Industrial Vehicle-to-Infrastructure (iV2I) networks are increasingly adopted in settings such as warehouses, construction sites, and smart factories to enhance automation and operational efficiency. However, these systems face growing cybersecurity risks that threaten safety-critical operations. This paper introduces a realistic synthetic dataset created using the ID2T framework, which injects malicious traffic, such as DDoS, PortScan, and memory corruption exploits, into benign communication traces collected from actual iV2I environments. The resulting hybrid dataset, combining synthetic and real-world traffic, enables the supervised training of a Multi-Layer Perceptron (MLP) neural network using 16 meticulously crafted flow-based features. Experimental results demonstrate high detection accuracy under both balanced and threat-specific conditions, validating the effectiveness of ID2T in modeling domain-relevant cyberattack behaviors. In addition to strong classification performance, this work demonstrates how synthetic malicious traffic generation reduces the cost and complexity of cyberattack emulation. The proposed method offers a scalable and reproducible framework for training intrusion detection systems (IDS), highlighting the critical role of Artificial Intelligence (AI) in securing next-generation industrial vehicular networks.
{"title":"Synthetic Attack Dataset Generation With ID2T for AI-Based Intrusion Detection in Industrial V2I Network","authors":"Prinkle Sharma;Jaiganesh Anandan;Hong Liu;Jyoti Grover","doi":"10.1109/OJVT.2025.3609149","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3609149","url":null,"abstract":"Industrial Vehicle-to-Infrastructure (iV2I) networks are increasingly adopted in settings such as warehouses, construction sites, and smart factories to enhance automation and operational efficiency. However, these systems face growing cybersecurity risks that threaten safety-critical operations. This paper introduces a realistic synthetic dataset created using the ID2T framework, which injects malicious traffic, such as DDoS, PortScan, and memory corruption exploits, into benign communication traces collected from actual iV2I environments. The resulting hybrid dataset, combining synthetic and real-world traffic, enables the supervised training of a Multi-Layer Perceptron (MLP) neural network using 16 meticulously crafted flow-based features. Experimental results demonstrate high detection accuracy under both balanced and threat-specific conditions, validating the effectiveness of ID2T in modeling domain-relevant cyberattack behaviors. In addition to strong classification performance, this work demonstrates how synthetic malicious traffic generation reduces the cost and complexity of cyberattack emulation. The proposed method offers a scalable and reproducible framework for training intrusion detection systems (IDS), highlighting the critical role of Artificial Intelligence (AI) in securing next-generation industrial vehicular networks.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2509-2538"},"PeriodicalIF":4.8,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11159305","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141681","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 : 2025-09-10DOI: 10.1109/OJVT.2025.3608287
Vineet Dhanawat;Varun Shinde;Rachid Alami;Adnan Akhunzada;Zaid Bin Faheem;Anjanava Biswas
The exponential increase in the adoption of Electric Vehicles (EVs) presents significant problems to the stability of the power grid. Therefore, it is crucial to accurately anticipate the demand for EV Charging Station (CS) to address this issue. To improve forecasts and identify CS load variables, existing studies are based on load profiling, which may be difficult to obtain for commercial EV charging stations. This paper proposes an efficient deep BiLSTMNet model to solve and mitigate these problems. Energy consumption and storage at four charging stations in California are analyzed. To guarantee accuracy and uniformity, the data is preprocessed by addressing missing values and ensuring consistency. A hybrid feature selection technique integrates the Boruta algorithm and SHAP (SHapley Additive exPlanations) values to ensure robust feature selection. The EfficientBiLSTMNet model, which integrates the EfficientNet and BiLSTM layers, is trained on the preprocessed datasets. The model's hyperparameters are optimized using an Enhanced Firefly Algorithm (EFA). The model performs a time series analysis to identify daily, weekly, monthly, and seasonal patterns in EV charging demand. The integration of renewable energy sources—specifically solar and wind generation—into the EV charging infrastructure is thoroughly examined in this study, not merely as input features but as key factors influencing the stability of charging demand at various stations. Their temporal patterns and environmental dependencies are leveraged to enhance forecasting accuracy and ensure grid-aware demand management across charging stations. The proposed model's performance is evaluated using metrics such as R-squared, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Simulation results demonstrate the effectiveness of the proposed model, with an average R-squared value of 0.9, MAE of 2.15 kW, and RMSE of 2.75 kW across the four stations. The EfficientBiLSTMNet model shows superior predictive accuracy compared to traditional models, highlighting the importance of comprehensive feature selection and engineering in forecasting EV charging demand. This study provides a robust framework for predicting EV charging demand, integrating renewable energy sources to enhance the stability and sustainability of the power grid amidst the increasing penetration of EVs.
