IEEE Transactions on Intelligent Transportation Systems最新文献

{"title":"Toward an Adaptive Cyber Resilience Paradigm of Rail Control Systems in the Digital Era","authors":"Zhicheng Huang;Xiaoya Hu;Weihong Ma;Hongxue Chen;Hao Zhang;Meng Ma;Ling Liu;Zonghua Zhang;Ping Wang","doi":"10.1109/TITS.2026.3669771","DOIUrl":"https://doi.org/10.1109/TITS.2026.3669771","url":null,"abstract":"Today, the railway industry is experiencing a profound digital transformation driven by advances in ICT technologies such as 5G, cloud computing, and artificial intelligence. In particular, the digitalization of rail control systems has significant potential to reduce system complexity and operating and maintenance costs while improving safety and efficiency. However, in addition to these significant benefits, security has emerged as a critical concern that could no longer be overlooked. Even a minor breach in any digitalized component can propagate through interconnected subsystems and eventually lead to severe safety incidents in the physical world. To holistically address both safety and security in digitalized rail control systems, we propose an adaptive cyber-resilience paradigm by analyzing the characteristics, risks, and requirements of the system. As safety has been extensively studied in the rail domain, this paper focuses primarily on cybersecurity and its interaction and integration with safety. By modeling the railway and its control system as a specialized form of Cyber-Physical System (CPS), we elucidate cybersecurity requirements and introduce a comprehensive risk-analysis methodology to identify the key challenges to achieve cyber resilience. We further define the cyber-resilience paradigm and conduct an in-depth examination of its four essential components: theoretic models, enabling techniques, standards, and practical implementations. Finally, we develop a MAPE-K–based approach and implement this paradigm in the Chinese Train Control System (CTCS), thus demonstrating its feasibility and practical applicability.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13621-13634"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097084","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 Behavior Based on Phase-Field Coupling Theory and Mathematized Expression of Panoramic Situation","authors":"Junyan Han;Xiaoyuan Wang;Jingheng Wang;Tinglin Chen;Kai Feng;Bin Wang","doi":"10.1109/TITS.2026.3726049","DOIUrl":"https://doi.org/10.1109/TITS.2026.3726049","url":null,"abstract":"Car-following behavior is the result of combined effects of various types of factors in real transportation systems. However, there is no car-following model that comprehensively incorporates the combined impacts of micro and macro factors, as well as the differences in car-following behavior among diverse drivers under the same impacts, i.e., driver heterogeneity. This paper presents a panoramic situation expression-based car-following model. First, the micro factors (including the types and positions of the vehicles in the current lane and adjacent lanes) and the macro factor (including the density of traffic flow ahead) that affect car-following behavior are modeled as the panoramic situation, and based on nonlinear mechanics and phase-field coupling theory, the mathematized expression of panoramic situation is established to achieve a unified expression of the combined impacts. Second, a car-following behavior decision-making method is proposed to incorporate driver heterogeneity based on cumulative prospect theory and the “decision-execution” mechanism of car-following behavior. Third, intelligent driving model is employed as the execution framework and integrated with the decision-making method to establish a car-following model. Real and virtual vehicle driving experiments are conducted to collect data and complete calibration. The fitting capability, numerical along with behavioral soundness, and scenario robustness of the proposed model are tested, evaluated, and verified through comprehensive utilization of the collected data, NGSIM dataset, and data of supplemental driving experiments in 15 cases within 10 representative scenarios. The capability of the proposed model to capture heterogeneous drivers’ car-following behavior, the cognitive rationality of its outputs for heterogeneous drivers, and the contribution of each module in the model to performance improvement were also tested.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12142-12157"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097193","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":"Fast Bi-Level Task Assignment and Routing for Truck-Drone Collaborative Delivery","authors":"Zonghan He;Jian Yang;Qi Zhao;Haobin Yang;Xinyu Chen;Xingyu Zhou;Yuhui Shi","doi":"10.1109/TITS.2026.3711461","DOIUrl":"https://doi.org/10.1109/TITS.2026.3711461","url":null,"abstract":"The emerging use of drones in last-mile delivery (e.g., for e-commerce and emergency services) creates a need to optimize collaborative operations among trucks, drones, and supporting facilities. In this paper, we focus on the Cumulative Vehicle Routing Problem with Drone Stations (CumVRP-DS), which jointly optimizes customer (task) assignment and vehicle routing in the context of drone-station-assisted last-mile delivery. The objective is to minimize the total customer waiting time. To solve this problem, we first formulate it as a Mixed Integer Linear Programming (MILP) model, which extends the multi-level network (MLN) formulation to incorporate drone-stations. Second, we propose an improved bi-level meta-heuristic algorithm, designed to reduce the search effort required at the inner routing layer. Computational experiments show that the proposed MILP formulation is able to produce theoretically-guaranteed optimal results for instances with up to 100 customers with Gurobi, and the improved bi-level meta-heuristic achieves significantly better solutions on large instances (over 100 customers) with an average 4.4% reduction in objective values. Furthermore, our analysis provides key operational insights: it demonstrates that (1) similar task assignments often lead to similar (near-)optimal truck routes, justifying the route-reconstruction strategy, and (2) inner-layer routing can be effectively handled by reconstruction alone, suggesting computational resources should be prioritized for the task-assignment sub-problem. These insights offer an effective solution framework and practical guidelines for similar drone-assisted delivery optimization problems.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12782-12790"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097252","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":"Lane-Aware Two-Stage Radar Multi-Object Tracking for Lane-Level Traffic Monitoring at Complex Intersections","authors":"Jaehwan Lee;Soyeong Kim;Hae-Seung Lim;Yoontae Hwang;Kichun Jo","doi":"10.1109/TITS.2026.3704852","DOIUrl":"https://doi.org/10.1109/TITS.2026.3704852","url":null,"abstract":"Reliable lane-level traffic monitoring at complex intersections is challenging with infrastructure radar alone: radar point clouds are sparse, cluttered, and provide only coarse angular resolution. We propose a <italic>lane-aware two-stage multi-object tracker</i> that mitigates these limitations by combining generic tracking with lane geometry. First, a dual-clustering detector groups radar points into moving object hypotheses (using Doppler similarity) and supplements them with clusters centered on previously confirmed tracks, recovering temporarily stationary vehicles. Tracking then proceeds in two stages. To provide a stable starting point for lane-level analysis, the first stage runs an IMM-EKF in the global Cartesian frame. Building on these coarse estimates, the second stage distributes tracks among corresponding lane-specific trackers through probabilistic assignment, considering distance to the centerline, track covariance, and velocity heading. The track is converted into the Frenet frame and re-filtered, constraining the motion to the road axis and sharply reducing the lateral uncertainty. Because an independent tracker runs in every lane-specific Frenet frame, the system outputs not only refined track results but also real-time per-lane traffic counts. In CARLA simulations, our method significantly reduced velocity heading and lateral state RMSE compared to a standard Cartesian tracking baseline, while eliminating false track counts per lane. Real-world tests with a 24 GHz radar and RTK GNSS/INS ground truth show consistent improvements, substantially lowering both heading and lateral errors relative to the conventional Cartesian tracker. These validation results confirm that the proposed lane-aware two-stage tracker delivers reliable, lane-level traffic metrics even with noisy radar data. Comparisons with recent Frenet-frame trackers confirm our two-stage design achieves the most consistent accuracy at complex intersections where single-stage methods degrade.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12751-12767"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097296","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":"AnisoNet: A Detecting Model for Initial Anisotropic Cracks in Complex Road Scenarios","authors":"Jiuyuan Huo;Zeyu Wu;Chuile Kong","doi":"10.1109/TITS.2026.3713802","DOIUrl":"https://doi.org/10.1109/TITS.2026.3713802","url":null,"abstract":"As a critical component of Intelligent Transportation Systems (ITS), automated pavement health monitoring plays a vital role in ensuring traffic safety and enabling predictive maintenance. At present, the accurate and efficient detection of incipient pavement cracks remains a key technical challenge in this field. However, challenges such as low resolution of captured road images and the small proportion of initial cracks result in current mainstream crack detection models exhibiting low recognition accuracy and a high likelihood of missed detections. To address these issues, this paper proposes a detection model called AnisoNet, specifically designed for early-stage cracks with anisotropic characteristics, aiming to enhance both the efficiency and accuracy of early crack detection. AnisoNet incorporates several innovative components: a three-level routing attention (TRA) mechanism, which dynamically adjusts the attention granularity to enhance the sensitivity of the model to small features; a multi-head routing dynamic convolution module (MRDC) to improve the ability to adapt to complex global features and curvilinear local features; a snake-aware receptive field convolution (SARFConv) designed to strengthen the model’s ability to detect subtle spatial variations and misalignments; and a multi-scale large kernel attention mechanism (LKMSA) that enhances the model’s capacity to capture detailed features of low-contrast cracks. To validate the