Maria Asuncion del Cacho Estil-Les;Agostino Marcello Mangini;Michele Roccotelli;Maria Pia Fanti
{"title":"Electric Vehicle Routing Optimization for Postal Delivery and Waste Collection in Smart Cities","authors":"Maria Asuncion del Cacho Estil-Les;Agostino Marcello Mangini;Michele Roccotelli;Maria Pia Fanti","doi":"10.1109/TITS.2025.3529181","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529181","url":null,"abstract":"This paper addresses two important smart city logistics problems, i.e., Postal Delivery and Waste Collection, using Electric Vehicle Routing Problems. To this aim two Mixed Integer Linear Programming problems are formulated with the objective of carrying out the collection or delivery activities by minimizing the route length, respecting the working time, and considering the Electric Vehicles (EVs) battery charge constraints. While satisfying the customer needs under the mentioned traveling constraints, the proposed models take into account the implementation of smart charging strategies to minimize the demand peaks on the power grid both at district and charge station levels, that is suitable in large scale problems. To address the complexity of the models, a heuristic algorithm implementing clustering and routing strategies is proposed. Two case studies are implemented to demonstrate the effectiveness of the proposed models for Postal Delivery and Waste Collection activities in large systems.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3307-3323"},"PeriodicalIF":7.9,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Task-Oriented Spatial Graph Structure Learning Method for Traffic Forecasting","authors":"Ting Wang;Shengjie Zhao;Wenzhen Jia;Daqian Shi","doi":"10.1109/TITS.2025.3537637","DOIUrl":"https://doi.org/10.1109/TITS.2025.3537637","url":null,"abstract":"Traffic forecasting is the foundation of intelligent transportation systems (ITS). In recent, graph neural networks (GNNs) have successfully captured spatial-temporal dependencies to forecast traffic conditions by transforming traffic data in the graph domain. Nevertheless, the existing methods focus only on learning informative graph representations and fail to model informative graph structures, which hinders the capture of dynamic spatial-temporal dependencies caused by dynamic factors such as weather, accidents, and special events. In this paper, we propose a novel task-oriented Spatial Graph Structure Learning (SGSL) method, which aims to capture dynamic dependencies by jointly learning graph structures and graph representations. Compared to methods that use spectral graph representations, we exploit a learnable spatial graph to effectively model dynamic dependencies in traffic data. Moreover, we directly define graph convolutions on spatial relations to specify different edge weights when aggregating the information of spatial neighbours. Thus, the graph structure alterations, i.e., the relation changes, and the time-varying weights of relations can be encapsulated, thereby effectively representing dynamic dependencies. The gradient descent strategy is introduced to periodically learn a spatial graph through joint optimization with a newly designed deep graph learning model named GAT-nLSTM. In this manner, the intrinsic behaviours of nodes are learned to capture correlations across periods. Notably, the optimization process is performed under the traffic forecasting constraint to ensure that the learned spatial graph is specific to this task. Compared with those of state-of-the-art baselines, the experimental results obtained on real-world traffic datasets show significant improvement, which verifies the superiority of the proposed SGSL.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 4","pages":"4770-4779"},"PeriodicalIF":7.9,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Guide to Image- and Video-Based Small Object Detection Using Deep Learning: Case Study of Maritime Surveillance","authors":"Aref Miri Rekavandi;Lian Xu;Farid Boussaid;Abd-Krim Seghouane;Stephen Hoefs;Mohammed Bennamoun","doi":"10.1109/TITS.2025.3530678","DOIUrl":"https://doi.org/10.1109/TITS.2025.3530678","url":null,"abstract":"Detecting small objects in optical images and videos is a significant challenge in numerous intelligent transportation and autonomous systems. State-of-the-art generic object detection methods fail to accurately localize and identify such small objects (e.g., pedestrians, small vehicles, obstacles). Because small objects occupy only a small area in the input image (e.g., <inline-formula> <tex-math>$32 times 32$ </tex-math></inline-formula> pixels or less), the information extracted from such a small area is not always rich enough to support decision-making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of Small Object Detection (SOD). In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provides a taxonomy that illustrates the broad picture of current research. We further explore methods to boost the performance of