{"title":"Electric Vehicles Charging Station Load Forecasting Integration With Renewable Energy Using Novel Deep EfficientBiLSTMNet","authors":"Vineet Dhanawat;Varun Shinde;Rachid Alami;Adnan Akhunzada;Zaid Bin Faheem;Anjanava Biswas","doi":"10.1109/OJVT.2025.3608287","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3608287","url":null,"abstract":"The exponential increase in the adoption of Electric Vehicles (EVs) presents significant problems to the stability of the power grid. Therefore, it is crucial to accurately anticipate the demand for EV Charging Station (CS) to address this issue. To improve forecasts and identify CS load variables, existing studies are based on load profiling, which may be difficult to obtain for commercial EV charging stations. This paper proposes an efficient deep BiLSTMNet model to solve and mitigate these problems. Energy consumption and storage at four charging stations in California are analyzed. To guarantee accuracy and uniformity, the data is preprocessed by addressing missing values and ensuring consistency. A hybrid feature selection technique integrates the Boruta algorithm and SHAP (SHapley Additive exPlanations) values to ensure robust feature selection. The EfficientBiLSTMNet model, which integrates the EfficientNet and BiLSTM layers, is trained on the preprocessed datasets. The model's hyperparameters are optimized using an Enhanced Firefly Algorithm (EFA). The model performs a time series analysis to identify daily, weekly, monthly, and seasonal patterns in EV charging demand. The integration of renewable energy sources—specifically solar and wind generation—into the EV charging infrastructure is thoroughly examined in this study, not merely as input features but as key factors influencing the stability of charging demand at various stations. Their temporal patterns and environmental dependencies are leveraged to enhance forecasting accuracy and ensure grid-aware demand management across charging stations. The proposed model's performance is evaluated using metrics such as R-squared, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Simulation results demonstrate the effectiveness of the proposed model, with an average R-squared value of 0.9, MAE of 2.15 kW, and RMSE of 2.75 kW across the four stations. The EfficientBiLSTMNet model shows superior predictive accuracy compared to traditional models, highlighting the importance of comprehensive feature selection and engineering in forecasting EV charging demand. This study provides a robust framework for predicting EV charging demand, integrating renewable energy sources to enhance the stability and sustainability of the power grid amidst the increasing penetration of EVs.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2642-2661"},"PeriodicalIF":4.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11155205","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210152","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 : 2025-09-08DOI: 10.1109/OJVT.2025.3597609
José rodríguez-Piñeiro;Zhongxiang Wei;Jingjing Wang;Carlos A. Gutiérrez;Luis M. Correia
{"title":"Guest Editorial: Introduction to the Special Section on Current Research Trends and Open Challenges for 6G-Enabled Vehicle-to-Everything Networks","authors":"José rodríguez-Piñeiro;Zhongxiang Wei;Jingjing Wang;Carlos A. Gutiérrez;Luis M. Correia","doi":"10.1109/OJVT.2025.3597609","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3597609","url":null,"abstract":"","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2301-2304"},"PeriodicalIF":4.8,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11153379","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145011310","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 : 2025-09-05DOI: 10.1109/OJVT.2025.3606652
Saddam Hussain;Ali Tufail;Haji Awg Abdul Ghani Naim;Muhammad Asghar Khan;Gordana Barb
Named Data Networking (NDN) is considered a future architecture for content distribution in the Internet of Vehicles (IoV). The primary principles of NDN, which include naming and in-network caching, are perfectly aligned with the IoV requirements for time and location independence. Despite significant research efforts, full-scale deployment remains limited due to ongoing concerns regarding trust, safety, and security within the IoV network. Moreover, traditional security algorithms proposed for IoV are complex, with high computational demands that challenge the strict real-time constraints. To minimize the computational overhead of vehicles, we proposed an RSU-empowered proxy signature scheme for NDN-based IoV. The security of the proposed scheme is proven to be Existentially Unforgeable against Adaptive Chosen-Message Attacks (EU-ACMA) under the Random Oracle Model (ROM), considering the hardness of the Hyperelliptic Curve Discrete Logarithm Problem (HCDLP). A performance analysis, which considers both computation time and communication overhead, shows that the proposed scheme effectively minimizes these factors. Besides, we applied the Multi-Criteria Decision-Making (MCDM) technique, namely Evaluation based on Distance from Average Solution (EDAS), to meet the particular need to prioritize data in IoV. The findings show that the proposed scheme performs better than those in the related literature.
