Pub Date : 2026-01-15DOI: 10.1109/OJITS.2026.3654451
Yihong Tang;Wei Ma
Accurate trajectory prediction of road agents (e.g., pedestrians, vehicles) is an essential prerequisite for various intelligent systems applications, such as autonomous driving and robotic navigation. Recent research highlights the importance of environmental contexts (e.g., maps) and the “multi-modality” of trajectories, leading to increasingly complex model structures. However, real-world deployments require lightweight models that can quickly migrate and adapt to new environments. Additionally, the core motivations of road agents, referred to as their intentions, deserves further exploration. In this study, we advocate that understanding and reasoning road agents’ intention plays a key role in trajectory prediction tasks, and the main challenge is that the concept of intention is fuzzy and abstract. To this end, we present Intent, an efficient intention-guided trajectory prediction model that relies solely on information contained in the road agent’s trajectory. Our model distinguishes itself from existing models in several key aspects: (i) We explicitly model road agents’ intentions through contrastive clustering, accommodating the fuzziness and abstraction of human intention in their trajectories. (ii) The proposed Intent is based solely on multi-layer perceptrons (Mlps), resulting in reduced training and inference time, making it very efficient and more suitable for real-world deployment. (iii) By leveraging estimated intentions and an innovative algorithm for transforming trajectory observations, we obtain more robust trajectory representations that lead to superior prediction accuracy. Extensive experiments on real-world trajectory datasets for pedestrians and autonomous vehicles demonstrate the effectiveness and efficiency of Intent.
{"title":"INTENT: Trajectory Prediction Framework With Intention-Guided Contrastive Clustering","authors":"Yihong Tang;Wei Ma","doi":"10.1109/OJITS.2026.3654451","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3654451","url":null,"abstract":"Accurate trajectory prediction of road agents (e.g., pedestrians, vehicles) is an essential prerequisite for various intelligent systems applications, such as autonomous driving and robotic navigation. Recent research highlights the importance of environmental contexts (e.g., maps) and the “multi-modality” of trajectories, leading to increasingly complex model structures. However, real-world deployments require lightweight models that can quickly migrate and adapt to new environments. Additionally, the core motivations of road agents, referred to as their intentions, deserves further exploration. In this study, we advocate that understanding and reasoning road agents’ intention plays a key role in trajectory prediction tasks, and the main challenge is that the concept of intention is fuzzy and abstract. To this end, we present <sc>Intent</small>, an efficient intention-guided trajectory prediction model that relies solely on information contained in the road agent’s trajectory. Our model distinguishes itself from existing models in several key aspects: (i) We explicitly model road agents’ intentions through contrastive clustering, accommodating the fuzziness and abstraction of human intention in their trajectories. (ii) The proposed <sc>Intent</small> is based solely on multi-layer perceptrons (<sc>Mlp</small>s), resulting in reduced training and inference time, making it very efficient and more suitable for real-world deployment. (iii) By leveraging estimated intentions and an innovative algorithm for transforming trajectory observations, we obtain more robust trajectory representations that lead to superior prediction accuracy. Extensive experiments on real-world trajectory datasets for pedestrians and autonomous vehicles demonstrate the effectiveness and efficiency of <sc>Intent</small>.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"337-352"},"PeriodicalIF":5.3,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11352503","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082017","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}
Pub Date : 2026-01-14DOI: 10.1109/OJITS.2026.3654547
Xingshuai Huang;Di Wu;Benoit Boulet
Efficient traffic signal control is of critical importance for minimizing traffic congestion and enhancing transportation efficiency. Researchers have turned to Reinforcement Learning (RL) for traffic signal control (TSC) due to the dynamic nature of traffic flow. Despite its potential, the real-world application of RL-based controllers is constrained by low sample efficiency and high computational demands. To address these challenges, we propose DTLight, a simple yet powerful lightweight Decision Transformer (DT)-based offline-to-online TSC method that can learn policy from pre-collected offline datasets while maintaining the capability to refine policy with minimal online interactions. Specifically, we propose three novel adaptive knowledge distillation methods to learn a lightweight offline controller from a well-trained larger teacher model to reduce implementation computation. Additionally, we integrate adapter modules to mitigate the expenses associated with fine-tuning, which makes DTLight practical for online enhancement with minimal computation and only a few fine-tuning steps during real deployment. Extensive experiments have been implemented on different traffic scenarios. The results show that DTLight pre-trained purely on offline datasets can outperform state-of-the-art methods in most scenarios. Additionally, online fine-tuning further improves the performance by up to 40.7% over the best online RL baseline methods. Moreover, we introduce $D$ atasets specifically designed for $T$ SC with offline RL (referred to as DTRL). Our datasets and code are publicly available: https://github.com/xingshuaihuang/dtlight.
