Pub Date : 2024-10-16DOI: 10.1109/OJITS.2024.3481643
Mahdi Razzaghpour;Babak Ebrahimi Soorchaei;Rodolfo Valiente;Yaser P. Fallah
Investigating Vehicle-to-everything (V2X) communication, we dive into the concept of vehicle platoons, a key innovation in transport systems, introducing a new era of cooperative driving. This new approach is designed to enhance fuel efficiency and improve overall traffic flow. Crucially, the success of this system relies on keeping vehicles at closely monitored distances, particularly at high speeds, which depends on rapid and reliable data exchange among vehicles through a wireless communication channel that is intrinsically unstable. The possibility of improving platoon efficiency through wireless data exchange is clear, but addressing network issues such as data loss and delays is crucial. These problems can compromise platoon functionality and need careful handling for real-world applications. Present platooning models also struggle with forming ‘long’ platoons with multiple vehicles due to the limited range of Vehicle-to-Vehicle (V2V) communication. Quick and efficient traffic information sharing is crucial to ensure vehicles have adequate time to respond. Given the safety-critical nature of these communications, both reliability and ultra-low latency are essential, particularly in platooning contexts. To address these challenges, we suggest a distance-based, network-aware relaying policy specifically for long platoons of connected vehicles. The results of our simulations indicate that this relaying approach significantly decreases communication breakdowns and narrows the error gap between vehicles, all achieved with only a slight increase in computational demand.
{"title":"Mass Platooning: Information Networking Structures for Long Platoons of Connected Vehicles","authors":"Mahdi Razzaghpour;Babak Ebrahimi Soorchaei;Rodolfo Valiente;Yaser P. Fallah","doi":"10.1109/OJITS.2024.3481643","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3481643","url":null,"abstract":"Investigating Vehicle-to-everything (V2X) communication, we dive into the concept of vehicle platoons, a key innovation in transport systems, introducing a new era of cooperative driving. This new approach is designed to enhance fuel efficiency and improve overall traffic flow. Crucially, the success of this system relies on keeping vehicles at closely monitored distances, particularly at high speeds, which depends on rapid and reliable data exchange among vehicles through a wireless communication channel that is intrinsically unstable. The possibility of improving platoon efficiency through wireless data exchange is clear, but addressing network issues such as data loss and delays is crucial. These problems can compromise platoon functionality and need careful handling for real-world applications. Present platooning models also struggle with forming ‘long’ platoons with multiple vehicles due to the limited range of Vehicle-to-Vehicle (V2V) communication. Quick and efficient traffic information sharing is crucial to ensure vehicles have adequate time to respond. Given the safety-critical nature of these communications, both reliability and ultra-low latency are essential, particularly in platooning contexts. To address these challenges, we suggest a distance-based, network-aware relaying policy specifically for long platoons of connected vehicles. The results of our simulations indicate that this relaying approach significantly decreases communication breakdowns and narrows the error gap between vehicles, all achieved with only a slight increase in computational demand.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"740-755"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720084","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679263","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 : 2024-10-14DOI: 10.1109/OJITS.2024.3479716
Seungyoung Park;Duksoo Kim;Seokwoo Lee
In this paper, we address the limitations of existing deep learning (DL) methods for local misbehavior detection (LMBD) in vehicle-to-everything (V2X) communication systems by proposing an approach that combines rule-based and DL-based techniques. Conventional DL-based methods at roadside units (RSUs) struggle with forwarding basic safety messages (BSMs) received from every vehicle to centralized locations and preprocessing them, which leads to considerable time delays. To overcome these challenges, our approach leveraged multi-access edge computing (MEC) connected to RSU to decentralize the processing workload, considerably reducing latency and resource consumption. Specifically, we implemented a system where RSUs directly receive and forward BSMs to the MEC server, bypassing traditional deduplication and sorting processes at the centralized server. However, due to the fixed locations of RSUs, they often receive only truncated sequences of BSMs from passing vehicles, which necessitates LMBD on these incomplete datasets. To mitigate the performance degradation of DL-based anomaly detection in truncated sequences, we integrated a rule-based method performed for single or two consecutively received BSMs. Simulation results demonstrated that this combined rule-based pre-screening with DL analysis effectively improves the overall detection performances.
