Communications in Transportation Research最新文献

{"title":"Sustainable operational strategies for mixed fleets: Integrating autonomous and human-driven taxis with heterogeneous energy types","authors":"Qinru Hu ,&nbsp;Beinuo Yang ,&nbsp;Keyang Zhang ,&nbsp;Jose Escribano Macias ,&nbsp;Xiqun (Michael) Chen ,&nbsp;Yanfeng Ouyang ,&nbsp;Simon Hu","doi":"10.1016/j.commtr.2025.100171","DOIUrl":"10.1016/j.commtr.2025.100171","url":null,"abstract":"<div><div>Taxi systems are transitioning into a complex integration of autonomous and human-driven vehicles powered by heterogeneous energy sources. Traditional operational strategies designed for homogeneous fleets fail to capture the unique dynamics and interactions present in mixed fleets. To address this gap, this study proposes a comprehensive modeling and simulation framework for the dynamic operation of mixed taxi fleets, including autonomous electric taxis (AETs), human-driven electric taxis, and human-driven gasoline taxis. The framework integrates centralized and decentralized control mechanisms to address the distinct characteristics of each taxi type. An integer linear programming model is developed to optimize taxi assignment and scheduling, with the objective of maximizing system profits by accounting for customer service revenues and energy and travel costs. An agent-based simulation platform is designed to model dynamic interactions among taxis, customers, and charging stations, offering continuous feedback on system performance. Real-world case studies reveal significant environmental, economic, and social benefits when incorporating operating costs into decision-making. Impact analyses demonstrate the competitiveness of AETs in passenger service due to lower operating costs and enhanced environmental efficiency, with reduced carbon emission intensity per kilometer and per request. This study provides valuable insights for taxi platforms and policymakers in formulating strategies that promote sustainable urban mobility during the ongoing transition period.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100171"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CASAformer: Congestion-aware sparse attention transformer for traffic speed prediction","authors":"Yifan Zhang ,&nbsp;Qishen Zhou ,&nbsp;Jianping Wang ,&nbsp;Anastasios Kouvelas ,&nbsp;Michail A. Makridis","doi":"10.1016/j.commtr.2025.100174","DOIUrl":"10.1016/j.commtr.2025.100174","url":null,"abstract":"<div><div>Accurate and efficient traffic speed prediction is crucial for improving roaDongguand safety and efficiency. With the emerging deep learning and extensive traffic data, data-driven methods are widely adopted to achieve this task with increasingly complicated structures and progressively deeper layers of neural networks. Despite the design of the models, they aim to optimize the overall average performance without discriminating against different traffic states. However, the fact is that predicting the traffic speed under congestion is normally more important than under free flow since the downstream tasks, such as traffic control and optimization, are more interested in congestion rather than free flow. Most of the State-Of-The-Art (SOTA) models unfortunately do not differentiate between the traffic states during training and evaluation. To this end, we first comprehensively study the performance of the SOTA models under different speed regimes to illustrate the low accuracy of low-speed prediction. We further propose and design a novel Congestion-Aware Sparse Attention transformer (CASAformer) to enhance the prediction performance under low-speed traffic conditions. Specifically, the CASA layer emphasizes the congestion data and reduces the impact of free-flow data. Moreover, we adopt a new congestion adaptive loss function for training to make the model learn more from the congestion data. Extensive experiments on real-world datasets show that our CASAformer outperforms the SOTA models for predicting speed under 40 mph in all prediction horizons.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100174"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can combined virtual-real testing speed up autonomous vehicle testing? Findings from AEB field experiments","authors":"Meng Zhang,&nbsp;Jiatong Xu,&nbsp;Ying Gao,&nbsp;Dandan Shen,&nbsp;Zhigang Xu","doi":"10.1016/j.commtr.2025.100216","DOIUrl":"10.1016/j.commtr.2025.100216","url":null,"abstract":"<div><div>Proving ground testing has become a standard methodology for the development and validation of autonomous vehicles in the automotive industry. However, it suffers from inherent limitations in efficiency, cost, and scenario coverage. Combined virtual-real testing (CVRT) offers a promising alternative by integrating virtual scenarios with