small object detection in maritime settings, where enhanced performance is crucial for ensuring safety and managing traffic. Detecting small objects in the maritime environment requires additional considerations and the current survey aims to review the advanced techniques addressing those aspects. In addition, the popular SOD datasets for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided. The link to these datasets appears in <uri>https://github.com/arekavandi/Datasets_SOD</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2851-2879"},"PeriodicalIF":7.9,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535525","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":"Dual-STGAT: Dual Spatio-Temporal Graph Attention Networks With Feature Fusion for Pedestrian Crossing Intention Prediction","authors":"Jing Lian;Yiyang Luo;Xuecheng Wang;Linhui Li;Ge Guo;Weiwei Ren;Tao Zhang","doi":"10.1109/TITS.2025.3528391","DOIUrl":"https://doi.org/10.1109/TITS.2025.3528391","url":null,"abstract":"Pedestrian intent prediction is critical for autonomous driving, as accurately predicting crossing intentions helps prevent collisions and ensures the safety of both pedestrians and passengers. Recent research has focused on vision-based deep neural networks for this task, but challenges remain. First, current methods suffer from low efficiency in multi-feature fusion and unreliable predictions under challenging conditions. Additionally, real-time performance is essential in practical applications, so the efficiency of the algorithm is crucial. To address these issues, we propose a novel architecture, Dual-STGAT, which uses a dual-level spatio-temporal graph network to extract pedestrian pose and scene interaction features, reducing information loss and improving feature fusion efficiency. The model captures key features of pedestrian behavior and the surrounding environment through two modules: the Pedestrian Module and the Scene Module. The Pedestrian Module extracts pedestrian motion features using a spatio-temporal graph attention network, while the Scene Module models interactions between pedestrians and surrounding objects by integrating visual, semantic, and motion information through a graph network. Extensive experiments conducted on the PIE and JAAD datasets show that Dual-STGAT achieves over 90% accuracy in pedestrian crossing intention prediction, with inference latency close to 5ms, making it well-suited for large-scale production autonomous driving systems that demand both performance and computational efficiency.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 4","pages":"5396-5410"},"PeriodicalIF":7.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726528","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":"HighlightNet: Learning Highlight-Guided Attention Network for Nighttime Vehicle Detection","authors":"Yu-Pei Song;Xiao Wu;Wei Li;Ting-Quan He;Dong-Feng Hu;Qiang Peng","doi":"10.1109/TITS.2025.3539095","DOIUrl":"https://doi.org/10.1109/TITS.2025.3539095","url":null,"abstract":"Vehicle detection at night is a crucial task in Intelligent Transportation Systems. Due to the complex lighting environment, vehicle detection at night remains a challenging task. Headlights and taillights are essential cues to identify vehicles at night. However, existing methods struggle to effectively utilize the light information of the vehicle. This paper proposes a novel highlight-guided framework to identify vehicles, named HighlightNet, by utilizing both the illumination data from the vehicle lights and the reflective properties of vehicles. The framework combines vehicle detection and highlight area recognition via dual-branch joint learning. To ensure that both branches focus on the highlighted regions, Feature Similarity Awareness Attention (FSAA) is introduced to capture the common attention regions of different branches. Highlight Region Perception (HRP) is proposed to exclude streetlights and other reflective illuminations from the FSAA output, which generates a mask map capable of differentiating the foreground from the background of highlighted areas. It improves the allocation of feature weights and adaptively modifies the distribution within the dual-branch configuration. Furthermore, to address the severe pixel imbalance between the highlighted area and the background, Adaptive Spatial Balance (ASB) loss is introduced to allocate the attention towards prospective vehicle regions while diminishing the emphasis on background regions. Extensive experiments conducted on the BDD100K-Night dataset and a newly acquired dataset specifically designed for nighttime surveillance, called the NightVehicle dataset, demonstrate that HighlightNet outperforms the state-of-the-art methods for nighttime vehicle detection.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 4","pages":"4491-4503"},"PeriodicalIF":7.