{"title":"A Lightweight Proxy Signature Scheme for Resource-Constrained NDN-Based Internet of Vehicles","authors":"Saddam Hussain;Ali Tufail;Haji Awg Abdul Ghani Naim;Muhammad Asghar Khan;Gordana Barb","doi":"10.1109/OJVT.2025.3606652","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3606652","url":null,"abstract":"Named Data Networking (NDN) is considered a future architecture for content distribution in the Internet of Vehicles (IoV). The primary principles of NDN, which include naming and in-network caching, are perfectly aligned with the IoV requirements for time and location independence. Despite significant research efforts, full-scale deployment remains limited due to ongoing concerns regarding trust, safety, and security within the IoV network. Moreover, traditional security algorithms proposed for IoV are complex, with high computational demands that challenge the strict real-time constraints. To minimize the computational overhead of vehicles, we proposed an RSU-empowered proxy signature scheme for NDN-based IoV. The security of the proposed scheme is proven to be Existentially Unforgeable against Adaptive Chosen-Message Attacks (EU-ACMA) under the Random Oracle Model (ROM), considering the hardness of the Hyperelliptic Curve Discrete Logarithm Problem (HCDLP). A performance analysis, which considers both computation time and communication overhead, shows that the proposed scheme effectively minimizes these factors. Besides, we applied the Multi-Criteria Decision-Making (MCDM) technique, namely Evaluation based on Distance from Average Solution (EDAS), to meet the particular need to prioritize data in IoV. The findings show that the proposed scheme performs better than those in the related literature.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2607-2626"},"PeriodicalIF":4.8,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11152359","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210155","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 : 2025-09-04DOI: 10.1109/OJVT.2025.3606120
Reza Jafari;Pouria Sarhadi;Amin Paykani;Shady S. Refaat;Pedram Asef
This study presents an innovative solution for simultaneous energy optimization and dynamic yaw control of all-wheel-drive (AWD) electric vehicles (EVs) using deep reinforcement learning (DRL) techniques. To this end, three model-free DRL-based methods, based on deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and TD3 enhanced with curriculum learning (CL TD3), are developed for determining optimal yaw moment control and energy optimization online. The proposed DRL controllers are benchmarked against model-based controllers, i.e., linear quadratic regulator with the sequential quadratic programming (LSQP) and sliding mode control with SQP (SSQP). A tailored multi-term reward function is structured to penalize excessive yaw rate error, sideslip angle, tire slip deviations beyond peak grip regions, and power losses based on a realistic electric machine efficiency map. The learning environment is based on a nonlinear double-track vehicle model, incorporating tire-road interactions. To evaluate the generalizability of the algorithms, the agents are tested across various velocities, tire–road friction coefficients, and additional scenarios implemented in IPG CarMaker, a high-fidelity vehicle dynamics simulator. In addition to the deployment without requiring an explicit model of the plant, the simulation results demonstrate that the proposed solution modifies vehicle dynamics and maneuverability in most cases compared to the model-based conventional controller. Furthermore, the reduction in sideslip angle, excellent traction through minimizing tire slip ratio, avoiding oversteering and understeering, and maintaining an acceptable range of energy optimization are demonstrated for DRL controllers, especially for the TD3 and CL TD3 algorithms.