{"title":"Enhancing V2X Security Through Combined Rule-Based and DL-Based Local Misbehavior Detection in Roadside Units","authors":"Seungyoung Park;Duksoo Kim;Seokwoo Lee","doi":"10.1109/OJITS.2024.3479716","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3479716","url":null,"abstract":"In this paper, we address the limitations of existing deep learning (DL) methods for local misbehavior detection (LMBD) in vehicle-to-everything (V2X) communication systems by proposing an approach that combines rule-based and DL-based techniques. Conventional DL-based methods at roadside units (RSUs) struggle with forwarding basic safety messages (BSMs) received from every vehicle to centralized locations and preprocessing them, which leads to considerable time delays. To overcome these challenges, our approach leveraged multi-access edge computing (MEC) connected to RSU to decentralize the processing workload, considerably reducing latency and resource consumption. Specifically, we implemented a system where RSUs directly receive and forward BSMs to the MEC server, bypassing traditional deduplication and sorting processes at the centralized server. However, due to the fixed locations of RSUs, they often receive only truncated sequences of BSMs from passing vehicles, which necessitates LMBD on these incomplete datasets. To mitigate the performance degradation of DL-based anomaly detection in truncated sequences, we integrated a rule-based method performed for single or two consecutively received BSMs. Simulation results demonstrated that this combined rule-based pre-screening with DL analysis effectively improves the overall detection performances.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"656-668"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715733","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517895","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 : 2024-10-14DOI: 10.1109/OJITS.2024.3481328
Mehmet Kiraz;Fikret Sivrikaya;Sahin Albayrak
The progress towards fully autonomous mobility is significantly impacted by the integration of evolving technologies in connected and automated mobility (CAM). Connected and automated vehicles (CAVs) have the potential to revolutionize our transportation system by improving efficiency, safety, and environmental sustainability. Automated shuttles and public buses, smart traffic signals, intelligent passenger cars, and smart roundabouts are just a few examples of technologies that are being planned and actively researched for integration into transportation systems. Sensors are essential in making this possible. This article provides a structured overview of research on the selection and positioning of sensors on- and off-vehicle to achieve cooperative, connected, and automated mobility. The general integration and usage of sensors in vehicles and infrastructure is described, a detailed taxonomy of the examined research is provided, and future research directions are presented, involving solutions for quantification of sensor performance and addressing current trends. The findings of this article also highlight numerous challenges in creating a universal framework, the lack of application of novel machine learning methods, and the complexity of modeling multi-sensor settings.
{"title":"A Survey on Sensor Selection and Placement for Connected and Automated Mobility","authors":"Mehmet Kiraz;Fikret Sivrikaya;Sahin Albayrak","doi":"10.1109/OJITS.2024.3481328","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3481328","url":null,"abstract":"The progress towards fully autonomous mobility is significantly impacted by the integration of evolving technologies in connected and automated mobility (CAM). Connected and automated vehicles (CAVs) have the potential to revolutionize our transportation system by improving efficiency, safety, and environmental sustainability. Automated shuttles and public buses, smart traffic signals, intelligent passenger cars, and smart roundabouts are just a few examples of technologies that are being planned and actively researched for integration into transportation systems. Sensors are essential in making this possible. This article provides a structured overview of research on the selection and positioning of sensors on- and off-vehicle to achieve cooperative, connected, and automated mobility. The general integration and usage of sensors in vehicles and infrastructure is described, a detailed taxonomy of the examined research is provided, and future research directions are presented, involving solutions for quantification of sensor performance and addressing current trends. The findings of this article also highlight numerous challenges in creating a universal framework, the lack of application of novel machine learning methods, and the complexity of modeling multi-sensor settings.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"692-710"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716737","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555120","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 : 2024-10-11DOI: 10.1109/OJITS.2024.3479098
Aizaz Sharif;Dusica Marijan
Autonomous vehicles are advanced driving systems that revolutionize transportation, but their vulnerability to adversarial attacks poses significant safety risks. Consider a scenario in which a slight perturbation in sensor data causes an autonomous vehicle to fail unexpectedly, potentially leading to accidents. Current testing methods often rely on computationally expensive active learning techniques to identify such vulnerabilities. Rather than actively training complex adversaries by interacting with the environment, there is a need to first intelligently find and reduce the search space to only those states where autonomous vehicles are found to be less confident. In this paper, we propose a black-box testing framework ReMAV that uses offline trajectories first to efficiently identify weaknesses of autonomous vehicles without the need for active interaction. To this end, we introduce a three-step methodology which i) uses offline state action pairs of any autonomous vehicle under test, ii) builds an abstract behavior representation using our designed reward modeling technique to analyze states with uncertain driving decisions, and iii) uses a disturbance model for minimal perturbation attacks where the driving decisions are less confident. Our reward modeling creates a behavior representation that highlights regions of likely uncertain autonomous vehicle behavior, even when performance seems adequate. This enables efficient testing without computationally expensive active adversarial learning. We evaluated ReMAV in a high-fidelity urban driving simulator across various single- and multi-agent scenarios. The results show substantial increases in failure events compared to the standard behavior of autonomous vehicles: 35% in vehicle collisions, 23% in road object collisions, 48% in pedestrian collisions, and 50% in off-road steering events. ReMAV outperforms two baselines and previous testing frameworks in effectiveness, efficiency, and speed of identifying failures. This demonstrates ReMAV’s capability to efficiently expose autonomous vehicle weaknesses using simple perturbation models.
