Transportation Research Part C-Emerging Technologies最新文献

{"title":"Jam propagation in mixed traffic of autonomous and human-driven vehicles: A random walk-based analysis","authors":"Hao Guan,&nbsp;Xiangdong Chen,&nbsp;Qiang Meng","doi":"10.1016/j.trc.2025.105310","DOIUrl":"10.1016/j.trc.2025.105310","url":null,"abstract":"<div><div>Traffic jams, characterized by backward-moving waves that disrupt upstream vehicles, are a major concern in transportation that cause congestion and diminish efficiency. This study explores the role of autonomous vehicles (AVs) in mitigating jam propagation in mixed traffic with both AVs and human-driven vehicles (HVs). To capture the complex dynamics of jam propagation in mixed traffic, we develop a novel analytical model grounded in a microscopic perspective to formulate the stochastic jam propagation process and quantify the impact of jam waves in closed-form expressions. Analyses of the closed-form solutions reveal how capacity drops amplify jam waves and identify critical conditions under which AVs can effectively mitigate congestion. Building on these theoretical insights, we use the random walk model to propose enhanced slow-in strategies and validate their effectiveness in mitigating jam propagation through numerical simulations. By modeling the stochastic nature of jam propagation and mitigation, this study contributes to a deeper understanding of AVs’ potential to improve traffic flow, providing a basis for future research on managing mixed traffic systems in the era of AV adoption.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105310"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048891","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":"Prediction of ship risk by a monotonic decision tree","authors":"Ran Yan ,&nbsp;Shuo Jiang ,&nbsp;Panagiotis Angeloudis ,&nbsp;Xinhu Cao ,&nbsp;Jing Wang ,&nbsp;Shuaian Wang","doi":"10.1016/j.trc.2025.105317","DOIUrl":"10.1016/j.trc.2025.105317","url":null,"abstract":"<div><div>Ship inspections as part of the port state control (PSC) process can ensure that major international conventions and regulations are complied with by foreign visiting ships. Due to the scarcity of inspection resources and concerns over prolonged inspection time, accurate identification of ships with higher risk is necessary for PSC. While previous studies have developed data-driven models to predict vessel’s risk profile, domain knowledge is not adequately integrated into existing models. The gap can challenge the model’s performance, as well as the trustworthiness, which can subsequently affect industry adoption. To bridge the knowledge gap, this study develops a monotonic regression decision tree model to predict ships’ risk profiles. The monotonicity is realized by first constructing a normal regression decision tree. Then, the outputs of the tree are revised by an optimization model whose objective is to minimize the prediction error with monotonicity constraints to guarantee that the outputs follow domain knowledge while retaining the tree structure. Real inspection records at the Port of Hong Kong are used to validate model performance in terms of monotonicity and accuracy. In addition to the enhanced interpretability and trustworthiness from monotonicity, improvement on accuracy performance is also observed on the proposed model. Moreover, the proposed model is applicable to a wide range of regression problems, such as shipping emission prediction, where monotonicity constraints shall be applied.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105317"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048890","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":"Dynamic partitioning of heterogeneously loaded road networks: A two-level regionalization scheme with Monte Carlo tree search","authors":"Cheng Hu ,&nbsp;Jinjun Tang ,&nbsp;Junjie Hu ,&nbsp;Yaopeng Wang ,&nbsp;Zhitao Li ,&nbsp;Jie Zeng ,&nbsp;Chunyang Han","doi":"10.1016/j.trc.2025.105341","DOIUrl":"10.1016/j.trc.2025.105341","url":null,"abstract":"<div><div>This paper proposes a novel dynamic road network partitioning framework tailored for hierarchical network control based on macroscopic fundamental diagrams. The framework establishes a subregion-region system that can be used for both dynamic road network partitioning and perimeter control strategies through a two-level regionalization model. The first level of regionalization is formulated as a mixed-integer quadratic programming (MIQP) problem, and a specialized max-p region algorithm is designed to solve it. An adaptive large neighborhood search (ALNS) algorithm is introduced to optimize the road network partitioning at the subregion level. Treating each subregion as a fundamental geographic unit, the second level of regionalization is modeled as a mixed-integer linear programming (MILP) model. Due to the significant reduction in the problem size, this model can be solved exactly using a solver. Subsequently, dynamic road network partitioning is achieved by performing multiple boundary subregion movements at discrete time points, based on past network partitioning solutions. This partitioning update process is described using a Markov decision process (MDP), and a Monte Carlo tree search (MCTS) algorithm is designed to iteratively determine the optimal movement actions. The performance of the two-level regionalization method in static road network partitioning is analyzed using the urban road network of Yuelu District in Changsha, China. The dynamic road network partitioning method is tested through simulations on a grid network and the urban road network of Bilbao, Spain. The results validate the effectiveness of the proposed framework, which provides valuable insights and practical support for embedding dynamic road network partitioning methods into network-level traffic control strategies.