physical vehicles and the environment, enhancing scenario coverage and test flexibility. Nevertheless, few studies have systematically investigated its effectiveness and applicability. To address this gap, this study develops a digital-twin-based CVRT system and conducts consistency verification experiments, taking the autonomous emergency braking (AEB) system test as a case study. Four typical scenarios selected from C-NCAP (China New Car Assessment Programme) 2024 were tested at speeds of 30, 40, and 50 ​km/h, utilizing both real-world and CVRT methods, with each experiment repeated 15 times. Vehicle dynamics data were collected, and the Fréchet distance metric was used to quantify similarity, whereas statistical hypothesis testing was used to assess differences in time-to-collision (TTC) trigger times. The results show that the average Fréchet distance ratio between the CVRT and real-world tests almost approaches 1.0, and the differences in the TTC trigger times were not statistically significant. However, the results of the simulation experiments differed significantly from those of the real-world tests (0.528 ​m/s in speed and 1.150 ​m/s² in acceleration higher than the CVRT). Additionally, the data communication delay between the CVRT platform and the physical autonomous vehicle under test remained well below tolerable thresholds. These results indicate high consistency between CVRT and real-world testing. Furthermore, CVRT achieved considerable improvements in testing efficiency, saving approximately 40%–70% compared with real-world testing.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100216"},"PeriodicalIF":14.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145319540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DFUN-KDF: Efficient and robust decentralized federated framework for UAV networks via knowledge distillation and filtering","authors":"Wenyuan Yang ,&nbsp;Yuhang Liu ,&nbsp;Xinlin Leng ,&nbsp;Hanlin Gu ,&nbsp;Gege Jiang ,&nbsp;Xiaochuan Yu ,&nbsp;Xiaochun Cao","doi":"10.1016/j.commtr.2025.100173","DOIUrl":"10.1016/j.commtr.2025.100173","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) are increasingly crucial across various fields. There is a growing interest in using federated learning (FL) methods to enhance the efficiency of UAV operations. Nevertheless, incumbent methods remain encumbered by significant drawbacks, including high energy consumption from extensive parameter exchanges, the imperative for homogeneous networks, and sensitivity to single-point failures. These difficulties are compounded by the unreliable nature of communication channels and the current inability to effectively manage the diversity of UAV models, highlighting the imperative for more resilient and adaptable FL solutions. To address these issues, we propose an efficient and robust decentralized FL framework for heterogeneous UAV networks. Our framework first leverages the knowledge distillation where UAVs transmit embeddings instead of model parameters to reduce the number of transmission parameter. UAVs update their local models using embeddings generated by other UAVs, which also enables UAVs with diverse architectures to participate in training. Moreover, our framework incorporates a filtering mechanism to remove malicious embeddings, ensuring resilience against adversities in UAV networks. Extensive experiments on various datasets validate the effectiveness and practical deployment potential of our framework.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100173"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CCDSReFormer: Traffic flow prediction with a criss-crossed dual-stream enhanced rectified transformer model","authors":"Zhiqi Shao ,&nbsp;Michael G.H. Bell ,&nbsp;Ze Wang ,&nbsp;D. Glenn Geers ,&nbsp;Xusheng Yao ,&nbsp;Junbin Gao","doi":"10.1016/j.commtr.2025.100189","DOIUrl":"10.1016/j.commtr.2025.100189","url":null,"abstract":"<div><div>Accurate, efficient, and rapid traffic forecasting is essential for intelligent transportation systems and plays a pivotal role in urban traffic planning, management, and control. While existing spatiotemporal transformer models have demonstrated effectiveness in traffic flow prediction, they face notable challenges in achieving a balance between computational efficiency and accuracy. Additionally, they often prioritize global trends over local time series information and treat spatial and temporal data separately, limiting their ability to capture complex spatiotemporal interactions. To overcome these limitations, we propose the criss-crossed dual-stream enhanced rectified transformer (CCDSReFormer). This model introduces a novel rectified linear self-attention (ReLSA) mechanism combined with enhanced convolution (EnCov) to reduce computational overhead and sharpen the local feature focus. Furthermore, our cross-learning strategy seamlessly integrates spatial and temporal data, improving the model's ability to capture intricate traffic dynamics. Extensive experiments on six real-world datasets show that CCDSReFormer outperforms existing models in both accuracy and efficiency. An ablation study further validates the contributions of each component, confirming the model's superior ability to forecast traffic flow accurately and efficiently.