IEEE Open Journal of Intelligent Transportation Systems最新文献

{"title":"Adopting Graph Neural Networks to Understand and Reason About Dynamic Driving Scenarios","authors":"Peng Su;Conglei Xiang;Dejiu Chen","doi":"10.1109/OJITS.2025.3563428","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3563428","url":null,"abstract":"With advances in Deep Neural Networks (DNN), Automated Driving Systems (ADS) enable the vehicle to perceive their surroundings in dynamic driving scenarios and perform behaviors by collecting operational data from sensors such as LiDAR and cameras. Current DNN typically detect objects by analyzing and classifying unstructured data (e.g., image data), providing critical information for ADS planning and decision-making. However, advanced ADS, particularly those required to perform the Dynamic Driving Task (DDT) autonomously, are expected to understand driving scenarios across various Operational Design Domains (ODD). This capability requires the support for a continuous comprehension of driving scenarios according to operational data collected by sensors. This paper presents a framework that adopts Graph Neural Networks (GNN) to describe and reason about dynamic driving scenarios via analyzing graph-based data based on collected sensor inputs. We first construct the graph-based data using a meta-path, which defines various interactions among different traffic participants. Next, we propose a design of GNN to support both the classification of the node types of objects and predicting relationships between objects. As results, the performance of the proposed method shows significant improvements compared to the baseline method. Specifically, the accuracy of node classification increases from 0.77 to 0.85, while that of relationships prediction rises from 0.74 to 0.82. To further utilize graph-based data constructed from dynamic driving scenarios, the proposed framework supports reasoning about operational risks by analyzing the observed nodes and relationships in the graph-based data. As a result, the model achieves a MRR of 0.78 in operational risks reasoning. To evaluate the practicality of the proposed framework in real-world systems, we also conduct a real-time performance evaluation by measuring the average process time and the Worst Case Execution Time (WCET). Compared to the baseline models, the results demonstrate the proposed framework presents acceptable real-time performance in analyzing graph-based data.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"579-589"},"PeriodicalIF":4.6,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973289","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949180","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":"OppIN: Optimal Path Intervention for Emergency Response Leveraging IoT and Big Data Technologies","authors":"Yassine Gacha;Takoua Abdellatif","doi":"10.1109/OJITS.2025.3563310","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3563310","url":null,"abstract":"In this paper, we introduce the Optimal Path Intervention System (OppIN), a solution designed to support multiple emergency services, including fire response, civil protection, and emergency medical assistance, to reach crisis locations as quickly as possible by harnessing Big Data technologies and IoT infrastructure. OppIN computes quasi-real-time optimal intervention paths using a multi-criteria approach, incorporating both static factors (such as road network geometry, road conditions, and service locations) and dynamic data (including crisis locations captured by IoT sensors and real-time traffic conditions monitored through surveillance cameras). Using the IoT infrastructure and local data for quasi-real-time updates, OppIN adapts effectively to dynamic changes in context, ensuring the use of up-to-date information alongside Big Data technologies and AI for real-time processing. Compared to existing solutions such as Google Maps, our system uses a broader set of data sources and criteria, such as weather conditions, distance, traffic dynamics, and road status, to provide a more comprehensive and tailored analysis for specialized service navigation. Additionally, OppIN offers superior scalability and performance, using a Big Data-driven system design to handle high data volumes and real-time processing demands effectively. Furthermore, our system uses AI programs to estimate different criteria and to aggregate these criteria for quasi-real-time paths calculation.