An effective energy management strategy (EMS) is crucial to improve the energy efficiency of hybrid vehicles, especially for heavy-duty mining trucks. An energy management strategy based on a proximal policy optimization algorithm with mask layer and novel reward functions (PPO-MASK-NR) is proposed for hybrid electric mining trucks (HEMTs) with multi-planetary systems. This algorithm fundamentally avoids irrational exploration by an intelligent agent by incorporating a real-time mask layer, and it accelerates learning efficiency by suppressing the backward propagation of gradients for irrational actions. A universally designed reward function is applied to ensure the achievement of the correct final state of charge (SOC) value and the expansion of the SOC's exploration range. Finally, the generalization performance of the proposed algorithm is validated through new driving cycles, and its authenticity is confirmed through hardware-in-the-loop (HiL) testing. The simulation results show that within the selected training cycles, the proposed algorithm achieves 98% compared with the dynamic programming algorithm (DP). The proposed algorithm has an improvement of 11% and 5% in online applications for a new driving cycle compared to a rule-based technique (RB) and the equivalent fuel consumption minimization approach (ECMS), respectively.
{"title":"Real-Time Energy Management Based on Proximal Policy Optimization With Mask Layer for Hybrid Electric Mining Trucks","authors":"Xinxin Zhao;Menglei Liu;Jiaqi Li;Nasser Lashgarian Azad;Milad Farsi","doi":"10.1109/OJVT.2025.3620014","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3620014","url":null,"abstract":"An effective energy management strategy (EMS) is crucial to improve the energy efficiency of hybrid vehicles, especially for heavy-duty mining trucks. An energy management strategy based on a proximal policy optimization algorithm with mask layer and novel reward functions (PPO-MASK-NR) is proposed for hybrid electric mining trucks (HEMTs) with multi-planetary systems. This algorithm fundamentally avoids irrational exploration by an intelligent agent by incorporating a real-time mask layer, and it accelerates learning efficiency by suppressing the backward propagation of gradients for irrational actions. A universally designed reward function is applied to ensure the achievement of the correct final state of charge (SOC) value and the expansion of the SOC's exploration range. Finally, the generalization performance of the proposed algorithm is validated through new driving cycles, and its authenticity is confirmed through hardware-in-the-loop (HiL) testing. The simulation results show that within the selected training cycles, the proposed algorithm achieves 98% compared with the dynamic programming algorithm (DP). The proposed algorithm has an improvement of 11% and 5% in online applications for a new driving cycle compared to a rule-based technique (RB) and the equivalent fuel consumption minimization approach (ECMS), respectively.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2988-2999"},"PeriodicalIF":4.8,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11198896","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560674","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 : 2025-10-08DOI: 10.1109/OJVT.2025.3619421
Daniel Dinis;João Guerreiro;Marko Beko;Rui Dinis;Risto Wichman
Most of the signals widely employed in wireless communications can have significant envelope fluctuations that make them very prone to nonlinear (NL) effects, leading to significant performance degradation when conventional receivers (designed for ideal linear conditions) are utilized. However, if optimum maximum likelihood (ML) receivers are employed, NL effects do not necessarily lead to performance degradation, and can actually outperform the corresponding linear systems. This paper presents a general framework for studying the impact of NL effects on a wide class of block transmission techniques with blockwise pre-processing where the transmitted signals have significant envelope fluctuations. This class includes many of the widely employed transmission techniques like Orthogonal Frequency Division Multiplexing (OFDM), Multiple-Input Multiple-Output (MIMO), Single Carier-Frequency Domain Equalization (SC-FDE) and Code Division Multiple Access (CDMA). Our approach provides accurate bounds on the achievable performance of optimum receivers, and enables the design of iterative receivers able to approach that optimum performance with complexity much lower than the corresponding optimum ML receivers.
