Transportation Research Part C-Emerging Technologies最新文献

{"title":"Mitigating metropolitan carbon emissions with dynamic eco-driving at scale","authors":"Vindula Jayawardana ,&nbsp;Baptiste Freydt ,&nbsp;Ao Qu ,&nbsp;Cameron Hickert ,&nbsp;Edgar Sanchez ,&nbsp;Catherine Tang ,&nbsp;Mark Taylor ,&nbsp;Blaine Leonard ,&nbsp;Cathy Wu","doi":"10.1016/j.trc.2025.105146","DOIUrl":"10.1016/j.trc.2025.105146","url":null,"abstract":"<div><div>The sheer scale and diversity of transportation make it a formidable sector to decarbonize. Here, we consider an emerging opportunity to reduce carbon emissions: the growing adoption of semi-autonomous vehicles, which can be programmed to mitigate stop-and-go traffic through intelligent speed commands and, thus, reduce emissions. But would such <em>dynamic eco-driving</em> move the needle on climate change? A comprehensive impact analysis has been out of reach due to the vast array of traffic scenarios and the complexity of vehicle emissions. Such an analysis would require careful modeling of many traffic scenarios and solving an eco-driving problem at each one of them - a challenge that has been out of reach for previous studies. We address this challenge with large-scale scenario modeling efforts and by using multi-task deep reinforcement learning with a carefully designed network decomposition strategy. We perform an in-depth prospective impact assessment of dynamic eco-driving at 6,011 signalized intersections across three major US metropolitan cities, simulating a million traffic scenarios. Overall, we find that vehicle trajectories optimized for emissions can cut city-wide intersection carbon emissions by 11%–22%, without harming throughput or safety, and with reasonable assumptions, equivalent to the national emissions of Israel and Nigeria, respectively. We find that 10% eco-driving adoption yields 25%–50% of total reduction, and nearly 70% of the benefits come from 20% of intersections, suggesting near-term implementation pathways. However, the composition of this high-impact subset of intersections varies considerably across different adoption levels, with minimal overlap, calling for careful strategic planning for eco-driving deployments. Moreover, the impact of eco-driving, when considered jointly with projections of vehicle electrification, hybrid vehicle adoption, and travel growth, remains significant. More broadly, this work paves the way for large-scale analysis of traffic externalities, such as time, safety, and air quality, and the potential impact of solution strategies. Visual details can be found on the project page <span><span>https://vindulamj.github.io/eco-drive</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105146"},"PeriodicalIF":7.6,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780128","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":"Estimating the value of safety against road crashes: A stated preference experiment on route choice of food delivery riders","authors":"Kuldeep Kavta ,&nbsp;Shadi Sharif Azadeh ,&nbsp;Yousef Maknoon ,&nbsp;Yihong Wang ,&nbsp;Gonçalo Homem de Almeida Correia","doi":"10.1016/j.trc.2025.105272","DOIUrl":"10.1016/j.trc.2025.105272","url":null,"abstract":"<div><div>The rapid growth of the online food delivery industry has led to a significant increase in the number of delivery riders navigating urban streets, predominantly using bikes and e-bikes. This growth has been accompanied by a concerning rise in crashes involving these riders, posing a critical challenge for city authorities and policymakers. Promoting safer riding behavior, such as choosing safer routes while delivering food, can potentially reduce crash risks. With this motivation, this paper aims to evaluate the effectiveness of strategies that encourage riders to choose safer routes and estimate the value riders place on reducing the risk of road crashes. The paper presents a stated preference experiment conducted with food delivery riders in Amsterdam and Copenhagen to assess two targeted strategies: ’safety information’ and ’monetary incentives’, designed to encourage riders toward selecting safer routes. The results from the route choice model show that presenting information about safety against crashes on different routes and offering monetary incentives can effectively motivate riders to choose safer routes, even if these are longer. The trade-offs riders make between safer and shorter routes were quantified by calculating the Value of Risk Reduction (VRR) and Willingness to Accept (WTA) indicators, which offer valuable insights into riders’ safety preferences. These indicators highlight how much riders value risk reduction and the compensation required to choose safer routes. Furthermore, the findings reveal that factors related to riders’ working arrangements and socio-demographic profiles significantly influence their route choice decisions. The paper concludes with a discussion about the practical challenges associated with implementing the strategies to enhance rider safety and proposing potential solutions that can be useful for food delivery platforms and policymakers.