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"484-502"},"PeriodicalIF":4.6,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973160","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900565","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":"Multi-Hop Upstream Anticipatory Traffic Signal Control With Deep Reinforcement Learning","authors":"Xiaocan Li;Xiaoyu Wang;Ilia Smirnov;Scott Sanner;Baher Abdulhai","doi":"10.1109/OJITS.2025.3562757","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3562757","url":null,"abstract":"Coordination in traffic signal control is crucial for managing congestion in urban networks. Existing pressure-based control methods focus only on immediate upstream links, leading to suboptimal green time allocation and increased network delays. However, effective signal control inherently requires coordination across a broader spatial scope, as the effect of upstream traffic should influence signal control decisions at downstream intersections, impacting a large area in the traffic network. Although agent communication using neural network-based feature extraction can implicitly enhance spatial awareness, it significantly increases the learning complexity, adding an additional layer of difficulty to the challenging task of control in deep reinforcement learning. To address the issue of learning complexity and myopic traffic pressure definition, our work introduces a novel concept based on Markov chain theory, namely multi-hop upstream pressure, which generalizes the conventional pressure to account for traffic conditions beyond the immediate upstream links. This farsighted and compact metric informs the deep reinforcement learning agent to preemptively clear the multi-hop upstream queues, guiding the agent to optimize signal timings with a broader spatial awareness. Simulations on synthetic and realistic (Toronto) scenarios demonstrate controllers utilizing multi-hop upstream pressure significantly reduce overall network delay by prioritizing traffic movements based on a broader understanding of upstream congestion.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"554-567"},"PeriodicalIF":4.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10970747","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143908362","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":"Digital Twin Technologies for Vehicular Prototyping: A Survey","authors":"Md Rafiul Kabir;Bhagawat Baanav Yedla Ravi;Sandip Ray","doi":"10.1109/OJITS.2025.3562504","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3562504","url":null,"abstract":"Digital Twin (DT) technology is widely regarded as one of the most promising tools for industry development, demonstrating substantial application across numerous cyber-physical systems. Gradually, this technology has been introduced into modern vehicular systems focusing on its application in intelligent driving, connected vehicles, automotive engineering, aircraft health, and many more. By creating dynamic, virtual replicas of physical vehicles and their associated components, DT enables unprecedented levels of analysis, simulation, and real-time monitoring, thereby enhancing performance, safety, and sustainability. This paper offers a comprehensive review, extending beyond digital twins to include various prototyping approaches for target-specific applications focusing on the smart vehicular systems across automotive, aviation, and maritime domains driving the evolution of next-generation vehicular infrastructure.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"503-521"},"PeriodicalIF":4.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10969983","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900566","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":"Joint Optimization of Transportation-Energy Systems Through Electric Vehicle Charging Pricing in the Morning Commute","authors":"Kevin Freymiller;Junjie Qin;Sean Qian","doi":"10.1109/OJITS.2025.3557038","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3557038","url":null,"abstract":"We investigate how electric vehicles (EV) market share and EV charging pricing would impact the joint transportation and grid system during the morning commute. Using a simplified network consisting of a single corridor, we analytically derive time-varying flow patterns for both EV and internal combustion engine vehicle (ICV) groups, as a result of travelers’ departure time choices upon travel time, schedule delay and EV charging fee at an arbitrary morning time. For cities with a small or moderate portion of electricity generated from solar, one primary cost for the grid system during the morning commute is power generation ramping in addition to energy cost. By imposing a single charging price change during the morning commute period, we solve for the optimal charging price change time and magnitude to minimize joint system cost. We show that a price increase during morning commute is always preferred. There is a trade-off between transportation and grid costs with respect to when/how grid and transportation infrastructure are utilized by vehicles, particularly electric vehicles. Increasing EV peak charge would increase the grid ramping cost, as more EVs would depart home earlier. However, the same EV peak charge would reduce the transportation cost when the charge is mild or EV penetration is relatively low. When the energy generation ramping is considerable, there always exists an optimal EV peak charge balancing transportation cost and grid cost. We mathematically show the benefits of replacing ICVs with EVs in reducing transportation cost on top of emission/energy reductions, which can be achieved by imposing optimal EV charging prices alone. In addition, we would impose a higher peak charging price during winter for high latitude areas, or areas on the western end of a time zone, as such a price would reduce transportation cost without burdening the grid.