{"title":"Quasi-Optimum Detection for a Wide Class of Digital Signals With Strong Nonlinear Distortion Effects","authors":"Daniel Dinis;João Guerreiro;Marko Beko;Rui Dinis;Risto Wichman","doi":"10.1109/OJVT.2025.3619421","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3619421","url":null,"abstract":"Most of the signals widely employed in wireless communications can have significant envelope fluctuations that make them very prone to nonlinear (NL) effects, leading to significant performance degradation when conventional receivers (designed for ideal linear conditions) are utilized. However, if optimum maximum likelihood (ML) receivers are employed, NL effects do not necessarily lead to performance degradation, and can actually outperform the corresponding linear systems. This paper presents a general framework for studying the impact of NL effects on a wide class of block transmission techniques with blockwise pre-processing where the transmitted signals have significant envelope fluctuations. This class includes many of the widely employed transmission techniques like Orthogonal Frequency Division Multiplexing (OFDM), Multiple-Input Multiple-Output (MIMO), Single Carier-Frequency Domain Equalization (SC-FDE) and Code Division Multiple Access (CDMA). Our approach provides accurate bounds on the achievable performance of optimum receivers, and enables the design of iterative receivers able to approach that optimum performance with complexity much lower than the corresponding optimum ML receivers.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2842-2856"},"PeriodicalIF":4.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11196955","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145456068","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 : 2025-10-07DOI: 10.1109/OJVT.2025.3618855
Xinxing Ren;Chun Sing Lai;Gareth Taylor;Yujie Yuan
Eco-driving research has grown significantly over the past decade, increasingly incorporating real-world traffic and road conditions such as road gradients, lane changes, and queue effects. However, most existing studies that account for queue effects are limited to single-lane scenarios, without considering lane-merging disturbances, and can only estimate queue length or discharge time within restricted regions. To address these limitations, this paper proposes a novel deep reinforcement learning (DRL) based eco-driving algorithm that simultaneously considers on-the-fly queue dissipation time estimation and lane-merging disturbances. The approach integrates a practical and cost-effective navigation-app-based traffic data sharing framework with a data-driven dissipation time estimation model, enabling the reinforcement learning agent to continuously receive accurate modified reference speeds that reflect both queueing and merging vehicle effects. Five comprehensive case studies, benchmarked against conventional and state-of-the-art eco-driving methods, were conducted to evaluate the effectiveness of the proposed approach. Simulation results demonstrate that the proposed method consistently achieves the best energy performance across all scenarios, reducing energy consumption by an average of 37.5% compared with the Intelligent Driver Model (IDM) baseline.
{"title":"Eco-Driving With Deep Reinforcement Learning at Signalized Intersections Considering On-the-Fly Queue Dissipation Estimation and Lane-Merging Disturbances","authors":"Xinxing Ren;Chun Sing Lai;Gareth Taylor;Yujie Yuan","doi":"10.1109/OJVT.2025.3618855","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3618855","url":null,"abstract":"Eco-driving research has grown significantly over the past decade, increasingly incorporating real-world traffic and road conditions such as road gradients, lane changes, and queue effects. However, most existing studies that account for queue effects are limited to single-lane scenarios, without considering lane-merging disturbances, and can only estimate queue length or discharge time within restricted regions. To address these limitations, this paper proposes a novel deep reinforcement learning (DRL) based eco-driving algorithm that simultaneously considers on-the-fly queue dissipation time estimation and lane-merging disturbances. The approach integrates a practical and cost-effective navigation-app-based traffic data sharing framework with a data-driven dissipation time estimation model, enabling the reinforcement learning agent to continuously receive accurate modified reference speeds that reflect both queueing and merging vehicle effects. Five comprehensive case studies, benchmarked against conventional and state-of-the-art eco-driving methods, were conducted to evaluate the effectiveness of the proposed approach. Simulation results demonstrate that the proposed method consistently achieves the best energy performance across all scenarios, reducing energy consumption by an average of 37.5% compared with the Intelligent Driver Model (IDM) baseline.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2789-2803"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11195193","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352069","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 : 2025-10-03DOI: 10.1109/OJVT.2025.3617526
Joaquín M. Sánchez-Martín;Matías Toril;Carolina Gijón;Salvador Luna-Ramírez;Celia García-Corrales
In 5G cellular systems, network densification is a key technique to cope with the strong increase of traffic volume in mobile communications. The deployment of indoor small cells offloads macrocells at the cost of increasing network complexity. In this work, a methodology for planning Centralized-Radio Access Networks (C-RANs) comprising macrocells and small cells is proposed. The aim is to group Radio Remote Heads (RRH) into Base Band Unit (BBU) pools and coordination sets (a.k.a. BBU planning) to maximize user throughput. To this end, the above assignment problem is formulated as a graph partitioning problem, which is solved by graph theory algorithms. Method assessment is carried out by using a radio planning tool that implements a novel analytical system model to check spectral efficiency and resource allocation. Different BBU planning strategies are first compared, and the impact of Inter-Cell Interference Coordination (ICIC), Coordinated Multi-Point Transmission/Reception (CoMP) and Multi-Connectivity (MC) on network performance with the best BBU plan is then assessed under different system loads and coordination constraints. Results show that the selection of a proper graph partitioning scheme for RRH clustering is key to ensure that the above schemes improve system capacity in heterogeneous environments.