{"title":"Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach","authors":"Xingshuai Huang;Di Wu;Benoit Boulet","doi":"10.1109/OJITS.2026.3654547","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3654547","url":null,"abstract":"Efficient traffic signal control is of critical importance for minimizing traffic congestion and enhancing transportation efficiency. Researchers have turned to Reinforcement Learning (RL) for traffic signal control (TSC) due to the dynamic nature of traffic flow. Despite its potential, the real-world application of RL-based controllers is constrained by low sample efficiency and high computational demands. To address these challenges, we propose DTLight, a simple yet powerful lightweight Decision Transformer (DT)-based offline-to-online TSC method that can learn policy from pre-collected offline datasets while maintaining the capability to refine policy with minimal online interactions. Specifically, we propose three novel adaptive knowledge distillation methods to learn a lightweight offline controller from a well-trained larger teacher model to reduce implementation computation. Additionally, we integrate adapter modules to mitigate the expenses associated with fine-tuning, which makes DTLight practical for online enhancement with minimal computation and only a few fine-tuning steps during real deployment. Extensive experiments have been implemented on different traffic scenarios. The results show that DTLight pre-trained purely on offline datasets can outperform state-of-the-art methods in most scenarios. Additionally, online fine-tuning further improves the performance by up to 40.7% over the best online RL baseline methods. Moreover, we introduce <inline-formula> <tex-math>$D$ </tex-math></inline-formula>atasets specifically designed for <inline-formula> <tex-math>$T$ </tex-math></inline-formula>SC with offline RL (referred to as DTRL). Our datasets and code are publicly available: <uri>https://github.com/xingshuaihuang/dtlight</uri>.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"396-411"},"PeriodicalIF":5.3,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11352509","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082016","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}
Pub Date : 2026-01-12DOI: 10.1109/OJITS.2026.3652748
R. Frolow;L. Zhang;V. Schwieger
This contribution is embedded into the challenge of track fault localization with low-cost hardware. For precise localization on the track, with an accuracy of a few decimeters for separating overlapping errors, a high resolution trajectory is needed and therefore sensor fusion is used. The commonly used combination of sensors consists of Global Navigation Satellite Systems and Inertial Measurement Units. The steps of the Kalman filter for sensor fusion are covered and afterwards the Unscented transform is described. This transform is applied to the prediction step of the Kalman filter. The implemented filters are extended by an adaptive stochastic model that applies to the observations used in the update steps. The Error-state Kalman filter and the Unscented Kalman filter are compared with and without the adaptive stochastic model with respect to their resulting root-mean-square (RMS) values. It is observed that the applied adaptive stochastic model improves performance for both filters by a small margin of 2 to 3 cm down to an RMS of 0.26 m. Meanwhile the roll angle estimation achieves deviations down to 0.1°. Both implemented filters achieve comparable results.