{"title":"ReMAV: Reward Modeling of Autonomous Vehicles for Finding Likely Failure Events","authors":"Aizaz Sharif;Dusica Marijan","doi":"10.1109/OJITS.2024.3479098","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3479098","url":null,"abstract":"Autonomous vehicles are advanced driving systems that revolutionize transportation, but their vulnerability to adversarial attacks poses significant safety risks. Consider a scenario in which a slight perturbation in sensor data causes an autonomous vehicle to fail unexpectedly, potentially leading to accidents. Current testing methods often rely on computationally expensive active learning techniques to identify such vulnerabilities. Rather than actively training complex adversaries by interacting with the environment, there is a need to first intelligently find and reduce the search space to only those states where autonomous vehicles are found to be less confident. In this paper, we propose a black-box testing framework ReMAV that uses offline trajectories first to efficiently identify weaknesses of autonomous vehicles without the need for active interaction. To this end, we introduce a three-step methodology which i) uses offline state action pairs of any autonomous vehicle under test, ii) builds an abstract behavior representation using our designed reward modeling technique to analyze states with uncertain driving decisions, and iii) uses a disturbance model for minimal perturbation attacks where the driving decisions are less confident. Our reward modeling creates a behavior representation that highlights regions of likely uncertain autonomous vehicle behavior, even when performance seems adequate. This enables efficient testing without computationally expensive active adversarial learning. We evaluated ReMAV in a high-fidelity urban driving simulator across various single- and multi-agent scenarios. The results show substantial increases in failure events compared to the standard behavior of autonomous vehicles: 35% in vehicle collisions, 23% in road object collisions, 48% in pedestrian collisions, and 50% in off-road steering events. ReMAV outperforms two baselines and previous testing frameworks in effectiveness, efficiency, and speed of identifying failures. This demonstrates ReMAV’s capability to efficiently expose autonomous vehicle weaknesses using simple perturbation models.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"669-691"},"PeriodicalIF":4.6,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714436","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518003","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}
In the context of vehicle trajectory planning, motion primitives are trajectories connecting pairs of boundary conditions. In autonomous racing, motion primitives have been used as computationally faster alternatives to model predictive control, for online obstacle avoidance. However, the existing motion primitive formulations are either simplified and suboptimal, or computationally expensive for accurate collision avoidance. This paper introduces new motion primitives for autonomous racing, aiming to accurately approximate the minimum-time vehicle trajectories while ensuring computational efficiency. We present a novel neural network, named PathPoly-NN, whose internal architecture is designed to learn the minimum-time vehicle path. Our motion primitives combine PathPoly-NN with a fast forward-backward method to compute the minimum-time speed profile. Compared to existing neural networks, PathPoly-NN generalizes better with small training sets, and it has better accuracy in approximating the minimum-time path. Additionally, our motion primitives have lower computational burden and higher accuracy than existing methods based on cubic polynomials and $G^{2}$ clothoid curves. Finally, the motion primitives of this paper achieve similar maneuver times as minimum-time economic nonlinear model predictive control (E-NMPC), but with significantly lower computational load (two orders of magnitude). The results open promising perspectives of applications in graph-based trajectory planners for autonomous racing.