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105272"},"PeriodicalIF":7.6,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780129","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":"Modeling car-following behaviors considering driver heterogeneity: A multi-regime stochastic framework","authors":"Shubo Wu ,&nbsp;Dong Ngoduy ,&nbsp;Zhengbing He ,&nbsp;Yajie Zou ,&nbsp;Jian Sun","doi":"10.1016/j.trc.2025.105282","DOIUrl":"10.1016/j.trc.2025.105282","url":null,"abstract":"<div><div>Car-following behavior exhibits stochastic characteristics influenced by the inherent randomness of human drivers. Stochastic models have been extensively developed to capture the probabilistic nature of car-following behavior dynamics. However, the time-varying nature driven by driver heterogeneity has not been adequately studied. To this end, this paper proposes a stochastic modeling framework that incorporates multi-regime car-following models with a Bayesian calibration approach to account for the driver heterogeneity in human car-following behaviors. More specifically, our framework employs a K-means clustering algorithm to categorize human drivers into three driving styles and leverages a hierarchical Dirichlet process-hidden semi-Markov model (HDP-HSMM) to segment car-following sequences into diverse driving regimes, thereby capturing driver heterogeneity. According to the segmented driving regimes, three distinct hierarchies of multi-regime Bayesian intelligent driver models (denoted pooled, hierarchical, and unpooled B-IDM) are developed to capture the time-varying nature of car-following behaviors across diverse driving regimes. These models are well-calibrated using a Bayesian approach with car-following trajectory data extracted from the Waymo open motion dataset and Lyft level-5 dataset. Deterministic and stochastic simulations are performed to evaluate the effectiveness of the proposed stochastic modeling framework. The experimental results demonstrate significant differences in car-following behaviors across various driving styles and driving regimes. The proposed framework effectively represents these heterogeneous car-following behaviors through the developed multi-regime hierarchical B-IDM with time-varying parameters. Additionally, the stochastic simulation achieves a more accurate representation than the deterministic simulation in replicating the dynamics of human car-following behaviors.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105282"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771531","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":"Crash event detection using acoustic conformer","authors":"Zubayer Islam,&nbsp;Mohamed Abdel-Aty","doi":"10.1016/j.trc.2025.105275","DOIUrl":"10.1016/j.trc.2025.105275","url":null,"abstract":"<div><div>Crash events identification and prediction plays a vital role in understanding safety conditions for transportation systems. While existing systems use traffic parameters correlated with crash data to classify and train these models, we propose the use of a novel sensory unit that can also accurately identify crash events: microphone. Audio events can be collected and analyzed to classify events such as crash. In this paper, we have demonstrated the use of an Acoustic Conformer, a convolution augmented transformer, for road event classification. The conformer is able to apprehend global features with a transformer while local features are captured by the Convolution module. Important audio parameters such as Mel Frequency Cepstral Coefficients (MFCC), log Mel-filterbank energy spectrum and Fourier Spectrum were used as feature set. Additionally, the dataset was augmented with more sample data by the use of audio augmentation techniques such as time and pitch shifting. Together with the feature extraction this data augmentation can achieve reasonable accuracy. Four events such as crash, tire skid, horn and siren sounds can be accurately identified giving indication of a road hazard that can be useful for traffic operators or paramedic. The proposed methodology can reach 83% f1-score with a recall of 85%.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105275"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive and flexible rail transit network service dispatching as a partially observable Markov decision process","authors":"Shou-yi Wang ,&nbsp;Andy H.F. Chow ,&nbsp;Cheng-shuo Ying","doi":"10.1016/j.trc.2025.105286","DOIUrl":"10.1016/j.trc.2025.105286","url":null,"abstract":"<div><div>This paper presents a novel adaptive train scheduling framework with flexible fleet sizes for routing and scheduling in network-wide rail transit services. This framework aims to minimize both passenger waiting times and operating costs driven by prevailing passenger demand. The train scheduling problem is formulated as a partially observable Markov decision process (POMDP) to reflect the practicality in training and real-world applications. To address the computational challenges associated with the train scheduling problem, deep reinforcement learning techniques are applied to seek potential optimal solutions to the optimization problem. The proposed train scheduling framework is tested using real-world scenarios and the data collected from the Hong Kong Light Rail Transit (LRT) network. The experiment results demonstrate that the proposed train scheduling framework using flexible fleet sizes can effectively reduce passenger waiting time and operating costs. This study contributes to the real-time routing and scheduling of network-wide rail transit services by advanced optimization technology.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105286"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771527","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 multi-task Transformer with mixture-of-experts for personalized periodic predictions of individual travel behavior in multimodal public transport","authors":"Haoning Xi ,&nbsp;Zhiqi Shao ,&nbsp;David A. Hensher ,&nbsp;John D. Nelson ,&nbsp;Huaming Chen ,&nbsp;Kasun Wijayaratna","doi":"10.1016/j.trc.2025.105287","DOIUrl":"10.1016/j.trc.2025.105287","url":null,"abstract":"<div><div>Integrated multimodal public transport (PT) systems are reshaping urban mobility by providing personalized travel experiences tailored to individual users. A critical challenge in realizing personalized mobility is predicting users’ periodic travel behaviors to capture each user’s evolving travel preferences and patterns. Big data and AI have opened new opportunities to accurately