{"title":"Remote Radio Head Clustering in 5G HetNets by Graph Partitioning","authors":"Joaquín M. Sánchez-Martín;Matías Toril;Carolina Gijón;Salvador Luna-Ramírez;Celia García-Corrales","doi":"10.1109/OJVT.2025.3617526","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3617526","url":null,"abstract":"In 5G cellular systems, network densification is a key technique to cope with the strong increase of traffic volume in mobile communications. The deployment of indoor small cells offloads macrocells at the cost of increasing network complexity. In this work, a methodology for planning Centralized-Radio Access Networks (C-RANs) comprising macrocells and small cells is proposed. The aim is to group Radio Remote Heads (RRH) into Base Band Unit (BBU) pools and coordination sets (a.k.a. BBU planning) to maximize user throughput. To this end, the above assignment problem is formulated as a graph partitioning problem, which is solved by graph theory algorithms. Method assessment is carried out by using a radio planning tool that implements a novel analytical system model to check spectral efficiency and resource allocation. Different BBU planning strategies are first compared, and the impact of Inter-Cell Interference Coordination (ICIC), Coordinated Multi-Point Transmission/Reception (CoMP) and Multi-Connectivity (MC) on network performance with the best BBU plan is then assessed under different system loads and coordination constraints. Results show that the selection of a proper graph partitioning scheme for RRH clustering is key to ensure that the above schemes improve system capacity in heterogeneous environments.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2876-2890"},"PeriodicalIF":4.8,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11192674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145456069","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}
Perception systems play a crucial role in real-time decision-making in intelligent transportation, particularly in uncertain traffic. Challenges such as dynamic movement, unpredictability, occlusion, and ambiguous interactions necessitate the development of adaptive detection and tracking frameworks. To address these issues, we present the uncertainty mixed-traffic (UMT-Dataset), an extension of the MXT-Dataset, tailored to address dynamic object behavior in mixed-traffic environments. We also propose the YOLOv10-UMT framework, which integrates YOLOv10n with a modified bag-of-tricks for re-identification + simple online and real-time tracking (BoT-SORT) algorithm enhanced by an extended Kalman filter (EKF) and a noise scaling adaptive (NSA) mechanism. This method enhances BoT-SORT's ability to estimate object positions more reliably under uncertain conditions. The EKF integration can handle nonlinear trajectories more accurately, whereas the NSA can adaptively adjust measurements for detection. Experimental results show that integrating YOLOv10n with modified BoT-SORT using EKF+NSA significantly improves the precision and efficiency. This method achieves HOTA 42.064, MOTA 22.868, and IDF1 46.324 with an inference time of 2668 ± 37.01 ms. Evaluations on datasets of varying sizes (1600, 2000, and 2500 images) further confirm the robustness of EKF+NSA, supported by 95% confidence intervals (CI), inference time standard deviations, and computational cost analysis. Additionally, YOLOv10n trained on the UMT-Dataset outperformed YOLOv9t and YOLOv11n, achieving mAP@0.5 of 0.858, precision 0.868, recall 0.781, F1-score 0.82, and speed of 555.56 FPS. The proposed method is effective for adaptive detection and tracking in uncertain traffic, prioritizing accuracy, time efficiency, and contributing to a reliable perception module in real-world intelligent transportation systems.