{"title":"Integrated Energy Optimization and Stability Control Using Deep Reinforcement Learning for an All-Wheel-Drive Electric Vehicle","authors":"Reza Jafari;Pouria Sarhadi;Amin Paykani;Shady S. Refaat;Pedram Asef","doi":"10.1109/OJVT.2025.3606120","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3606120","url":null,"abstract":"This study presents an innovative solution for simultaneous energy optimization and dynamic yaw control of all-wheel-drive (AWD) electric vehicles (EVs) using deep reinforcement learning (DRL) techniques. To this end, three model-free DRL-based methods, based on deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and TD3 enhanced with curriculum learning (CL TD3), are developed for determining optimal yaw moment control and energy optimization online. The proposed DRL controllers are benchmarked against model-based controllers, i.e., linear quadratic regulator with the sequential quadratic programming (LSQP) and sliding mode control with SQP (SSQP). A tailored multi-term reward function is structured to penalize excessive yaw rate error, sideslip angle, tire slip deviations beyond peak grip regions, and power losses based on a realistic electric machine efficiency map. The learning environment is based on a nonlinear double-track vehicle model, incorporating tire-road interactions. To evaluate the generalizability of the algorithms, the agents are tested across various velocities, tire–road friction coefficients, and additional scenarios implemented in IPG CarMaker, a high-fidelity vehicle dynamics simulator. In addition to the deployment without requiring an explicit model of the plant, the simulation results demonstrate that the proposed solution modifies vehicle dynamics and maneuverability in most cases compared to the model-based conventional controller. Furthermore, the reduction in sideslip angle, excellent traction through minimizing tire slip ratio, avoiding oversteering and understeering, and maintaining an acceptable range of energy optimization are demonstrated for DRL controllers, especially for the TD3 and CL TD3 algorithms.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2583-2606"},"PeriodicalIF":4.8,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11150741","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210188","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 : 2025-09-04DOI: 10.1109/OJVT.2025.3606229
Siran Xu;Xiaomin Chen;Qiang Sun;Jiayi Zhang
In practical cell-free (CF) massive multiple-input multiple-output (mMIMO) networks, asynchronous reception occurs due to distributed and low-cost access points (APs), where the signals arrive at each AP at different time. In this paper, we investigate uplink (UL) spectral efficiency (SE) of asynchronous CF mMIMO with spatially correlated Rician fading channel. On the basis of the availability of prior information at APs, we derive the phase-aware minimum mean square error (MMSE) and non-perceptual linear MMSE (LMMSE) estimators. To mitigate the inter-user interference, we consider a two-layer decoding method in UL transmission. For the first-layer decoding, maximum ratio (MR) precoding is employed, while the large-scale fading decoding (LSFD) method is utilized in the second-layer decoding. Meanwhile, we consider the scenario in CF mMIMO where there is a large number of user equipment (UE), resulting in high computational complexity. To address this challenge, scalable CF mMIMO (SCF-mMIMO) architecture is proposed. On the basis of MMSE and LMMSE estimators, the novel low complexity partial MMSE (P-MMSE) detector and partial LMMSE (P-LMMSE) detector are proposed for centralized combining. For distributed combining, we also proposed the novel local partial MMSE (LP-MMSE) detector and local partial LMMSE (LP-LMMSE) detector. Numerical results demonstrate that LSFD method can enhance UL SE in CF mMIMO. Furthermore, the impact of performance loss resulting from the absence of phase information is contingent upon the length of pilot. It is minimal when pilot contamination is low. Finally, the simulation results demonstrate that the SE of the proposed detectors closely approximate the optimal combining technique for both distributed and centralized combing. It is important to note that the proposed detectors preserve performance while significantly lowering complexity.