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"465-483"},"PeriodicalIF":4.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947487","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845547","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":"Information-Driven Model Predictive Control With Adaptive Partitioning for Energy Optimization in Automated Electric Vehicles","authors":"Shahriar Shahram;Yaser P. Fallah","doi":"10.1109/OJITS.2025.3575031","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3575031","url":null,"abstract":"This paper presents a methodology to optimize energy consumption in electric vehicles (EVs) using a Model Predictive Control (MPC) framework integrated with detailed power loss models. Minimizing energy usage during drive cycles is a complex problem due to the nonlinear and non-convex characteristics of energy consumption models. We derive a power loss model quantifying mechanical and electrical losses, dependent on vehicle speed and acceleration. To handle the non-convex power loss function, we apply adaptive partitioning to fit convex quadratic models within smaller operational regions. These convex models are integrated into the MPC to compute optimal control inputs that minimize energy consumption while satisfying vehicle dynamics and constraints. We model packet loss and sensor noise to enhance robustness against communication losses and data uncertainties, simulating real-world scenarios. Our strategy reduces battery energy demand by selecting energy-efficient trajectories, balancing energy savings with ride comfort by minimizing abrupt speed and acceleration changes. This methodology is suitable for integration with Advanced Driver-Assistance Systems (ADAS), contributing to improved vehicle performance, safety, and sustainability. Simulations using National Renewable Energy Laboratory (NREL) datasets demonstrate significant energy savings across diverse driving scenarios. Our method achieves up to 34.28% energy savings, outperforming the policy-based energy optimization algorithm integrated with Adaptive Cruise Control (ACC). Results confirm that our algorithm effectively maintains desired speed following and distance coverage under varying packet error rates (PERs), ensuring safe and efficient operation while achieving a balanced trade-off between significant energy savings and acceptable passenger comfort.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"708-721"},"PeriodicalIF":4.6,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11017725","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272654","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":"Aircraft Trajectory Segmentation-Based Contrastive Coding: A Framework for Self-Supervised Trajectory Representation","authors":"Thaweerath Phisannupawong;Joshua J. Damanik;Han-Lim Choi","doi":"10.1109/OJITS.2025.3574746","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3574746","url":null,"abstract":"Air traffic trajectory recognition has gained significant interest within the air traffic management community, particularly for fundamental tasks such as classification and clustering. This paper introduces Aircraft Trajectory Segmentation-based Contrastive Coding (ATSCC), a self-supervised time series representation learning framework designed to capture semantic information in air traffic trajectory data, resulting in a data representation that best explains the trajectory instances. The framework leverages the segmentable characteristic of trajectories and ensures consistency within the self-assigned segments. Intensive experiments were conducted on datasets from three different airports, totaling four datasets, to compare the performance of the learned representation in downstream classification and clustering with that of other state-of-the-art representation learning techniques. The results show that ATSCC outperforms the baseline methods by aligning the representation with maneuvering procedures. Moreover, ATSCC is adaptable to various airport configurations and applicable to incomplete trajectories. This research has expanded upon existing capabilities, achieving these improvements independently without predefined inputs such as airport configurations, maneuvering procedures, or labeled data. The trajectory datasets used in this paper are available at huggingface.co/datasets/petchthwr/ATFMTraj. The implementation code is publicly available at github.com/petchthwr/ATSCC.