{"title":"Real-Time Detection and Tracking Framework Using Extended Kalman Filter BoT-SORT in Uncertainty Mixed-Traffic","authors":"Mirshal Arief;Afdhal Afdhal;Khairun SaddamI;Ramzi Adriman;Nasaruddin Nasaruddin","doi":"10.1109/OJVT.2025.3617470","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3617470","url":null,"abstract":"Perception systems play a crucial role in real-time decision-making in intelligent transportation, particularly in uncertain traffic. Challenges such as dynamic movement, unpredictability, occlusion, and ambiguous interactions necessitate the development of adaptive detection and tracking frameworks. To address these issues, we present the uncertainty mixed-traffic (UMT-Dataset), an extension of the MXT-Dataset, tailored to address dynamic object behavior in mixed-traffic environments. We also propose the YOLOv10-UMT framework, which integrates YOLOv10n with a modified bag-of-tricks for re-identification + simple online and real-time tracking (BoT-SORT) algorithm enhanced by an extended Kalman filter (EKF) and a noise scaling adaptive (NSA) mechanism. This method enhances BoT-SORT's ability to estimate object positions more reliably under uncertain conditions. The EKF integration can handle nonlinear trajectories more accurately, whereas the NSA can adaptively adjust measurements for detection. Experimental results show that integrating YOLOv10n with modified BoT-SORT using EKF+NSA significantly improves the precision and efficiency. This method achieves HOTA 42.064, MOTA 22.868, and IDF1 46.324 with an inference time of 2668 <bold>±</b> 37.01 ms. Evaluations on datasets of varying sizes (1600, 2000, and 2500 images) further confirm the robustness of EKF+NSA, supported by 95% confidence intervals (CI), inference time standard deviations, and computational cost analysis. Additionally, YOLOv10n trained on the UMT-Dataset outperformed YOLOv9t and YOLOv11n, achieving mAP@0.5 of 0.858, precision 0.868, recall 0.781, F1-score 0.82, and speed of 555.56 FPS. The proposed method is effective for adaptive detection and tracking in uncertain traffic, prioritizing accuracy, time efficiency, and contributing to a reliable perception module in real-world intelligent transportation systems.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2804-2827"},"PeriodicalIF":4.8,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11192652","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405249","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 : 2025-10-01DOI: 10.1109/OJVT.2025.3616195
Olaf Borsboom;Mauro Salazar;Theo Hofman
In early phases of electric vehicle development, powertrain design requires a system-level approach with sufficiently accurate component models. This paper presents optimization frameworks for electric motor sizing and transmission gear ratio selection, focusing on electric motor modeling. Specifically, we express motor losses and operational limits as functions of scaling factors, which proportionally adjust a reference design in axial and radial directions. Thereby we apply surrogate modeling techniques in three ways on a computationally expensive high-fidelity motor design tool. The first framework integrates Bayesian optimization with the high-fidelity tool and drive cycle simulation in the loop. The second and third frameworks use scalable motor models in a static optimization problem, employing convex and Gaussian radial basis function surrogate models, respectively. We demonstrate these methods in a case study for an electric crossover SUV, optimizing motor size and gear ratio while meeting performance requirements. Validation shows that the drift in energy consumption below 0.6 %. The resulting motor designs and gear ratios differ minimally across frameworks, with only a 0.3 % energy consumption improvement favoring the radial basis function model. This suggests that all three frameworks provide effective optimization strategies with little deviations in the design and the energy efficiency between the frameworks.
{"title":"Design Optimization of Electric Vehicle Drivetrains Using Surrogate Modeling Frameworks","authors":"Olaf Borsboom;Mauro Salazar;Theo Hofman","doi":"10.1109/OJVT.2025.3616195","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3616195","url":null,"abstract":"In early phases of electric vehicle development, powertrain design requires a system-level approach with sufficiently accurate component models. This paper presents optimization frameworks for electric motor sizing and transmission gear ratio selection, focusing on electric motor modeling. Specifically, we express motor losses and operational limits as functions of scaling factors, which proportionally adjust a reference design in axial and radial directions. Thereby we apply surrogate modeling techniques in three ways on a computationally expensive high-fidelity motor design tool. The first framework integrates Bayesian optimization with the high-fidelity tool and drive cycle simulation in the loop. The second and third frameworks use scalable motor models in a static optimization problem, employing convex and Gaussian radial basis function surrogate models, respectively. We demonstrate these methods in a case study for an electric crossover SUV, optimizing motor size and gear ratio while meeting performance requirements. Validation shows that the drift in energy consumption below 0.6 %. The resulting motor designs and gear ratios differ minimally across frameworks, with only a 0.3 % energy consumption improvement favoring the radial basis function model. This suggests that all three frameworks provide effective optimization strategies with little deviations in the design and the energy efficiency between the frameworks.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2776-2788"},"PeriodicalIF":4.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11189072","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145351973","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 proposes a federated reinforcement learning (FRL) framework for optimizing energy efficiency (EE) and Age of Information (AoI) in device-to-device (D2D) and Internet of Things (IoT) networks. The model leverages simultaneous wireless information and power transfer (SWIPT) with heterogeneous energy harvesting mechanisms—time switching (TS) for D2D users and power splitting (PS) for IoT devices. The objective is to maximize EE while satisfying constraints on data rate, AoI, power transmission, spectrum sharing, and time allocation. The resulting non-convex mixed-integer nonlinear programming problem is addressed using an FRL approach, where a software-defined network controller coordinates distributed agents to optimize resource allocation while preserving data privacy. Simulations demonstrate that the proposed framework achieves up to 25% higher EE and maintains AoI below critical thresholds compared to baseline methods, offering a scalable solution for energy-constrained, time-sensitive communication systems.