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100189"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Drone to recharge electric vehicles: Operations, benefits, and challenges","authors":"Dongdong He ,&nbsp;Ying Yang ,&nbsp;Andrea Morichetta ,&nbsp;Jianjun Wu","doi":"10.1016/j.commtr.2025.100162","DOIUrl":"10.1016/j.commtr.2025.100162","url":null,"abstract":"<div><div>Electric vehicles (EVs) are a promising solution to reduce greenhouse gas emissions and foster sustainable urban transportation. However, the widespread adoption of EVs is hindered by range anxiety and the fear of running outnqt of battery before reaching a charging station. To address this challenge, we propose a novel drone-to-vehicle (D2V) charging system, which leverages drones as mobile charging units to provide on-the-go recharging services for EVs. This study explores the operational and technical aspects of the D2V system, including drone charging docks, order-dispatching strategies, and dynamic drone reallocation mechanisms. A key contribution is to introduce a concept of the adaptive route meetup location selection (ARMLS), which optimizes drone dispatch and pricing models based on real-time parameters such as distance, battery levels, and traffic conditions. Our analysis highlights the potential of D2V systems to alleviate range anxiety, enhance road network efficiency through dynamic traffic redistribution, and reduce carbon emissions by integrating renewable energy sources. The study suggests that implementing D2V services can significantly improve the reliability of EVs in critical situations while fostering broader EV adoption. Future work will focus on reinforcement learning-based optimization algorithms to further improve drone operations and address scalability challenges. The proposed D2V system represents a crucial step toward a sustainable and efficient urban mobility future.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100162"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Survey of research on autonomous driving testing with large models","authors":"Songyan Liu ,&nbsp;Shijie Cong ,&nbsp;Lan Yang","doi":"10.1016/j.commtr.2025.100179","DOIUrl":"10.1016/j.commtr.2025.100179","url":null,"abstract":"","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100179"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting","authors":"Zezhi Shao ,&nbsp;Fei Wang ,&nbsp;Tao Sun ,&nbsp;Chengqing Yu ,&nbsp;Yuchen Fang ,&nbsp;Guangyin Jin ,&nbsp;Zhulin An ,&nbsp;Yang Liu ,&nbsp;Xiaobo Qu ,&nbsp;Yongjun Xu","doi":"10.1016/j.commtr.2025.100218","DOIUrl":"10.1016/j.commtr.2025.100218","url":null,"abstract":"<div><div>Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential component of intelligent transportation. Recent proposals on Spatial-Temporal Graph Neural Networks (STGNNs) have made significant progress by combining sequential models with graph convolution networks. However, due to high complexity issues, STGNNs only focus on short-term traffic forecasting (e.g., 1-h ahead), while ignoring more practical long-term forecasting. In this paper, we make the first attempt to explore long-term traffic forecasting (e.g., 1-day ahead). To this end, we first reveal its unique challenges in exploiting multi-scale representations. Then, we propose a novel Hierarchical U-net TransFormer (HUTFormer) to address the issues of long-term traffic forecasting. HUTFormer consists of a hierarchical encoder and decoder to jointly generate and utilize multi-scale representations of traffic data. Specifically, for the encoder, we propose window self-attention and segment merging to extract multi-scale representations from long-term traffic data. For the decoder, we design a cross-scale attention mechanism to effectively incorporate multi-scale representations. In addition, HUTFormer employs an efficient input embedding strategy to address the complexity issues. Extensive experiments on four traffic datasets show that the proposed HUTFormer significantly outperforms state-of-the-art traffic forecasting and long time series forecasting baselines.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100218"},"PeriodicalIF":14.