{"title":"Precise Train Positioning With Unscented Kalman Filter and Low-Cost Sensors","authors":"R. Frolow;L. Zhang;V. Schwieger","doi":"10.1109/OJITS.2026.3652748","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3652748","url":null,"abstract":"This contribution is embedded into the challenge of track fault localization with low-cost hardware. For precise localization on the track, with an accuracy of a few decimeters for separating overlapping errors, a high resolution trajectory is needed and therefore sensor fusion is used. The commonly used combination of sensors consists of Global Navigation Satellite Systems and Inertial Measurement Units. The steps of the Kalman filter for sensor fusion are covered and afterwards the Unscented transform is described. This transform is applied to the prediction step of the Kalman filter. The implemented filters are extended by an adaptive stochastic model that applies to the observations used in the update steps. The Error-state Kalman filter and the Unscented Kalman filter are compared with and without the adaptive stochastic model with respect to their resulting root-mean-square (RMS) values. It is observed that the applied adaptive stochastic model improves performance for both filters by a small margin of 2 to 3 cm down to an RMS of 0.26 m. Meanwhile the roll angle estimation achieves deviations down to 0.1°. Both implemented filters achieve comparable results.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"304-312"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11345483","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026572","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}
Pub Date : 2026-01-06DOI: 10.1109/OJITS.2026.3651438
Hafiz Muhammad Waseem;Noor Munir;Seong Oun Hwang
Intelligent transportation initiatives increasingly employ extensive networks of Internet-of-Things (IoT) sensors in combination with fog-computing platforms that locate computational resources near data sources in both maritime and urban environments. Although such connectivity enhances traffic monitoring and control, it simultaneously broadens the attack surface, placing sensitive operational data at heightened risk. Identity-Based Encryption (IBE) simplifies cryptographic key management in these contexts; however, it remains constrained by key-escrow exposure and the practical complexity of securely distributing private keys. This study analyzes these limitations and evaluates the extent to which two quantum techniques, Blind Quantum Computation (BQC) and Quantum Annealing (QA), can provide effective solutions. In particular, BQC enables encrypted computation without disclosing the user’s identity to the processing server, thereby substantially mitigating the key-escrow vulnerability inherent in conventional IBE deployments. Meanwhile, QA is recommended for its ability to dynamically optimize network performance and security configurations. By synthesizing recent developments, discussing challenges, and recommending quantum-enhanced solutions, this study marks a significant step towards securing and optimizing smart transportation systems through advanced cryptographic techniques and quantum computing.
{"title":"Advancing IoT-Driven Transportation Security: A Comprehensive Review of Privacy-Preserving Identity-Based Encryption With Quantum Enhancements","authors":"Hafiz Muhammad Waseem;Noor Munir;Seong Oun Hwang","doi":"10.1109/OJITS.2026.3651438","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3651438","url":null,"abstract":"Intelligent transportation initiatives increasingly employ extensive networks of Internet-of-Things (IoT) sensors in combination with fog-computing platforms that locate computational resources near data sources in both maritime and urban environments. Although such connectivity enhances traffic monitoring and control, it simultaneously broadens the attack surface, placing sensitive operational data at heightened risk. Identity-Based Encryption (IBE) simplifies cryptographic key management in these contexts; however, it remains constrained by key-escrow exposure and the practical complexity of securely distributing private keys. This study analyzes these limitations and evaluates the extent to which two quantum techniques, Blind Quantum Computation (BQC) and Quantum Annealing (QA), can provide effective solutions. In particular, BQC enables encrypted computation without disclosing the user’s identity to the processing server, thereby substantially mitigating the key-escrow vulnerability inherent in conventional IBE deployments. Meanwhile, QA is recommended for its ability to dynamically optimize network performance and security configurations. By synthesizing recent developments, discussing challenges, and recommending quantum-enhanced solutions, this study marks a significant step towards securing and optimizing smart transportation systems through advanced cryptographic techniques and quantum computing.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"268-284"},"PeriodicalIF":5.3,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11329403","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982222","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}
Pub Date : 2026-01-05DOI: 10.1109/OJITS.2026.3650976
Francesco Vitale;Ramin Niroumand;Claudio Roncoli
We propose a novel control strategy for signal-free intersection management through trajectory optimization for connected and automated vehicles. Such methodology is designed to be employed in a distributed manner, hence with no need for central units or specific tasks for leading vehicles, while only a limited amount of information needs to be exchanged and processed. The approach relies on an iterative distributed allocation and subsequent optimization of the time slots to cross the intersection. The distributed allocation aims to identify the constraints for the optimization problem to be solved, which enables the formulation of uncoupled subproblems that can be solved by each vehicle independently. The iterative algorithm initially allows the allocated time slots to overlap via a violation function that gradually decreases to zero as the algorithm progresses. This provides the optimization problem with enough flexibility to allow vehicles to resize their time slots and make them more suitable to meet their own requirements of trajectory smoothness and error minimization. We include simulation results and sensitivity analyses to demonstrate the effectiveness of our approach.