{"title":"Uplink Performance Analysis of Asynchronous Cell-Free mMIMO With Two-Layer Decoding","authors":"Siran Xu;Xiaomin Chen;Qiang Sun;Jiayi Zhang","doi":"10.1109/OJVT.2025.3606229","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3606229","url":null,"abstract":"In practical cell-free (CF) massive multiple-input multiple-output (mMIMO) networks, asynchronous reception occurs due to distributed and low-cost access points (APs), where the signals arrive at each AP at different time. In this paper, we investigate uplink (UL) spectral efficiency (SE) of asynchronous CF mMIMO with spatially correlated Rician fading channel. On the basis of the availability of prior information at APs, we derive the phase-aware minimum mean square error (MMSE) and non-perceptual linear MMSE (LMMSE) estimators. To mitigate the inter-user interference, we consider a two-layer decoding method in UL transmission. For the first-layer decoding, maximum ratio (MR) precoding is employed, while the large-scale fading decoding (LSFD) method is utilized in the second-layer decoding. Meanwhile, we consider the scenario in CF mMIMO where there is a large number of user equipment (UE), resulting in high computational complexity. To address this challenge, scalable CF mMIMO (SCF-mMIMO) architecture is proposed. On the basis of MMSE and LMMSE estimators, the novel low complexity partial MMSE (P-MMSE) detector and partial LMMSE (P-LMMSE) detector are proposed for centralized combining. For distributed combining, we also proposed the novel local partial MMSE (LP-MMSE) detector and local partial LMMSE (LP-LMMSE) detector. Numerical results demonstrate that LSFD method can enhance UL SE in CF mMIMO. Furthermore, the impact of performance loss resulting from the absence of phase information is contingent upon the length of pilot. It is minimal when pilot contamination is low. Finally, the simulation results demonstrate that the SE of the proposed detectors closely approximate the optimal combining technique for both distributed and centralized combing. It is important to note that the proposed detectors preserve performance while significantly lowering complexity.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2494-2508"},"PeriodicalIF":4.8,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11150737","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141680","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 : 2025-09-01DOI: 10.1109/OJVT.2025.3604823
Rajendramayavan Sathyam;Yueqi Li
Foundation models are revolutionizing autonomous driving perception, transitioning the field from narrow, task-specific deep learning models to versatile, general-purpose architectures trained on vast, diverse datasets. This survey examines how these models address critical challenges in autonomous perception, including limitations in generalization, scalability, and robustness to distributional shifts. The survey introduces a novel taxonomy structured around four essential capabilities for robust performance in dynamic driving environments: generalized knowledge, spatial understanding, multi-sensor robustness, and temporal reasoning. For each capability, the survey elucidates its significance and comprehensively reviews cutting-edge approaches. Diverging from traditional method-centric surveys, our unique framework prioritizes conceptual design principles, providing a capability-driven guide for model development and clearer insights into foundational aspects. We conclude by discussing key challenges, particularly those associated with the integration of these capabilities into real-time, scalable systems, and broader deployment challenges related to computational demands and ensuring model reliability against issues like hallucinations and out-of-distribution failures. The survey also outlines crucial future research directions to enable the safe and effective deployment of foundation models in autonomous driving systems.
{"title":"Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities","authors":"Rajendramayavan Sathyam;Yueqi Li","doi":"10.1109/OJVT.2025.3604823","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3604823","url":null,"abstract":"Foundation models are revolutionizing autonomous driving perception, transitioning the field from narrow, task-specific deep learning models to versatile, general-purpose architectures trained on vast, diverse datasets. This survey examines how these models address critical challenges in autonomous perception, including limitations in generalization, scalability, and robustness to distributional shifts. The survey introduces a novel taxonomy structured around four essential capabilities for robust performance in dynamic driving environments: generalized knowledge, spatial understanding, multi-sensor robustness, and temporal reasoning. For each capability, the survey elucidates its significance and comprehensively reviews cutting-edge approaches. Diverging from traditional method-centric surveys, our unique framework prioritizes conceptual design principles, providing a capability-driven guide for model development and clearer insights into foundational aspects. We conclude by discussing key challenges, particularly those associated with the integration of these capabilities into real-time, scalable systems, and broader deployment challenges related to computational demands and ensuring model reliability against issues like hallucinations and out-of-distribution failures. The survey also outlines crucial future research directions to enable the safe and effective deployment of foundation models in autonomous driving systems.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2554-2582"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210033","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 : 2025-09-01DOI: 10.1109/OJVT.2025.3604561
Martin Zavrel;Pavel Drabek;Vladimir Kindl;Michal Frivaldsky
This article presents the design and development of a low-level control approach for a wireless charger intended for modern electro-mobility (e-mobility) applications. It outlines future trends in the e-mobility market and technical advancements in wireless power transfer (WPT) systems, aligning them with the proposed wireless charger design methodology. A key advantage of the proposed solution is its full competitiveness with conventional wired charging stations. The primary focus of this work is the control system design for the wireless charging station (WCS), which features active and optimal load impedance tracking. This tracking adapts to varying load parameters (such as battery characteristics) and misalignments in coupling elements, ensuring maximum power transfer efficiency and high-power transfer controlled by supply voltage. The system complies fully with the SAE J2954 standard for wireless charging in e-mobility. The developed test system achieves power transfer of up to 65 kW across an air gap of 15 to 25 cm, with an overall system efficiency exceeding 95.5%.