{"title":"Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning","authors":"Mattia Piccinini;Simon Gottschalk;Matthias Gerdts;Francesco Biral","doi":"10.1109/OJITS.2024.3476540","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3476540","url":null,"abstract":"In the context of vehicle trajectory planning, motion primitives are trajectories connecting pairs of boundary conditions. In autonomous racing, motion primitives have been used as computationally faster alternatives to model predictive control, for online obstacle avoidance. However, the existing motion primitive formulations are either simplified and suboptimal, or computationally expensive for accurate collision avoidance. This paper introduces new motion primitives for autonomous racing, aiming to accurately approximate the minimum-time vehicle trajectories while ensuring computational efficiency. We present a novel neural network, named PathPoly-NN, whose internal architecture is designed to learn the minimum-time vehicle path. Our motion primitives combine PathPoly-NN with a fast forward-backward method to compute the minimum-time speed profile. Compared to existing neural networks, PathPoly-NN generalizes better with small training sets, and it has better accuracy in approximating the minimum-time path. Additionally, our motion primitives have lower computational burden and higher accuracy than existing methods based on cubic polynomials and \u0000<inline-formula> <tex-math>$G^{2}$ </tex-math></inline-formula>\u0000 clothoid curves. Finally, the motion primitives of this paper achieve similar maneuver times as minimum-time economic nonlinear model predictive control (E-NMPC), but with significantly lower computational load (two orders of magnitude). The results open promising perspectives of applications in graph-based trajectory planners for autonomous racing.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"642-655"},"PeriodicalIF":4.6,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10711857","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517858","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 : 2024-09-25DOI: 10.1109/OJITS.2024.3458288
Abel C. H. Chen
{"title":"Editorial Special Section on Machine Learning and Deep Learning for Transportation","authors":"Abel C. H. Chen","doi":"10.1109/OJITS.2024.3458288","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3458288","url":null,"abstract":"","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"603-607"},"PeriodicalIF":4.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10694683","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320439","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 : 2024-09-25DOI: 10.1109/OJITS.2024.3468021
David Brecht;Nils Gehrke;Tobias Kerbl;Niklas Krauss;Domagoj Majstorović;Florian Pfab;Maria-Magdalena Wolf;Frank Diermeyer
Teleoperation is a popular solution to remotely support highly automated vehicles through a human remote operator whenever a disengagement of the automated driving system is present. The remote operator wirelessly connects to the vehicle and solves the disengagement through support or substitution of automated driving functions and therefore enables the vehicle to resume automation. There are different approaches to support automated driving functions on various levels, commonly known as teleoperation concepts. A variety of teleoperation concepts is described in the literature, yet there has been no comprehensive and structured comparison of these concepts, and it is not clear what subset of teleoperation concepts is suitable to enable safe and efficient remote support of highly automated vehicles in a broad spectrum of disengagements. The following work establishes a basis for comparing teleoperation concepts through a literature overview on automated vehicle disengagements and on already conducted studies on the comparison of teleoperation concepts and metrics used to evaluate teleoperation performance. An evaluation of the teleoperation concepts is carried out in an expert workshop, comparing different teleoperation concepts using a selection of automated vehicle disengagement scenarios and metrics. Based on the workshop results, a set of three teleoperation concepts is derived that can be used to address a wide variety of automated vehicle disengagements in a safe and efficient way. This set includes the Remote Driving concept Shared Control as well as Collaborative Planning and Perception Modification from the Remote Assistance category.