effectiveness and superiority of the AnisoNet, multiple experiments were conducted on several public datasets. The results show that the proposed method outperforms existing state-of-the-art models in crack detection accuracy, achieving improvements of 6.1% in mAP@50 and 6.8% in mAP@95 compared to baseline models, while AnisoNet exhibits excellent generalization capabilities across various complex scenarios, including different acquisition viewpoints, challenging illumination conditions, and background interferences. Furthermore, to validate the method’s engineering feasibility within real-world ITS scenarios, a real-time detection system was implemented on a UAV-based edge computing platform. Field tests confirm that AnisoNet achieves an inference speed of approximately 26 FPS on embedded devices, successfully substantiating its applicability for low-latency pavement health monitoring tasks.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12247-12264"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097320","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":"Smoothing Traffic Flow Through Automated Vehicle Control With Optimal Parameter Selection","authors":"Shian Wang;Jose Carlos Acedo Aguilar;Miguel Velez-Reyes","doi":"10.1109/TITS.2026.3725896","DOIUrl":"https://doi.org/10.1109/TITS.2026.3725896","url":null,"abstract":"Stop-and-go traffic waves reduce transportation system efficiency by increasing traffic oscillations and energy consumption. This study develops an approach to synthesize a class of additive feedback controllers for automated vehicles (AVs) to smooth nonlinear mixed traffic flow, which includes both AVs and human-driven vehicles (HVs). Unlike recent AV controllers that rely on strict assumptions, such as vehicle-to-vehicle communication or equilibrium traffic speed, our proposed controller utilizes only local traffic information, including inter-vehicle spacing and relative speed, which is readily available through onboard AV sensors. By tracking a smoothed version of the perturbed speed profile of its preceding vehicle, the controlled AV facilitates smoother traffic flow. Additionally, we present a method for selecting optimal control parameter values to enhance traffic-smoothing efficiency. These features significantly improve the implementability of the proposed AV controller. We evaluate its effectiveness through simulations of three distinct traffic scenarios with varying levels of oscillation. The results show that AVs using the proposed controller can effectively reduce traffic oscillations and decrease fuel consumption by up to 46.96% and 2.74%, respectively, across the traffic scenarios considered. The traffic-smoothing effect is more pronounced at higher AV penetration rates. While the proposed approach exhibits slightly lower performance than the most recent additive AV controller, which relies on stricter assumptions, it offers greater implementability and provides a systematic method for selecting optimal control parameters.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12013-12026"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097327","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":"Critical Configuration Testing for Autonomous Driving Systems---Targeting the Achilles' Heel of Four Open Autopilots","authors":"Changwen Li;Joseph Sifakis;Rongjie Yan;Jian Zhang","doi":"10.1109/TITS.2026.3713467","DOIUrl":"https://doi.org/10.1109/TITS.2026.3713467","url":null,"abstract":"The question of how to validate autonomous driving systems (ADS) has been the subject of much study and debate. The complexity and heterogeneity of ADS make testing, preferably by simulation, the main validation method. One of the difficulties of ADS testing lies in the fact that autopilot failures are rare events, and their exposure must be achieved by applying critical test cases that generate high-risk scenarios, whereas solely increasing criticality may lead to unavoidable failures that cannot reveal genuine defects. We propose the Critical Configuration Testing (CCTest) approach, which evaluates an ego vehicle driven by its autopilot under configurations involving conflicts between vehicles. High-risk scenarios are generated by applying test cases that specify the most critical initial kinematic attributes of the vehicles and worst-case movements of non-ego vehicles. This approach differs from existing methods in two key respects. First, it generates test cases that ensure the tested autopilot has a provably safe policy, so that any observed failure reflects a genuine defect in the autopilot. Second, it targets short scenarios involving interactions between at most three relevant vehicles, enabling precise identification of the most critical test cases. We present the mathematical framework for calculating critical parameter values for the test cases, as well as its application to four open autopilots: Apollo, Autoware, and the built-in autopilots in the Carla and LGSVL simulators. Our experiment reveals numerous failures in critical configurations, including accidents, traffic rule violations, blockages, and software failures, that would be difficult for existing methods to fully capture.