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Data-Driven Dynamics Simulation Model for Railway Vehicles Based on Lightweight 3DCNN With Physics-Informed Constraints","authors":"Zhiwei Zheng;Cai Yi;Jianhui Lin","doi":"10.1109/TITS.2025.3533614","DOIUrl":"https://doi.org/10.1109/TITS.2025.3533614","url":null,"abstract":"The dynamics simulation of complex railway vehicles requires a dedicated vehicle model, such as multi-body dynamics model. However, the multi-body model is time-consuming in long-distance simulation due to its computational complexity. This issue can be alleviated by using a data-driven vehicle dynamics model due to its effective generalization and computational speed. Firstly, the construction of the physical model of the vehicle system is carried out to obtain the coupling relationship between the components. Secondly, the coupling relationship between the components is embedded into the loss function of the deep neural network as physics-informed constraints. Further, the network parameters satisfying certain physical laws are obtained by minimizing the loss function. Finally, the proposed lightweight 3D convolutional neural network is used to predict the vibration state of the vehicle system. The dynamic response resulting from both the data-driven simulation model and the multi-body simulation model are investigated and compared. The simulation results show that the data-driven dynamics simulation model can accurately predict the vibration state of the vehicle system. The data-driven simulation model has smaller size and faster operation speed, which can be applied to long-distance prediction research of vehicle systems.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3004-3015"},"PeriodicalIF":7.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535424","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}
Zbigniew Marszalek;Tomasz Konior;Jacek Izydorczyk;Mateusz Szulik;Krzysztof Duda
{"title":"Vehicle Classification Based on Multi-Frequency Resistance and Reactance Magnetic Profiles","authors":"Zbigniew Marszalek;Tomasz Konior;Jacek Izydorczyk;Mateusz Szulik;Krzysztof Duda","doi":"10.1109/TITS.2025.3537137","DOIUrl":"https://doi.org/10.1109/TITS.2025.3537137","url":null,"abstract":"This paper presents the application of inductive loop (IL) sensor technology to classify vehicles in traffic lanes. Two wide and two slim IL sensors were installed in the traffic lane. The wide and slim IL sensors feature distinct structural designs and varying levels of sensitivity. An advanced multi-frequency impedance measurement (MFIM) system was used to operate the IL sensors. For a passing vehicle, the impedance of every IL sensor at three different operating frequencies is computed and finally recorded at a sampling frequency of 1 kHz. Each of the 12 recorded signals provides a complex-value vehicle magnetic profile (VMP). Based on the VMPs from two IL sensors positioned one after the other, an accurate measurement of vehicle speed is obtained. Furthermore, the system can capture images of vehicles. A reference database of VMPs was created for various vehicle categories. The software selects 10 statistical features from each real and imaginary VMP part. Eight machine learning algorithms were implemented using ready-made Python3 implementations. Cross-validation accuracy was tested for five feature configurations, including slim and wide IL sensors. The Random Forest (RF) algorithm, utilizing 20 features from the complex VMP, achieved an accuracy of 99.8 % for the wide IL sensor. No errors were made by the Voting Classifier and RF algorithm when they incorporated a fusion of features from complex VMPs with MFIM system, utilizing both slim and wide IL sensors.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 4","pages":"5322-5331"},"PeriodicalIF":7.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive Testing Environment Generation for Connected and Automated Vehicles With Dense Reinforcement Learning","authors":"Jingxuan Yang;Ruoxuan Bai;Haoyuan Ji;Yi Zhang;Jianming Hu;Shuo Feng","doi":"10.1109/TITS.2025.3535866","DOIUrl":"https://doi.org/10.1109/TITS.2025.3535866","url":null,"abstract":"The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate models), conducting tests in these scenarios, and subsequently evaluating CAVs’ safety performances. However, substantial differences between CAVs and the prior knowledge can significantly diminish the evaluation efficiency. In response to this issue, existing studies predominantly concentrate on the adaptive design of testing scenarios during the CAV testing process. Yet, these methods have limitations in their applicability to high-dimensional scenarios. To overcome this challenge, we develop an adaptive testing environment that bolsters evaluation robustness by incorporating multiple surrogate models and optimizing the combination coefficients of these surrogate models to enhance evaluation efficiency. We formulate the optimization problem as a regression task utilizing quadratic programming. To efficiently obtain the regression target via reinforcement learning, we propose the dense reinforcement learning method and devise a new adaptive policy with high sample efficiency. Essentially, our approach centers on learning the values of critical scenes displaying substantial surrogate-to-real gaps. The effectiveness of our method is validated in high-dimensional overtaking scenarios, demonstrating that our approach achieves notable evaluation efficiency.