predict individual travel behavior, which is a critical initial step toward effective planning of personalized mobility bundle subscriptions and improvement of mobility services. This study proposes a novel framework, <span>PTBformer-MMoE</span>, for personalized periodic prediction of individual travel behavior, specifically predicting each user’s monthly mode-specific travel frequency class (classification tasks) and each user’s monthly expected travel fare (regression task), using the user’s most recent travel records. Within the multi-gate mixture-of-experts (MMoE) framework, each expert network is realized by a <span>PTBformer</span>, and each gate determines the weighted contributions of expert outputs relevant to a specific task tower. The <span>PTBformer</span> integrates two key modules, i.e., a Multi-mode Transformer employing multi-feature self-attention for continuous time-series travel data; and an OD Transformer capturing OD-specific travel features with multi-OD self-attention. Evaluated on a multimodal (bus, rail, ferry, and tram) dataset with over 0.96 billion travel records of 1.58 million users in Queensland, Australia, during 01/2021<span><math><mo>−</mo></math></span>01/2023, the proposed <span>PTBformer-MMoE</span> demonstrates state-of-the-art performance in predicting each user’s monthly mode-specific travel frequency class and monthly expected travel fare compared to 9 baseline models, setting a new benchmark for individual travel behavior predictions. The predictive capabilities of <span>PTBformer-MMoE</span> demonstrate its significant potential for real-world applications such as personalized mobility subscriptions, targeted recommendations, and optimized demand management, ultimately paving the way toward data-driven and user-centric multimodal PT systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105287"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771528","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 multi-modal ride-matching with transfers","authors":"Patrick Stokkink ,&nbsp;André de Palma ,&nbsp;Nikolas Geroliminis","doi":"10.1016/j.trc.2025.105274","DOIUrl":"10.1016/j.trc.2025.105274","url":null,"abstract":"<div><div>One of the limitations of ride-sharing is that matched drivers and riders need to have similar itineraries and desired arrival times for ride-sharing to be competitive against other transport modes. By allowing a single transfer at a designated transfer hub, their itineraries need to be only partially similar, and therefore more matching options are created. In this paper, we develop an optimal matching approach that matches riders to drivers, taking into account multi-modal routing options to model competition and collaboration between multiple modes of transport. We allow for transfers between modes and between multiple drivers. We model this as a path-based integer programming problem and we develop a simulated annealing algorithm to efficiently solve realistic large-scale instances of the problem.</div><div>Our analysis indicates that a single transfer hub can reduce significantly the average generalized cost of riders and the total vehicle hours traveled by creating efficient matches. As opposed to previous studies, our work shows that ride-sharing not only attracts former public transport users but also former private car users. By allowing for intermodal transfers and by choosing the cost parameters such that transfers are favorable, itineraries where commuters use their car first, before sharing a ride on the second part of their journey, becomes an appealing alternative. Multi-modal ride-matching with transfers has the potential to increase ride-sharing, reduce the number of vehicle hours traveled in private cars, and reduce the number of cars that are present in urban areas during peak hours of congestion.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105274"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771529","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 hybrid e-bike sharing system design problem considering multiple types of facilities","authors":"Jiatong Song ,&nbsp;W.Y. Szeto ,&nbsp;Baicheng Li ,&nbsp;Yi Wang ,&nbsp;Xingbin Zhan","doi":"10.1016/j.trc.2025.105267","DOIUrl":"10.1016/j.trc.2025.105267","url":null,"abstract":"<div><div>Shared electric bikes (e-bikes) have become a rapidly growing mode of transportation worldwide, with electric bike-sharing systems (EBSSs) successfully implemented in numerous cities. The mainstream EBSSs can generally be categorized into two types: station-based and free-floating (or dockless). Each type has its respective advantages and disadvantages. For example, free-floating systems have a lower total construction and maintenance cost, but some users return e-bikes at improper locations without considering social impacts, such as blocking vehicle and pedestrian movements, and the induced safety issues. A hybrid e-bike sharing system (HEBSS) that combines elements from both systems has the potential to exploit the advantages of both and overcome their drawbacks, leading to an improvement in system performance. However, few existing studies have proposed a methodology to design such a system to demonstrate its effectiveness and address the inconsiderate e-bike return behavior.</div><div>In this paper, we formulate the design problem of an HEBSS as a bi-level optimization problem. The upper-level problem is to determine the locations and capacities of various facilities, including charging stations and geofencing areas, aiming to maximize social welfare under a budget constraint. The lower-level problem is an e-bike sharing network equilibrium problem with elastic demand considering the inconsiderate drop-off behavior of users, waiting time costs, roaming behavior during rental and return processes, and parking rewards and fines. The upper-level problem is solved by our proposed hybrid solution method, which is based on genetic algorithm coupled with our proposed capacity-setting heuristic. The lower-level problem is transformed into a fixed demand equivalent problem and solved by the self-regulated averaging method. We present numerical results to demonstrate the properties of the problem, identify the key factors that affect the design, illustrate the performance of the proposed hybrid solution algorithm, and provide design insights to the system operator.