{"title":"Distributed Signal-Free Intersection Optimization via Iterative Time Slots Adjustment for Connected and Automated Vehicles","authors":"Francesco Vitale;Ramin Niroumand;Claudio Roncoli","doi":"10.1109/OJITS.2026.3650976","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3650976","url":null,"abstract":"We propose a novel control strategy for signal-free intersection management through trajectory optimization for connected and automated vehicles. Such methodology is designed to be employed in a distributed manner, hence with no need for central units or specific tasks for leading vehicles, while only a limited amount of information needs to be exchanged and processed. The approach relies on an iterative distributed allocation and subsequent optimization of the time slots to cross the intersection. The distributed allocation aims to identify the constraints for the optimization problem to be solved, which enables the formulation of uncoupled subproblems that can be solved by each vehicle independently. The iterative algorithm initially allows the allocated time slots to overlap via a violation function that gradually decreases to zero as the algorithm progresses. This provides the optimization problem with enough flexibility to allow vehicles to resize their time slots and make them more suitable to meet their own requirements of trajectory smoothness and error minimization. We include simulation results and sensitivity analyses to demonstrate the effectiveness of our approach.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"285-303"},"PeriodicalIF":5.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11329051","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026411","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}
Pub Date : 2026-01-02DOI: 10.1109/OJITS.2025.3650561
Muhammad Fawzan Anwari Muhammad Saiful Anuar;Fadhlan Hafizhelmi Kamaru Zaman;Syahrul Afzal Bin Che Abdullah;Kok Mung Ng;Kanendra Naidu Vijyakumar;Shyh Kang Ng
Distracted driving is a leading cause of road accidents, with visual and manual distractions being particularly prevalent. Traditional computer vision methods, particularly Convolutional Neural Networks (CNNs), have been extensively utilized for detecting driver behavior; however, they face challenges in effectively modeling long-range dependencies and complex spatiotemporal patterns. Recent advancements in Vision Transformer (ViT) demonstrate significant potential to address these limitations by leveraging global attention mechanisms and a scalable architecture. This review presents a comprehensive review of ViT-based approaches in distracted driving detection, which covers both image-based and video-based methods. It examines several architectural innovations, such as lightweight ViT variants, pose-aware attention-enhanced models, and hybrid ViT-architecture designs. The review also explores multi-modal and multi-view fusion strategies, which integrate several inputs such as RGB, infrared, depth, and physiological signals to enhance model robustness across diverse driving scenarios. In addition, the paper highlights benchmark datasets and performance comparisons used in distracted driving behavior detection. Finally, this review highlights the current challenges, including computational cost and interpretability, while also proposing directions for future research. Overall, ViT-based models present a promising foundation for developing the next generation of intelligent driver monitoring systems.
{"title":"Transformer Architectures for Distracted Driving Behavior Detection: A Comprehensive Review of Vision-Based Approaches","authors":"Muhammad Fawzan Anwari Muhammad Saiful Anuar;Fadhlan Hafizhelmi Kamaru Zaman;Syahrul Afzal Bin Che Abdullah;Kok Mung Ng;Kanendra Naidu Vijyakumar;Shyh Kang Ng","doi":"10.1109/OJITS.2025.3650561","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3650561","url":null,"abstract":"Distracted driving is a leading cause of road accidents, with visual and manual distractions being particularly prevalent. Traditional computer vision methods, particularly Convolutional Neural Networks (CNNs), have been extensively utilized for detecting driver behavior; however, they face challenges in effectively modeling long-range dependencies and complex spatiotemporal patterns. Recent advancements in Vision Transformer (ViT) demonstrate significant potential to address these limitations by leveraging global attention mechanisms and a scalable architecture. This review presents a comprehensive review of ViT-based approaches in distracted driving detection, which covers both image-based and video-based methods. It examines several architectural innovations, such as lightweight ViT variants, pose-aware attention-enhanced models, and hybrid ViT-architecture designs. The review also explores multi-modal and multi-view fusion strategies, which integrate several inputs such as RGB, infrared, depth, and physiological signals to enhance model robustness across diverse driving scenarios. In addition, the paper highlights benchmark datasets and performance comparisons used in distracted driving behavior detection. Finally, this review highlights the current challenges, including computational cost and interpretability, while also proposing directions for future research. Overall, ViT-based models present a promising foundation for developing the next generation of intelligent driver monitoring systems.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"233-267"},"PeriodicalIF":5.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11322789","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982216","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}
The integration of Internet of Things (IoT) technologies into modern vehicles has facilitated the emergence of the Internet of Vehicles (IoV), revolutionizing the automotive industry by enabling advanced connectivity and data-driven functionalities. Among the many applications made possible by these advancements, accurate driver identification has become essential for enhancing vehicle security, personalizing user experiences, and supporting usage-based services. However, existing driver identification methods often struggle to maintain accuracy across various road environments, as driving behavior varies with road characteristics. This paper introduces a novel driver identification framework that dynamically adapts to varying road geometries by integrating road curvature analysis to improve both accuracy and robustness across diverse road environments. Using global positioning system (GPS) sensor data, road curvature is estimated using the Menger curvature method, and road curvature segments are classified into distinct types through $k$ -means clustering with dynamic time warping. Separate driver identification models are then developed for each road type using machine learning algorithms, including Random Forest, XGBoost, and LightGBM, to capture the subtle differences in driving behavior with varying road types. Extensive experiments using real-world driving data demonstrate that the proposed method achieves up to 86.02% accuracy on unseen road environments and outperforms existing methods by up to 18.64%. These experimental results highlight the improved generalization capability and comprehensive validation of the proposed model, emphasizing its effectiveness for robust driver identification in realistic scenarios.