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13125-13140"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097466","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":"Deep Learning-Driven Mobility and Handover Prediction for ICN-Enabled Vehicular Networks","authors":"Kamrul Hasan;Seong Ho Jeong","doi":"10.1109/TITS.2026.3699551","DOIUrl":"https://doi.org/10.1109/TITS.2026.3699551","url":null,"abstract":"Seamless content delivery in ICN-based vehicular networks remains a critical challenge due to rapid mobility, frequent handovers, and varying vehicle densities. While mobility and handover prediction are often treated similarly, they serve distinct roles: mobility prediction estimates future vehicle position, whereas handover prediction determines transitions between wireless access points (WAPs) such as roadside units (RSUs), access points (APs), and base stations (BSs). This paper proposes a unified framework that explicitly separates these tasks, where an LSTM-based Mobility Prediction Algorithm (LMPA) captures temporal mobility patterns, and multiple handover prediction methods, including Markov-based (MHPA), LSTM-based (LHPA), an Advanced Handover Prediction Algorithm (AHPA), and a Handover Decision Prediction (HDP) mechanism based on angular movement are introduced. In addition, a novel grid-based LSTM model integrates spatial and temporal information using GPS and WAP sequences. Experimental results using a large-scale real-world dataset collected over six months from two major South Korean telecom operators show that the proposed grid-based model achieves an overall prediction accuracy of 65.82% and up to 86.27% within an 11 km coverage area, outperforming the regular model (55.79%), while reducing unnecessary handovers by 43.65% and 29.22% for SKT and LGU+ datasets, respectively. Compared with baseline models, including Markov models (51.19% and 57.11%) and deep learning models such as CNN, GRU, CLDNN, and standard LSTM, the proposed framework demonstrates superior performance, enabling proactive caching and efficient content delivery in high-mobility vehicular networks.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12573-12591"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097600","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":"TeLL-Drive: Enhancing Autonomous Driving With Teacher LLM-Guided Deep Reinforcement Learning","authors":"Chengkai Xu;Jiaqi Liu;Shiyu Fang;Yiming Cui;Dong Chen;Peng Hang;Jian Sun","doi":"10.1109/TITS.2026.3705604","DOIUrl":"https://doi.org/10.1109/TITS.2026.3705604","url":null,"abstract":"Although Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) each show promise in addressing decision-making challenges in autonomous driving, DRL often suffers from high sample complexity, while LLMs have difficulty ensuring real-time decision making. To address these limitations, we propose TeLL-Drive, a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy. By incorporating risk metrics, historical scenario retrieval, and domain heuristics into context-rich prompts, the LLM produces high-level driving strategies through chain-of-thought reasoning. A self-attention mechanism then fuses these strategies with the DRL agent’s exploration, accelerating policy convergence and boosting robustness across diverse driving conditions. The experimental results, evaluated across multiple traffic scenarios, show that TeLL-Drive outperforms existing baseline methods, including other LLM-based approaches, in terms of success rates, average returns, and real-time feasibility. Ablation studies underscore the importance of each model component, especially the synergy between the attention mechanism and LLM-driven guidance. Finally, we build a virtual-real fusion experimental platform to verify the real-time performance, robustness, and reliability of the algorithm running on real vehicles through vehicle-in-loop experiments. Full validation results are available on Our Website.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12486-12498"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097744","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 Traffic Accident Detection From Speed Data: A Visual Method Based on Multi-Perspective Spatiotemporal Tensors","authors":"Zhengchao Zhang;Yandong Li;Ying Xiao;Meng Li","doi":"10.1109/TITS.2026.3702863","DOIUrl":"https://doi.org/10.1109/TITS.2026.3702863","url":null,"abstract":"Timely detection of traffic accidents is crucial for improving the road safety and traffic efficiency. However, existing methods typically suffer from the reliance of video cameras, coarse granularity, inadequate real-time responsiveness and low accuracy. To address these challenges, this study proposes a novel two-stage spatiotemporal accident detection (TSTAD) approach. By integrating the real-time speed data, historical speed data, similar patterns and speed entropy into a multi-perspective spatiotemporal tensor, the congestion waves caused by accidents are underlined. Subsequently, a two-stage detection framework is designed, which takes the spatiotemporal tensor and auxiliary features (e.g., weather) as inputs. Stage-I classifies that whether accidents happen or not. Stage-II exploits deep visual techniques to detect the occurrence times and locations of accidents. Furthermore, a dynamic sample caching strategy is introduced to speed up the training procedure. Validated on two real-world datasets, TSTAD outperforms baselines by a 3%–10% detection accuracy and over 50% computational efficiency.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13170-13180"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097740","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}