{"title":"Design of a 65-kW Wireless Charging Station Characterized by Optimal Load Impedance Tracking Control","authors":"Martin Zavrel;Pavel Drabek;Vladimir Kindl;Michal Frivaldsky","doi":"10.1109/OJVT.2025.3604561","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3604561","url":null,"abstract":"This article presents the design and development of a low-level control approach for a wireless charger intended for modern electro-mobility (e-mobility) applications. It outlines future trends in the e-mobility market and technical advancements in wireless power transfer (WPT) systems, aligning them with the proposed wireless charger design methodology. A key advantage of the proposed solution is its full competitiveness with conventional wired charging stations. The primary focus of this work is the control system design for the wireless charging station (WCS), which features active and optimal load impedance tracking. This tracking adapts to varying load parameters (such as battery characteristics) and misalignments in coupling elements, ensuring maximum power transfer efficiency and high-power transfer controlled by supply voltage. The system complies fully with the SAE J2954 standard for wireless charging in e-mobility. The developed test system achieves power transfer of up to 65 kW across an air gap of 15 to 25 cm, with an overall system efficiency exceeding 95.5%.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2462-2478"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11145950","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145110277","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 : 2025-08-28DOI: 10.1109/OJVT.2025.3603690
Yi Zhao;Mohammed El-Hajjar;Lie-Liang Yang
Future wireless communications are expected to support massive connectivity in various applications, such as massive Machine-Type Communications (mMTC) and different types of IoT networks, where many applications have the data traffic of sporadicnature. To support these kinds of applications, grant free multiple-access (GFMA) has been recognized to be more efficient thanthe conventional granted multiple access (GMA). However, due to sporadic transmission, GFMA faces the main challenges of User Activity Detection (UAD) and Channel Estimation (CE). To meet these challenges, in this paper, a multicarrier GFMA (MC-GFMA) system is introduced for supporting massive connectivity. A block-sparse signal model is derived, where the Expectation Maximization assisted Block Sparse Bayesian Learning (EM-BSBL) algorithm is employed to solve the joint UAD and CE problem. Furthermore, to augment the performance of EM-BSBL algorithm in GFMA systems, the statistical properties of the activity weights generated by EM-BSBL algorithm are investigated, showing that the activity weights follow closely the Gamma distribution. Then, using the Gamma modelling of the activity weights, the Neyman-Pearson (NP) method is considered for optimizing the threshold used for decision making in the EM-BSBL algorithm. Finally, the performance of GFMA systems is comprehensively studied by numerical simulations. Our results and analysis demonstrate that MC-GFMA is a feasible signalling scheme for supporting a massive number of users transmitting sporadic information. With the aid of the EM-BSBL algorithm enhanced by the NP-assisted threshold optimization, MC-GFMA is robust for operation in the communications environments where active users are random and the number of them is highly dynamic.