{"title":"Generalizable Driver Identification Through Road Curvature Analysis in Internet of Vehicles","authors":"Junghyun Lee;Hyeonseok Seo;Sangdon Park;Jaewoo Kim;Jun Kyun Choi","doi":"10.1109/OJITS.2025.3650291","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3650291","url":null,"abstract":"The integration of Internet of Things (IoT) technologies into modern vehicles has facilitated the emergence of the Internet of Vehicles (IoV), revolutionizing the automotive industry by enabling advanced connectivity and data-driven functionalities. Among the many applications made possible by these advancements, accurate driver identification has become essential for enhancing vehicle security, personalizing user experiences, and supporting usage-based services. However, existing driver identification methods often struggle to maintain accuracy across various road environments, as driving behavior varies with road characteristics. This paper introduces a novel driver identification framework that dynamically adapts to varying road geometries by integrating road curvature analysis to improve both accuracy and robustness across diverse road environments. Using global positioning system (GPS) sensor data, road curvature is estimated using the Menger curvature method, and road curvature segments are classified into distinct types through <inline-formula> <tex-math>$k$ </tex-math></inline-formula>-means clustering with dynamic time warping. Separate driver identification models are then developed for each road type using machine learning algorithms, including Random Forest, XGBoost, and LightGBM, to capture the subtle differences in driving behavior with varying road types. Extensive experiments using real-world driving data demonstrate that the proposed method achieves up to 86.02% accuracy on unseen road environments and outperforms existing methods by up to 18.64%. These experimental results highlight the improved generalization capability and comprehensive validation of the proposed model, emphasizing its effectiveness for robust driver identification in realistic scenarios.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"218-232"},"PeriodicalIF":5.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11321201","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982332","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}
This paper presents the First Boat Rescue (FBR) problem, a new challenging variant of the well-known Electric Vehicle Routing problem. FBR stems from practical rescue operations where a rescue lifeboat and its medical team provide assistance to a boat close to the coast. Quite often the boat calls for unnecessary assistance which leads to a waste of resources. As an alternative and cheaper approach, this paper proposes the use of Uncrewed Aerial Vehicles (UAVs) equipped with basic medical tools. More precisely, a lifeboat departure can be avoided when the UAV reaches the boat and remotely connects to the medical team which, by using the UAV’s medical tools, deems the assistance unneeded. UAVs are battery powered which may require recharging activities to accomplish the rescue operations. A buoy recharging station that uses the sea movement and provides a charging pad for a UAV can be used. When buoys are suitably disposed in the rescuing area, a UAV can assist multiple boats in need of emergency without wasting rescue lifeboat fuel and unnecessarily occupying the time of the medical team. This paper studies FBR in two scenarios with partial and full battery recharging policies and presents the Integer Linear Programming (ILP) formulations of the problems. For FBR in the partial recharging scenario, the paper proposes two heuristics. The paper also proves that there is an algorithm that approximates FBR with full recharging policy. The paper concludes by describing various simulations and evaluates the proposed algorithms on random and ad-hoc instances.