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105341"},"PeriodicalIF":7.6,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048888","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 computational graph-based model and a back-propagation solution algorithm for a networked train rescheduling problem","authors":"Junduo Zhao,&nbsp;Haiying Li,&nbsp;Xiaojie Luan,&nbsp;Lingyun Meng,&nbsp;Zhengwen Liao","doi":"10.1016/j.trc.2025.105323","DOIUrl":"10.1016/j.trc.2025.105323","url":null,"abstract":"<div><div>Real-time train rescheduling is of more significant requirements on both the computation time and solution performance compared to offline scheduling. The motivation for this study is to develop an efficient and effective method to reschedule disrupted trains in the context of severe disruptions, e.g., a four-hour segment blockage. A novel computational graph (CG)-based model is proposed to provide a continuous representation of the problem, wherein the discrete “if-then” decision-making process is transformed into continuous numerical computations that can be efficiently addressed. A customized back-propagation (BP) algorithm is developed to refine the solutions through an iterative process that includes a forward calculation of the objective function and a backward derivation of the decision variables. Owing to these computationally efficient processes, our proposed methodology can effectively handle the increasing complexity arising from detailed mesoscopic-level formulations in large-scale instances. We conduct experiments on both a small hypothetical network and the real-world Chinese high-speed railway network to validate the effectiveness and efficiency of our method. We also perform experimental analysis to examine the appropriate parameter settings for improved system performance.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105323"},"PeriodicalIF":7.6,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027063","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 impact of autonomous vehicles on ride-hailing platforms with strategic human drivers","authors":"Shuqin Gao ,&nbsp;Xinyuan Wu ,&nbsp;Antonis Dimakis ,&nbsp;Costas Courcoubetis","doi":"10.1016/j.trc.2025.105326","DOIUrl":"10.1016/j.trc.2025.105326","url":null,"abstract":"<div><div>We consider a ride-hailing platform that operates a mixed fleet of autonomous vehicles (AVs) and conventional vehicles (CVs), where AVs are fully controlled by the platform and CVs are operated by self-interested human drivers. Each vehicle is modeled using a Markov Decision Process where the vehicle maximizes long-run average rewards by choosing its repositioning actions. The behavior of CVs corresponds to a large-scale game in which agents interact through resource constraints that result in fluid queues. To optimize the mixed AV–CV system for arbitrary networks, we formulate a bi-level optimization problem <span><math><mi>OPT</mi></math></span> in which the platform moves first by controlling the demand revealed to the CVs and subsequently assigning the optimal actions to the AVs, while the CVs react by forming an equilibrium characterized by the solution to a convex optimization problem. We prove several structural properties of the optimal solution and analyze simple heuristics, such as AV-first, where we solve for the optimal dispatch of AVs without taking into account the subsequent reaction of CVs. We also propose three numerical algorithms to solve <span><math><mi>OPT</mi></math></span>, which is a non-convex non-smooth problem, and evaluate their performance for large networks. Finally, we use our computational tools to show some interesting trends in the optimal AV–CV fleet dimensioning when vehicle supply is exogenous and endogenous, and apply these results to New York City using demand and trip-time data from real-world taxi service datasets. Our results suggest that our model can be used to predict traffic behavior and optimize mixed-fleet deployment given topology and cost/reward information.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105326"},"PeriodicalIF":7.