{"title":"Federated Reinforcement Learning for Energy-Efficient D2D-IoT Networks With AoI Awareness","authors":"Parisa Parhizgar;Mehdi Mahdavi;Mohammad Reza Ahmadzadeh;Melike Erol-Kantarci","doi":"10.1109/OJVT.2025.3615958","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3615958","url":null,"abstract":"This paper proposes a federated reinforcement learning (FRL) framework for optimizing energy efficiency (EE) and Age of Information (AoI) in device-to-device (D2D) and Internet of Things (IoT) networks. The model leverages simultaneous wireless information and power transfer (SWIPT) with heterogeneous energy harvesting mechanisms—time switching (TS) for D2D users and power splitting (PS) for IoT devices. The objective is to maximize EE while satisfying constraints on data rate, AoI, power transmission, spectrum sharing, and time allocation. The resulting non-convex mixed-integer nonlinear programming problem is addressed using an FRL approach, where a software-defined network controller coordinates distributed agents to optimize resource allocation while preserving data privacy. Simulations demonstrate that the proposed framework achieves up to 25% higher EE and maintains AoI below critical thresholds compared to baseline methods, offering a scalable solution for energy-constrained, time-sensitive communication systems.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2828-2841"},"PeriodicalIF":4.8,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11184739","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405252","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 : 2025-09-23DOI: 10.1109/OJVT.2025.3607009
Giambattista Gruosso;Alain Bouscayrol;Lucia Gauchia;Davide De Simone;Lei Zhang;Hang Zhao
{"title":"Guest Editorial: Special Section on the Vehicular Power Propulsion Conference 2025","authors":"Giambattista Gruosso;Alain Bouscayrol;Lucia Gauchia;Davide De Simone;Lei Zhang;Hang Zhao","doi":"10.1109/OJVT.2025.3607009","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3607009","url":null,"abstract":"","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2459-2461"},"PeriodicalIF":4.8,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11176788","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141611","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 : 2025-09-22DOI: 10.1109/OJVT.2025.3613141
Mena Nagiub;Thorsten Beuth;Ganesh Sistu;Heinrich Gotzig;Ciar치n Eising
Indirect time-of-flight (iToF) LiDAR sensors have their technical challenges. They are a viable alternative to direct time-of-flight (dToF) LiDAR sensors and cameras for near-field applications, particularly in autonomous vehicles and mobile robots. iToF LiDAR sensors face issues with depth range ambiguity. Many modern Deep Neural Network (DNN) computer vision models that run on graphics processing units can effectively address this problem. However, GPUs' high electrical energy consumption poses a significant challenge when integrated with battery-based embedded systems. Nonetheless, viable alternatives can provide sufficient computational power while maintaining a low electric power profile. One such option is the low-power ARM processor architecture, which is supported by single-instruction, multiple-data (SIMD) accelerators. In this paper, we go deep into the system architecture differences between GPUs and CPUs-integrated SIMD, exploring the potential use cases for running DNN models, identify which models are suitable for which architectures, propose methods for running the depth correction algorithm on such low-power platforms, discuss the challenges of these methods, and suggest ways to overcome them, thereby enabling the use of sensors in low-power applications. We pose several questions about the embedded deployment of DNN models and offer recommendations to address them. We were able to achieve a real-time depth correction rate at 10 frames per second at acceptable accuracy, with no need for GPUs on low-power ARM architecture Cortex-A76.