{"title":"UAVs Missions for Sea Emergencies","authors":"Sajjad Ghobadi;Leonardo Mostarda;Alfredo Navarra;Francesco Piselli","doi":"10.1109/OJITS.2025.3650067","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3650067","url":null,"abstract":"This paper presents the First Boat Rescue (FBR) problem, a new challenging variant of the well-known Electric Vehicle Routing problem. FBR stems from practical rescue operations where a rescue lifeboat and its medical team provide assistance to a boat close to the coast. Quite often the boat calls for unnecessary assistance which leads to a waste of resources. As an alternative and cheaper approach, this paper proposes the use of Uncrewed Aerial Vehicles (UAVs) equipped with basic medical tools. More precisely, a lifeboat departure can be avoided when the UAV reaches the boat and remotely connects to the medical team which, by using the UAV’s medical tools, deems the assistance unneeded. UAVs are battery powered which may require recharging activities to accomplish the rescue operations. A buoy recharging station that uses the sea movement and provides a charging pad for a UAV can be used. When buoys are suitably disposed in the rescuing area, a UAV can assist multiple boats in need of emergency without wasting rescue lifeboat fuel and unnecessarily occupying the time of the medical team. This paper studies FBR in two scenarios with partial and full battery recharging policies and presents the Integer Linear Programming (ILP) formulations of the problems. For FBR in the partial recharging scenario, the paper proposes two heuristics. The paper also proves that there is an algorithm that approximates FBR with full recharging policy. The paper concludes by describing various simulations and evaluates the proposed algorithms on random and ad-hoc instances.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"200-217"},"PeriodicalIF":5.3,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11320441","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982331","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}
With the rapid rise of e-commerce, the logistics and distribution industry is experiencing unprecedented growth. In particular, intra-city distribution is the crucial “last mile” of logistics and plays a decisive role in determining overall customer satisfaction. This study improves an inclusive vehicle routing optimization framework for intra-city distribution under dynamic demand. The initiative of a novel memetic algorithm that efficiently solves the NP-hard dynamic vehicle routing problem while guaranteeing high service quality and cost reduction. However, modern intercity distribution systems often struggle with low information, unpredictable demand patterns, and high operational costs due to scattered customer locations and dynamic order information. Addressing these challenges, this study suggests a comprehensive and intelligent vehicle routing optimization framework tailored for intracity distribution under dynamic demand conditions. The proposed system begins with a grey prediction model for short-term demand forecasting across many distribution regions, permitting differentiated vehicle loading methods to optimize transportation costs and improve operational effectiveness. Building upon this, a dynamic vehicle routing optimization model is formulated to reduce costs while assuring high levels of customer satisfaction within strict delivery time windows. To competently manage fluctuating demand, a dynamic information processing approach is introduced; prioritizing customer needs based on their urgency and importance, thereby guaranteeing the timely delivery of critical orders with minimal computational overhead. Moreover, a novel memetic algorithm is considered to solve the complex NP-hard dynamic vehicle routing problem. This algorithm integrates an adaptive elite genetic algorithm for global search with improved crossover and mutation operators, improved by local search methods such as 2-opt and swap methods to refine solutions. Numerical experiments validate the feasibility and performance of the proposed method, indicating significant improvements over conventional fully loaded vehicle schemes and regular route update methods. The results highlight the practical value of the system in attractive intra-city logistics efficiency, reducing costs, and inspiring customer service standards.