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019636","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":"Traffic-IT: Enhancing traffic scene understanding for multimodal large language models","authors":"Senyun Kuang ,&nbsp;Yang Liu ,&nbsp;Xiaobo Qu ,&nbsp;Yintao Wei","doi":"10.1016/j.trc.2025.105325","DOIUrl":"10.1016/j.trc.2025.105325","url":null,"abstract":"<div><div>In recent years, the convergence of artificial intelligence and urban infrastructure has driven transformative advances in intelligent transportation systems (ITS). However, traditional models often lack the generalizability needed to adapt to diverse traffic scenarios. Multimodal large language models (MLLMs) offer a promising solution, yet they are typically trained on general datasets, limiting their effectiveness in specific transportation contexts. To address this, we introduce Traffic-IT, a dataset comprising 220,950 question-and-answer pairs from 30,000 images, designed to enhance MLLMs’ capabilities in traffic scene understanding. The dataset covers various traffic scenarios, including weather conditions, locations, and times of day, providing in-depth insights and driving strategies tailored to real-world needs. Created through expert consultation and rigorous validation, Traffic-IT significantly improves MLLMs’ performance in interpreting complex traffic scenes. We anticipate that Traffic-IT will be a crucial resource for future developments in smart city applications.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105325"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010510","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":"Inference of signal phase and timing with low penetration rate vehicle trajectories","authors":"Xingmin Wang ,&nbsp;Zihao Wang ,&nbsp;Zachary Jerome ,&nbsp;Henry X. Liu","doi":"10.1016/j.trc.2025.105324","DOIUrl":"10.1016/j.trc.2025.105324","url":null,"abstract":"<div><div>Traffic signals are a crucial component of urban traffic networks, and signal phase and timing (SPaT) information serves as an essential input for various urban traffic operational applications. Obtaining SPaT information on a large scale is challenging due to the diversity of traffic signal controllers from different manufacturers and jurisdictions. With the advent of broadly defined connected vehicles, vehicle trajectories can be leveraged to estimate SPaT information since they are directly controlled by traffic signals. Although some existing studies have proposed methods for estimating SPaT information using vehicle trajectory data, most are limited to fixed-time traffic signals. To address this limitation, this paper proposes a suite of SPaT inference algorithms applicable to both fixed-time and responsive signals. With only low penetration rate vehicle trajectory data as input, the inference program can estimate the complete SPaT information for traffic signals with fixed cycle lengths and the average cycle/splits for those with time-varying cycle lengths. The proposed method is validated through case studies at real-world intersections.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105324"},"PeriodicalIF":7.6,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003600","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":"RuleNet: rule-priority-aware multi-agent trajectory prediction in ambiguous traffic scenarios","authors":"Ruolin Shi ,&nbsp;Xuesong Wang ,&nbsp;Yang Zhou ,&nbsp;Meixin Zhu","doi":"10.1016/j.trc.2025.105339","DOIUrl":"10.1016/j.trc.2025.105339","url":null,"abstract":"<div><div>Accurately predicting surrounding traffic participants’ intentions and future trajectories is essential for automated vehicles in interactive scenarios. These interactions often involve diverse semantic interpretations embedded within different traffic rules. Accordingly, learning the priority characteristics of traffic rules offers a promising pathway to improving prediction performance. However, traffic rules are frequently ambiguous and are overlooked by trajectory prediction models. To address this issue, this paper introduces RuleNet, a multi-agent trajectory prediction framework that incorporates the priority evaluation of ambiguous traffic rules. RuleNet consists of three primary components. First, built upon Graph Neural Networks, it extracts agent kinematics, road topology, and traffic rule representations. Next, a multi-attention mechanism is employed to model interactions among agents, between historical and predicted trajectories, and across different prediction modes, thereby generating initial trajectory proposals. Finally, a rule-guided refinement module is introduced to adjust the predictions in accordance with learned rule priorities. This study focuses on two key traffic rule categories: safety and right-of-way, which are quantified using time to collision and relative distance, depending on the interaction type. Rule priorities are calculated through Signal Temporal Logic robustness measures and integrated into the prediction refinement process. Comprehensive experiments on the INTERACTION dataset validate the effectiveness of RuleNet. Results show that it outperforms existing baselines, achieving a 1.8–5.1% increase in prediction accuracy and a 16.8% improvement in safety. Furthermore, ablation studies are conducted to examine the influence of individual rule types and fusion strategies on model performance. The findings highlight three main findings: 1) Distance-based rules considerably improve prediction accuracy in ambiguous intersection scenarios. 2) Temporal rules are more influential in interactions involving vulnerable road users than in vehicle-to-vehicle cases. 