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105267"},"PeriodicalIF":7.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771526","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 versus diesel: Green supply chain network design with carbon footprint labeling","authors":"Ensieh Ghaedyheidary,&nbsp;Samir Elhedhli","doi":"10.1016/j.trc.2025.105277","DOIUrl":"10.1016/j.trc.2025.105277","url":null,"abstract":"<div><div>Transportation electrification and carbon footprint labeling are strong indicators of environmental commitment in green supply chains. We study this framework and assess its environmental and financial sustainability. We consider cradle-to-gate operations, from manufacturing to retail, mandate the use of electric trucks whenever their range allows, and impose a cap on product carbon footprints as would be advertised on a carbon label. We optimize the locations of distribution centers, the allocation of demand, and the transportation choices between diesel trucks and electric trucks. We account for the nonlinear relationship between emissions and payload for diesel trucks, focus on two representative functional forms- concave and convex- and propose a mixed-integer nonlinear optimization model to minimize costs and CO2-equivalent emissions. We use Lagrangean relaxation to decompose the model by echelon and isolate the convex and concave nonlinearity in an easy-to-solve subproblem. We then design a Lagrangean heuristic based on the solution of one of the subproblems, which has proven efficient and near-optimal. Based on a case study, we evaluate the impact of the emission function and the carbon label on the supply chain network, as well as the trade-off between the use of diesel trucks and electric trucks. We find that the relationship between emissions and payload for diesel trucks significantly influences the adoption of electric trucks. When concave, as would be the case for steady driving conditions, long hauls, well-maintained infrastructure, and light traffic, conventional diesel trucks continue to be the cost-efficient option, especially when electric truck mileage costs are high and the cap on unit emissions is elevated. In contrast, when diesel emissions are convex, corresponding to challenging driving conditions such as urban delivery, congested road networks, stop-and-go traffic, and degraded road infrastructure, transportation emissions dominate total emissions, diesel truck usage decreases, and electric trucks become a better choice even if the cap on unit emissions is high and diesel trucks are cheaper to operate. Furthermore, extending the range of electric trucks increases their usage under convex emissions but not under concave emissions, especially when the cap on carbon footprint is not tight.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105277"},"PeriodicalIF":7.6,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739617","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":"Goal-based neural physics vehicle trajectory prediction model","authors":"Rui Gan ,&nbsp;Haotian Shi ,&nbsp;Pei Li ,&nbsp;Keshu Wu ,&nbsp;Bocheng An ,&nbsp;Junwei You ,&nbsp;Linheng Li ,&nbsp;Junyi Ma ,&nbsp;Chengyuan Ma ,&nbsp;Bin Ran","doi":"10.1016/j.trc.2025.105283","DOIUrl":"10.1016/j.trc.2025.105283","url":null,"abstract":"<div><div>Vehicle trajectory prediction plays a vital role in intelligent transportation systems and autonomous driving, as it significantly affects vehicle behavior planning and control, thereby influencing traffic safety and efficiency. Numerous studies have been conducted to predict short-term vehicle trajectories in the immediate future. However, long-term trajectory prediction remains a major challenge due to accumulated errors and uncertainties. Additionally, balancing accuracy with interpretability in the prediction is another challenging issue in predicting vehicle trajectory. To address these challenges, this paper proposes a <strong>G</strong>oal-based <strong>N</strong>eural <strong>P</strong>hysics Vehicle Trajectory Prediction Model (<strong>GNP</strong>). The GNP model simplifies vehicle trajectory prediction into a two-stage process: determining the vehicle’s goal and then choosing the appropriate trajectory to reach this goal. The GNP model contains two sub-modules to achieve this process. The first sub-module employs a multi-head attention mechanism to accurately predict <strong>goals</strong>. The second sub-module integrates a deep learning model with a physics-based social force model to progressively predict the complete trajectory using the generated goals. The GNP demonstrates state-of-the-art long-term prediction accuracy compared to four baseline models. We provide interpretable visualization results to highlight the multi-modality and inherent nature of our neural physics framework. Additionally, ablation studies are performed to validate the effectiveness of our key designs. The source code for this work are available at: <span><span>https://github.com/mcgrche/GNP-Goal-based-Neural-Physics-Vehicle-Trajectory-Prediction-Model</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"179 ","pages":"Article 105283"},"PeriodicalIF":7.6,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722833","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}