{"title":"Low Power Indirect Time of Flight Near Field LiDAR Depth Correction","authors":"Mena Nagiub;Thorsten Beuth;Ganesh Sistu;Heinrich Gotzig;Ciar치n Eising","doi":"10.1109/OJVT.2025.3613141","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3613141","url":null,"abstract":"Indirect time-of-flight (iToF) LiDAR sensors have their technical challenges. They are a viable alternative to direct time-of-flight (dToF) LiDAR sensors and cameras for near-field applications, particularly in autonomous vehicles and mobile robots. iToF LiDAR sensors face issues with depth range ambiguity. Many modern Deep Neural Network (DNN) computer vision models that run on graphics processing units can effectively address this problem. However, GPUs' high electrical energy consumption poses a significant challenge when integrated with battery-based embedded systems. Nonetheless, viable alternatives can provide sufficient computational power while maintaining a low electric power profile. One such option is the low-power ARM processor architecture, which is supported by single-instruction, multiple-data (SIMD) accelerators. In this paper, we go deep into the system architecture differences between GPUs and CPUs-integrated SIMD, exploring the potential use cases for running DNN models, identify which models are suitable for which architectures, propose methods for running the depth correction algorithm on such low-power platforms, discuss the challenges of these methods, and suggest ways to overcome them, thereby enabling the use of sensors in low-power applications. We pose several questions about the embedded deployment of DNN models and offer recommendations to address them. We were able to achieve a real-time depth correction rate at 10 frames per second at acceptable accuracy, with no need for GPUs on low-power ARM architecture Cortex-A76.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2736-2760"},"PeriodicalIF":4.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11175510","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315363","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 : 2025-09-22DOI: 10.1109/OJVT.2025.3612973
Haoyan Chen;Zhijin Wen;Changbiao Lei
With the intensification of uncrewed aerial vehicle (UAV) “black flight” threat, the dynamic cooperative deployment of navigation spoofing jamming sites faces the triple challenges of integrity coverage, spoofing signal mutual interference suppression, and resource cost optimization. In this paper, we propose an intelligent deployment framework that breaks through the limitations of traditional algorithms of fixing the number of stations, fixing the radius, and optimizing only the location of stations. By constructing a multi-objective optimization model, we innovatively design a hybrid optimization mechanism that includes velocity-position update with local-best-driven, site-adaptive maintenance, and directed mutation. Among them, the local-best-driven module generates particle motion gradients through site-level dual-objective evaluation to solve the global guidance failure problem in dynamic scenarios; the site-adaptive maintenance module achieves site-level dynamic optimization through the judgement of site absence and redundancy; and the directed mutation module further optimizes the redundant resources through the transformation of inefficient sites. Simulation results demonstrate that this method significantly improves the reliability and economy of the deployment of the active protection system in the complex electromagnetic environment and provides theoretical support for the construction of adaptive protection networks in critical areas such as cities and coastal areas.
{"title":"A Navigation Spoofing Source Deployment Algorithm for Critical Infrastructure Under Illegal UAV Threats Utilizing Site-Adaptive NS-MOPSO With Local-Best-Driven and Directed Mutation","authors":"Haoyan Chen;Zhijin Wen;Changbiao Lei","doi":"10.1109/OJVT.2025.3612973","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3612973","url":null,"abstract":"With the intensification of uncrewed aerial vehicle (UAV) “black flight” threat, the dynamic cooperative deployment of navigation spoofing jamming sites faces the triple challenges of integrity coverage, spoofing signal mutual interference suppression, and resource cost optimization. In this paper, we propose an intelligent deployment framework that breaks through the limitations of traditional algorithms of fixing the number of stations, fixing the radius, and optimizing only the location of stations. By constructing a multi-objective optimization model, we innovatively design a hybrid optimization mechanism that includes velocity-position update with local-best-driven, site-adaptive maintenance, and directed mutation. Among them, the local-best-driven module generates particle motion gradients through site-level dual-objective evaluation to solve the global guidance failure problem in dynamic scenarios; the site-adaptive maintenance module achieves site-level dynamic optimization through the judgement of site absence and redundancy; and the directed mutation module further optimizes the redundant resources through the transformation of inefficient sites. Simulation results demonstrate that this method significantly improves the reliability and economy of the deployment of the active protection system in the complex electromagnetic environment and provides theoretical support for the construction of adaptive protection networks in critical areas such as cities and coastal areas.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"2721-2735"},"PeriodicalIF":4.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11175393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315333","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：