing the total travel time within the transportation system. Upon determining decisions at the upper level, the composite transportation network can be established by constructing new links that interconnect the vertiports and existing road networks. The lower-level model addresses the land-air collaboration network equilibrium (LAC-NE) problem through mathematical programming. To solve the bi-level programming problem, a customized Bayesian optimization method, namely the mixed-integer Bayesian optimization (MI-BO) method, is proposed. Specifically, MI-BO is developed by incorporating the branch-and-bound algorithm into the Bayesian optimization framework. Additionally, an advanced path-based improved gradient projection (IGP) algorithm is developed to efficiently resolve the LAC-NE problem. The efficacy of the proposed model and solution algorithms are substantiated through numerical experiments, and the results illustrate the impact of land-air coordinated operations on the performance of the composite transportation network.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104967"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143095590","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 demand-oriented and energy-efficiency train timetabling and rolling stock circulation planning for an urban rail transit line","authors":"Yu Huang,&nbsp;Wenliang Zhou,&nbsp;Guangming Xu,&nbsp;Lianbo Deng","doi":"10.1016/j.trc.2024.104993","DOIUrl":"10.1016/j.trc.2024.104993","url":null,"abstract":"<div><div>Saving energy has both significant environmental benefits and economic advantages. As the urban rail transit network and its consumed energy continue to expand, it is crucial to optimize the energy-saving operation scheme of trains. Energy-saving train operation often requires longer section running times, which is obviously not conducive to the quality of passenger service. In order to ensure passenger service quality when pursuing the decrease of the train’s energy consumption and rolling stocks’ operation cost, this paper proposes an integrated optimization model of the demand-oriented and energy-efficiency train timetable and rolling stock circulation plan for urban rail transit. Its objective is to minimize train net energy consumption, rolling stock utilization cost, as well as passenger waiting time and travel time. Specifically, the net energy consumption is defined as the difference between train required traction energy consumption and regenerative braking energy utilization. To efficiently solve this large-scale mixed integer nonlinear model, we design a solution algorithm combining Variable Neighborhood Search (VNS) and CPLEX, in which seven different neighborhood structures are constructed. Based on the data of Guangzhou Metro Line 13, we have verified the effectiveness and performance of the model and algorithm through numerical experiments of various scales, as well as through comparisons with other algorithms and models. The results demonstrate that the timetable and rolling stock circulation plan obtained by VNS can reduce net energy consumption by 9.55 %, rolling stock utilization cost by 9 %, and passenger waiting time by 4.77 %, and their travel time by 0.87 % compared to the current timetable.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104993"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096023","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}