3) Integrating rule priorities into both feature extraction and attention mechanisms yields the best overall performance.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105339"},"PeriodicalIF":7.6,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003605","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":"Agentic Large Language Models for day-to-day route choices","authors":"Leizhen Wang ,&nbsp;Peibo Duan ,&nbsp;Zhengbing He ,&nbsp;Cheng Lyu ,&nbsp;Xin Chen ,&nbsp;Nan Zheng ,&nbsp;Li Yao ,&nbsp;Zhenliang Ma","doi":"10.1016/j.trc.2025.105307","DOIUrl":"10.1016/j.trc.2025.105307","url":null,"abstract":"<div><div>Understanding travelers’ route choices can help policymakers devise optimal operational and planning strategies for both normal and abnormal circumstances. However, existing choice modeling methods often rely on predefined assumptions and struggle to capture the dynamic and adaptive nature of travel behavior. Recently, Large Language Models (LLMs) have emerged as a promising alternative, demonstrating remarkable ability to replicate human-like behaviors across various fields. Despite this potential, their capacity to accurately simulate human route choice behavior in transportation contexts remains doubtful. To satisfy this curiosity, this paper investigates the potential of LLMs for route choice modeling by introducing an LLM-empowered agent, “LLMTraveler.” This agent integrates an LLM as its core, equipped with a memory system that learns from past experiences and makes decisions by balancing retrieved data and personality traits. The study systematically evaluates the LLMTraveler’s ability to replicate human-like decision-making through two stages of day-to-day (DTD) congestion games: (1) analyzing its route-switching behavior in single origin–destination (OD) pair scenarios, where it demonstrates patterns that align with laboratory data but cannot be fully captured by traditional models, and (2) testing its capacity to model adaptive learning behaviors in multi-OD scenarios on the Ortuzar and Willumsen (OW) network, producing results comparable to Multinomial Logit (MNL) and Reinforcement Learning (RL) models. Additionally, the study assesses lightweight, open-source LLMs, highlighting their effectiveness in route choice simulation and their potential as cost-effective alternatives to more advanced closed-source models. These experiments demonstrate that the framework can partially replicate human-like decision-making in route choice while providing natural language explanations for its decisions. This capability offers valuable insights for transportation policymaking, such as simulating traveler responses to new policies or changes in the network. The code for this paper is open-source and available at: <span><span>https://github.com/georgewanglz2019/LLMTraveler</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105307"},"PeriodicalIF":7.6,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004869","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 reconstruction of fragmented trajectories: An integrated machine learning and behavior-based spatiotemporal framework","authors":"Hossameldin Helal,&nbsp;Mohamed Hussein","doi":"10.1016/j.trc.2025.105333","DOIUrl":"10.1016/j.trc.2025.105333","url":null,"abstract":"<div><div>High-quality road user trajectories are essential for various transportation applications. Despite the significant advancement of detection and tracking technologies, observed trajectories often suffer from several issues that impact their applicability, such as intrinsic errors, noise, and fragmentation. This paper introduces a real-time reconstruction framework for road user trajectories, designed to reconstruct coherent trajectories from potentially fragmented segments. The framework begins with processing the raw trajectories to extract several dynamic features such as velocity, acceleration, curvature, and heading. A Random Forest classifier is then utilized to identify trajectory segments likely belonging to the same path. The classifier incorporates the Subsequence Dynamic Time Warping (sDTW) metric and other spatiotemporal features. Next, similar segments are grouped into cohesive clusters where a trajectory reconstruction module merges the identified segments and interpolates missing segments using the Gaussian kernel-based regression. Finally, the reconstructed trajectories are smoothed using integrated wavelet transforms and Savitzky-Golay filters. The framework was trained and validated using trajectory data acquired from the Lyft Level 5 AV dataset. We focused on the reconstruction of pedestrian and cyclist trajectories due to their inherent complexity and unpredictability. Validation results confirmed the accuracy of the different system components as well as the accuracy of the reconstructed trajectories compared to ground truth data (RMSE of 0.1138 m and MAPE of 0.01%). Computational assessments indicate that the framework scales linearly with data size, with optimal performance for real-time applications achieved for 5- to 10-minute windows.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105333"},"PeriodicalIF":7.6,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997220","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}