{"title":"Joint User Activity Detection and Channel Estimation in MC-GFMA Systems by Block Sparse Bayesian Learning With Threshold Optimization","authors":"Yi Zhao;Mohammed El-Hajjar;Lie-Liang Yang","doi":"10.1109/OJVT.2025.3603690","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3603690","url":null,"abstract":"Future wireless communications are expected to support massive connectivity in various applications, such as massive Machine-Type Communications (mMTC) and different types of IoT networks, where many applications have the data traffic of sporadicnature. To support these kinds of applications, grant free multiple-access (GFMA) has been recognized to be more efficient thanthe conventional granted multiple access (GMA). However, due to sporadic transmission, GFMA faces the main challenges of User Activity Detection (UAD) and Channel Estimation (CE). To meet these challenges, in this paper, a multicarrier GFMA (MC-GFMA) system is introduced for supporting massive connectivity. A block-sparse signal model is derived, where the Expectation Maximization assisted Block Sparse Bayesian Learning (EM-BSBL) algorithm is employed to solve the joint UAD and CE problem. Furthermore, to augment the performance of EM-BSBL algorithm in GFMA systems, the statistical properties of the activity weights generated by EM-BSBL algorithm are investigated, showing that the activity weights follow closely the Gamma distribution. Then, using the Gamma modelling of the activity weights, the Neyman-Pearson (NP) method is considered for optimizing the threshold used for decision making in the EM-BSBL algorithm. Finally, the performance of GFMA systems is comprehensively studied by numerical simulations. Our results and analysis demonstrate that MC-GFMA is a feasible signalling scheme for supporting a massive number of users transmitting sporadic information. With the aid of the EM-BSBL algorithm enhanced by the NP-assisted threshold optimization, MC-GFMA is robust for operation in the communications environments where active users are random and the number of them is highly dynamic.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2441-2458"},"PeriodicalIF":4.8,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11143207","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060960","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 : 2025-08-27DOI: 10.1109/OJVT.2025.3603417
An-Toan Nguyen;Binh-Minh Nguyen;João Pedro F. Trovão;Minh C. Ta
Multi-motor electric vehicles (MMEVs) present complex challenges for control and optimization due to the distribution of control actions and state variables across multiple subsystems and hierarchical levels. Although electric vehicle (EV) modeling has been widely studied, accurately capturing and optimizing the longitudinal energy efficiency and dynamic performance of MMEVs remains a significant challenge. This complexity is further increased by the presence of different motor types, such as induction motors (IMs) and permanent magnet synchronous motors (PMSMs), and various mechanical configurations in all-wheel drive systems. To address these issues, this paper proposes a global-local modeling framework that extends the Energetic Macroscopic Representation (EMR) methodology. The framework integrates detailed models of the electrical drive system with comprehensive mechanical subsystem modeling, including gearbox, differential, half-shafts, wheels, and tires. A global input power model links local control actions and state variables to overall energy flow, supporting a unified approach to longitudinal motion control and energy optimization. In contrast to conventional EMR-based models, the proposed framework explicitly incorporates driveline and tire dynamics, which significantly affect energy consumption due to drivetrain losses and tire slip. The model is evaluated through two scenarios that assess the effects of drivetrain modeling and force distribution strategies. The results show improved control system performance and enhanced energy efficiency, supporting future advancements in longitudinal dynamics modeling for MMEV.
{"title":"An Integrated Modeling Framework for Motion Control and Energy Management in Multi-Motor Electric Vehicles","authors":"An-Toan Nguyen;Binh-Minh Nguyen;João Pedro F. Trovão;Minh C. Ta","doi":"10.1109/OJVT.2025.3603417","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3603417","url":null,"abstract":"Multi-motor electric vehicles (MMEVs) present complex challenges for control and optimization due to the distribution of control actions and state variables across multiple subsystems and hierarchical levels. Although electric vehicle (EV) modeling has been widely studied, accurately capturing and optimizing the longitudinal energy efficiency and dynamic performance of MMEVs remains a significant challenge. This complexity is further increased by the presence of different motor types, such as induction motors (IMs) and permanent magnet synchronous motors (PMSMs), and various mechanical configurations in all-wheel drive systems. To address these issues, this paper proposes a global-local modeling framework that extends the Energetic Macroscopic Representation (EMR) methodology. The framework integrates detailed models of the electrical drive system with comprehensive mechanical subsystem modeling, including gearbox, differential, half-shafts, wheels, and tires. A global input power model links local control actions and state variables to overall energy flow, supporting a unified approach to longitudinal motion control and energy optimization. In contrast to conventional EMR-based models, the proposed framework explicitly incorporates driveline and tire dynamics, which significantly affect energy consumption due to drivetrain losses and tire slip. The model is evaluated through two scenarios that assess the effects of drivetrain modeling and force distribution strategies. The results show improved control system performance and enhanced energy efficiency, supporting future advancements in longitudinal dynamics modeling for MMEV.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2479-2493"},"PeriodicalIF":4.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11142713","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141696","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：