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 4","pages":"5135-5145"},"PeriodicalIF":7.9,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740242","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":"Uncertainty Quantification for Safe and Reliable Autonomous Vehicles: A Review of Methods and Applications","authors":"Ke Wang;Chongqiang Shen;Xingcan Li;Jianbo Lu","doi":"10.1109/TITS.2025.3532803","DOIUrl":"https://doi.org/10.1109/TITS.2025.3532803","url":null,"abstract":"In the past decade, deep learning has been widely applied across various fields. However, its applicability in open-world scenarios is often limited due to the lack of quantifying uncertainty in both data and models. In recent years, a multitude of uncertainty quantification (UQ) approaches for neural networks have emerged and found applications in safety-critical domains such as autonomous vehicles and medical analysis. This paper aims to review the latest advancements in UQ methods and investigate their application specifically in the field of computer vision and autonomous vehicles. Initially, we identify several key qualifications, namely practicability, robustness, accuracy, scalability, and efficiency (referred to as PRASE), and employ them as evaluation criteria throughout this study. By considering these criteria as uniform measurements, we meticulously evaluate and compare the performance of different types of UQ methods, including Bayesian methods, ensemble methods, and single deterministic methods. Furthermore, we delve into the discussion of their application in diverse tasks within the autonomous vehicle domain, such as semantic segmentation, object detection, depth estimation, and end-to-end control. Through comprehensive analysis and comparison, we identify a range of challenges and propose future research directions in this field. Our findings shed light on the importance of addressing uncertainty quantification in deep learning models and provide insights into enhancing the reliability and performance of autonomous vehicles in real-world scenarios.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2880-2896"},"PeriodicalIF":7.9,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535418","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":"Framework of Adaptive Driving: Linking Situation Awareness, Driving Goals, and Driving Intentions Using Eye-Tracking and Vehicle Kinetic Data","authors":"Hsueh-Yi Lai","doi":"10.1109/TITS.2025.3530252","DOIUrl":"https://doi.org/10.1109/TITS.2025.3530252","url":null,"abstract":"Although current Artificial Intelligence (AI) can detect maneuvering intentions, it often overlooks the underlying driving goals that reveal drivers’ genuine requirements. To detect real-time driving goals using AI for providing effective decision aids, this research introduces the Framework of Adaptive Driving (FAD), which considers cognitive activities and action strategies. We have outlined five driving goals to elucidate the connections between Situation Awareness (SA), and intentions. The study involved 31 participants and 573 driving simulation events, during which we collected both eye-tracking and kinetic data. Exploratory Factor Analysis (EFA) identified 8 factors, categorized into SA and maneuver-related factors. Statistical and qualitative analysis follow up to specify the varying requirements among the driving foals defined. Generally, factor ‘Cognitive load’ can reflect cognitive activities, while ‘Saccade on the surroundings’ and ‘Saccade movement’ can indicate action strategies. For the goals where emerging risks are not a concern, ‘Active acceleration’ signifies drivers’ intention to enhance driving efficiency. However, the diverse features in ‘Saccade on the surroundings’ imply varying driving considerations. Goals for routine tasks focus on internal vehicle operations, while goals for driving benefits management highlight adjacent surroundings. Conversely, for goals addressing emerging risks, ‘Deceleration’ prevails. Furthermore, ‘Steering strategy’ implies a preference for steering when SA is adequate. In this context, SA-related factors like ‘Front observation,’ ‘Saccade movement,’ and ‘Cognitive load’ signify efforts to enhance SA under time constraints. However, for the driving goals under extreme urgency, the factor ‘Lateral movement’ replaces ‘Steering strategy’, implying severe steering without adequate SA.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3295-3306"},"PeriodicalIF":7.9,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535573","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}