{"title":"Dynamic Vehicle Routing Optimization for Urban Distribution Under Real-Time Demand Fluctuations","authors":"Hashim Hashim Armayau;Jiani Wu;Wajahat Akbar;Shuguang Li;Altaf Hussain;Insaf Ullah;Tariq Hussain;Mehmood Alam;Weiwei Jiang","doi":"10.1109/OJITS.2025.3649932","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3649932","url":null,"abstract":"With the rapid rise of e-commerce, the logistics and distribution industry is experiencing unprecedented growth. In particular, intra-city distribution is the crucial “last mile” of logistics and plays a decisive role in determining overall customer satisfaction. This study improves an inclusive vehicle routing optimization framework for intra-city distribution under dynamic demand. The initiative of a novel memetic algorithm that efficiently solves the NP-hard dynamic vehicle routing problem while guaranteeing high service quality and cost reduction. However, modern intercity distribution systems often struggle with low information, unpredictable demand patterns, and high operational costs due to scattered customer locations and dynamic order information. Addressing these challenges, this study suggests a comprehensive and intelligent vehicle routing optimization framework tailored for intracity distribution under dynamic demand conditions. The proposed system begins with a grey prediction model for short-term demand forecasting across many distribution regions, permitting differentiated vehicle loading methods to optimize transportation costs and improve operational effectiveness. Building upon this, a dynamic vehicle routing optimization model is formulated to reduce costs while assuring high levels of customer satisfaction within strict delivery time windows. To competently manage fluctuating demand, a dynamic information processing approach is introduced; prioritizing customer needs based on their urgency and importance, thereby guaranteeing the timely delivery of critical orders with minimal computational overhead. Moreover, a novel memetic algorithm is considered to solve the complex NP-hard dynamic vehicle routing problem. This algorithm integrates an adaptive elite genetic algorithm for global search with improved crossover and mutation operators, improved by local search methods such as 2-opt and swap methods to refine solutions. Numerical experiments validate the feasibility and performance of the proposed method, indicating significant improvements over conventional fully loaded vehicle schemes and regular route update methods. The results highlight the practical value of the system in attractive intra-city logistics efficiency, reducing costs, and inspiring customer service standards.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"313-336"},"PeriodicalIF":5.3,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11320445","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082140","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}
Pub Date : 2025-12-31DOI: 10.1109/OJITS.2025.3650100
Jairaj Desai;Christopher Gartner;Rahul Suryakant Sakhare;Edward D. Cox;Darcy M. Bullock
Traditionally, crash data, crash risk models, video recordings and user surveys have been utilized by agencies to measure the safety benefits of ramp metering technology. Connected vehicle data can now provide an agile evaluation alternative for quantifying impact of ramp meter deployments. Furthermore, in contrast to crash data, connected vehicle near miss events occur much more frequently, so the before-after evaluation can be conducted over a much shorter time period consisting of a few months, or perhaps even a few weeks. Indiana deployed ramp meters on the southeast section of I-465 around Indianapolis, on or around May 14, 2024, which were then active primarily during the morning and evening peak hours. Hard-braking events, a surrogate safety performance measure, were estimated from high-frequency connected vehicle data available at 3-second fidelity for vehicles passing through the metered ramps and the adjacent mainline interstate. A before-after analysis for the 4-5 PM peak hour showed approximately a 61% reduction in hard-braking events on mainline merge areas adjoining the metered ramps on the inner loop of I-465. Spatial analysis also showed a 70%, 41% and 33% median reduction in mild, moderate and severe hard-braking events per 0.1-mile segment in the entire 7.5-mile mainline corridor adjacent to metered ramps. The methodologies and performance measures provided in this paper demonstrate how connected vehicle data scales well to systematically assess and document the performance of new ramp metering deployments.
{"title":"Evaluating Safety Benefits of Ramp Metering By Leveraging Connected Vehicle Data: Case Study of Indiana Roadways","authors":"Jairaj Desai;Christopher Gartner;Rahul Suryakant Sakhare;Edward D. Cox;Darcy M. Bullock","doi":"10.1109/OJITS.2025.3650100","DOIUrl":"https://doi.org/10.1109/OJITS.2025.3650100","url":null,"abstract":"Traditionally, crash data, crash risk models, video recordings and user surveys have been utilized by agencies to measure the safety benefits of ramp metering technology. Connected vehicle data can now provide an agile evaluation alternative for quantifying impact of ramp meter deployments. Furthermore, in contrast to crash data, connected vehicle near miss events occur much more frequently, so the before-after evaluation can be conducted over a much shorter time period consisting of a few months, or perhaps even a few weeks. Indiana deployed ramp meters on the southeast section of I-465 around Indianapolis, on or around May 14, 2024, which were then active primarily during the morning and evening peak hours. Hard-braking events, a surrogate safety performance measure, were estimated from high-frequency connected vehicle data available at 3-second fidelity for vehicles passing through the metered ramps and the adjacent mainline interstate. A before-after analysis for the 4-5 PM peak hour showed approximately a 61% reduction in hard-braking events on mainline merge areas adjoining the metered ramps on the inner loop of I-465. Spatial analysis also showed a 70%, 41% and 33% median reduction in mild, moderate and severe hard-braking events per 0.1-mile segment in the entire 7.5-mile mainline corridor adjacent to metered ramps. The methodologies and performance measures provided in this paper demonstrate how connected vehicle data scales well to systematically assess and document the performance of new ramp metering deployments.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"190-199"},"PeriodicalIF":5.3,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11320434","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929404","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：