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Traffic simulation optimization considering driving styles","authors":"Yunyang Shi ,&nbsp;Tong Wu ,&nbsp;Tan Guo ,&nbsp;Jinbiao Huo ,&nbsp;Ziyuan Gu ,&nbsp;Yifan Dai ,&nbsp;Zhiyuan Liu","doi":"10.1016/j.commtr.2025.100181","DOIUrl":"10.1016/j.commtr.2025.100181","url":null,"abstract":"<div><div>Parameter calibration is essential for ensuring the accuracy of microscopic traffic simulations. The expected speed is a critical parameter that characterizes behaviors of vehicles in most simulation models, which is influenced by road traffic conditions and the driving characteristics of different drivers. Most existing parameter calibration methods typically concentrate on micro-level parameters such as time headway and lane change motivation, while overlooking the calibration of vehicle expected speeds in consideration of driver behavior habits. This study combines data from highway electronic toll collection (ETC), gantries, and 100-m mileage average speed data, and proposes a method for calibrating vehicle expected speed that considers driving style clustering. The Gaussian mixture model (GMM) algorithm is used to develop driver models with three distinct driving styles: aggressive, moderate, and conservative. To ensure driving diversity and enhance parameter calibration efficiency, we rebuild vehicle driving models and representative parameters based on the classification results. Moreover, the Bayesian optimization algorithm is modified in conjunction with a microscopic traffic simulation model to perform automatic calibration of expected speeds. Experiments conducted on the Shanghai–Hangzhou–Ningbo highway demonstrate that the proposed method significantly reduces the mean absolute percentage error (MAPE) from 20.2% (using default parameters) to 3.1%. Additionally, in the model robustness test, the MAPE reaches 5.01%, indicating a certain level of stability and scalability. This method proposes a tailored calibration method accounting for the heterogeneous driving behaviors of micro-traffic simulation models, achieving satisfactory calibration results for simulation models in highway scenarios.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100181"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reassessing desired time headway as a measure of car-following capability: Definition, quantification, and associated factors","authors":"Shubham Parashar ,&nbsp;Zuduo Zheng ,&nbsp;Andry Rakotonirainy ,&nbsp;Md Mazharul Haque","doi":"10.1016/j.commtr.2025.100169","DOIUrl":"10.1016/j.commtr.2025.100169","url":null,"abstract":"<div><div>The desired time headway is often used to incorporate human behavior in car-following (CF) models by treating it as a measure of driver capability in car-following interactions, which is latent and cannot be directly observed. However, the desired time headway is often assumed to be a constant value for a driver across all speed levels. This assumption can be unrealistic and unreliable. Studies indicate that the mean time headway during steady-state car-following interactions quantifies the desired time headway, but inconsistent conditions for steady-state interactions in the literature make such assessments challenging. This study aims to reassess the desired time headway as a metric of driver capability in car-following interactions. Specifically, it identifies steady-state car-following conditions for reliable desired time headway estimates via the NGSIM I80 dataset. The results show that using a sustenance window of 3.5 ​s with an acceleration threshold of ±0.75 ​m/s² and a relative speed of ±1.52 ​m/s reduces transient and sporadic time headway observations, which in turn improves the reliability of the desired time headway. The obtained conditions are applied to the car-following trajectories in a driving simulator experiment, designed to focus on the steady-state at two speed levels (85 and 40 ​km/h) in traditional environment (TE) and connected environment (CE). The results indicate that the desired time headway is significantly longer in high-speed car-following (85 ​km/h) than in low-speed car-following (40 ​km/h) in the TE and CE and that driving aids help maintain more consistent desired time headways. A comparison of the TE and CE in low-speed car-following shows that most drivers prioritize safety by increasing the desired time headway in the CE. However, in high-speed car-following, the mean desired time headway is not significantly different between the TE and the CE on an aggregate level. Furthermore, the study presents a generalized linear mixed model (GLMM) describing the desired time headway selection in different conditions, identifying age, gender, and crash involvement as significant variables other than the driving conditions.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100169"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}