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"738-757"},"PeriodicalIF":4.6,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11017720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299328","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":"Evaluation of Remote Driver Performance in Urban Environment Operational Design Domains","authors":"Ole Hans;Benedikt Walter;Jürgen Adamy","doi":"10.1109/OJITS.2025.3574692","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3574692","url":null,"abstract":"Remote driving has emerged as a solution for enabling human intervention in scenarios where Automated Driving Systems (ADS) face challenges, particularly in urban Operational Design Domains (ODDs). This study evaluates the performance of Remote Drivers (RDs) of passenger cars in a representative urban ODD in Las Vegas, focusing on the influence of cumulative driving experience and targeted training approaches. Using performance metrics such as efficiency, braking, acceleration, and steering, the study shows that driving experience can lead to noticeable improvements of RDs and demonstrates how experience up to 600 km correlates with improved vehicle control. In addition, driving efficiency exhibited a positive trend with increasing kilometers, particularly during the first 300 km of experience, which reaches a plateau from 400 km within a range of 0.35 to 0.42 km/min in the defined ODD. The research further compares ODD-specific training methods, where the detailed ODD training approaches attains notable advantages over other training approaches. The findings underscore the importance of tailored ODD training in enhancing RD performance, safety, and scalability for Remote Driving System (RDS) in real-world applications, while identifying opportunities for optimizing training protocols to address both routine and extreme scenarios. The study provides a robust foundation for advancing RDS deployment within urban environments, contributing to the development of scalable and safety-critical remote operation standards.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"722-737"},"PeriodicalIF":4.6,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11017673","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281283","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":"Multimodal Learning for Traffic Risk Prediction: Combining Aerial Imagery With Contextual Data","authors":"Hanlin Tian;Yuxiang Feng;Mohammed Quddus;Yiannis Demiris;Panagiotis Angeloudis","doi":"10.1109/OJITS.2025.3574866","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3574866","url":null,"abstract":"Accurately predicting traffic risks at urban intersections is essential for improving road safety. While traditional models use data sources like road traffic conditions, geometry, and signals, they often miss the spatial interactions between road networks and buildings. This study introduces a multimodal deep learning framework that integrates aerial imagery, building footprint data, and traffic flow information to improve traffic risk prediction and better capture these complex relationships. By leveraging datasets from OpenStreetMap, the U.K. Traffic Count, and high-resolution aerial imagery, our approach creates a comprehensive representation of the urban environment, capturing intricate spatial relationships between road networks, surrounding structures, and traffic conditions. Using DeepLabV3+, UNet++, and SegFormer as baseline models, we demonstrate that combining building and traffic data enhances prediction accuracy compared to models relying solely on visual data. Our results show that the DeepLabV3+ model, when incorporating both building and traffic data, achieves the highest Intersection over Union (IoU) score of 0.4052 and the lowest Root Mean Square Error (RMSE) of 0.0907. These findings underscore the effectiveness of a multimodal approach in traffic risk assessment, offering a more precise tool for urban planning and traffic management interventions. The code and data used in this study are available at <uri>https://github.com/zachtian/Multimodal-Learning-for-Traffic-Risk-Prediction</uri>.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"758-767"},"PeriodicalIF":4.6,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11017746","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144367053","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":"Online LiDAR-Camera Extrinsic Calibration Using Selected Semantic Features","authors":"Ping-Tzu Lin;Ying-Shiuan Huang;Wen-Chieh Lin;Chieh-Chih Wang;Huei-Yung Lin","doi":"10.1109/OJITS.2025.3555574","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3555574","url":null,"abstract":"Autonomous vehicles have gained great attention from all walks of life in recent years. The relative position and orientation between sensors often change gradually over time due to vibrations or thermal stress of materials. Thus, online re-calibrating extrinsic parameters periodically is required. In this situation, automatic targetless methods are more preferable as they do not require a calibration target or tedious calibration procedure. In this paper, we propose an online targetless camera-LiDAR extrinsic calibration approach with the help of semantic information. Our method could effectively ameliorate the problem of targetless methods which usually lack robust features and the correspondences. We also propose a feature selection technique to filter out improper feature correspondences by matching the image contours and point cloud projection contours. The experiment results show that our approach is more robust than previous work, and the calibration algorithm is applicable to more scenarios.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"6 ","pages":"456-464"},"PeriodicalIF":4.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10944781","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830516","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}