{"title":"Evaluation of Teleoperation Concepts to Solve Automated Vehicle Disengagements","authors":"David Brecht;Nils Gehrke;Tobias Kerbl;Niklas Krauss;Domagoj Majstorović;Florian Pfab;Maria-Magdalena Wolf;Frank Diermeyer","doi":"10.1109/OJITS.2024.3468021","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3468021","url":null,"abstract":"Teleoperation is a popular solution to remotely support highly automated vehicles through a human remote operator whenever a disengagement of the automated driving system is present. The remote operator wirelessly connects to the vehicle and solves the disengagement through support or substitution of automated driving functions and therefore enables the vehicle to resume automation. There are different approaches to support automated driving functions on various levels, commonly known as teleoperation concepts. A variety of teleoperation concepts is described in the literature, yet there has been no comprehensive and structured comparison of these concepts, and it is not clear what subset of teleoperation concepts is suitable to enable safe and efficient remote support of highly automated vehicles in a broad spectrum of disengagements. The following work establishes a basis for comparing teleoperation concepts through a literature overview on automated vehicle disengagements and on already conducted studies on the comparison of teleoperation concepts and metrics used to evaluate teleoperation performance. An evaluation of the teleoperation concepts is carried out in an expert workshop, comparing different teleoperation concepts using a selection of automated vehicle disengagement scenarios and metrics. Based on the workshop results, a set of three teleoperation concepts is derived that can be used to address a wide variety of automated vehicle disengagements in a safe and efficient way. This set includes the Remote Driving concept Shared Control as well as Collaborative Planning and Perception Modification from the Remote Assistance category.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"629-641"},"PeriodicalIF":4.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10693593","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517894","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 : 2024-09-25DOI: 10.1109/OJITS.2024.3467222
Mahmoud Masoud
This research examines the intricate correlation between speed variation (celeration), a metric of driver behavior associated with vehicle control, and occurrences of running red lights. The study is based on a thorough analysis of a large dataset that includes a variety of parameters, such as exceeding speed limits, driver age, passenger count, weather, road condition, and temporal factors. Using cutting-edge machine learning methods like AdaBoost and Bagging, predictive models for red-light violations are painstakingly built, achieving remarkable validation accuracies of 90.4% and 90.1%, respectively. The study acknowledges the dataset’s limitations in capturing real-world traffic complexities while focusing on the effectiveness and trade-offs inherent in these methodologies. This emphasizes how important it is to have synchronized and thorough data sources to guarantee accurate representation. The research field is enhancing predictive modeling techniques and improving transportation safety by connecting celebration, speed variation patterns over time, with instances of red-light violations.
{"title":"Machine Learning-Based Modeling of Celeration for Predicting Red-Light Violations","authors":"Mahmoud Masoud","doi":"10.1109/OJITS.2024.3467222","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3467222","url":null,"abstract":"This research examines the intricate correlation between speed variation (celeration), a metric of driver behavior associated with vehicle control, and occurrences of running red lights. The study is based on a thorough analysis of a large dataset that includes a variety of parameters, such as exceeding speed limits, driver age, passenger count, weather, road condition, and temporal factors. Using cutting-edge machine learning methods like AdaBoost and Bagging, predictive models for red-light violations are painstakingly built, achieving remarkable validation accuracies of 90.4% and 90.1%, respectively. The study acknowledges the dataset’s limitations in capturing real-world traffic complexities while focusing on the effectiveness and trade-offs inherent in these methodologies. This emphasizes how important it is to have synchronized and thorough data sources to guarantee accurate representation. The research field is enhancing predictive modeling techniques and improving transportation safety by connecting celebration, speed variation patterns over time, with instances of red-light violations.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"608-616"},"PeriodicalIF":4.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10693532","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142376625","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 : 2024-09-12DOI: 10.1109/OJITS.2024.3458987
Hiroya Tanaka;Keita Funayama
Vehicular transportation design and control are critical topics of research. In two-dimensional topological systems, edge states exist at the boundary and support transport along the system edges. In this study, we demonstrate the directional flow of vehicular traffic in a hexagonal street network with a two-dimensional topological structure. We model the network structure by the topology of vertices and edges, and vehicular transport as a symmetric random walk between the vertices. We show that the proposed structure provides a macroscopically unidirectional traffic flow to a group of vehicles. Furthermore, we note that such unidirectional properties deteriorate because of the decay of the topological edge mode. To overcome the disappearance of traffic unidirectionarity, we propose a strategy for controlling the entry–exit timing of vehicles in a street network and confirm its effectiveness through simulations. The proposed vehicle management strategy sustainably allows unidirectional traffic in street networks. Our work thus provides a critical building block for designing and controlling transportation networks.
{"title":"Design of Unidirectional Vehicular Traffic With a Two-Dimensional Topological Structure","authors":"Hiroya Tanaka;Keita Funayama","doi":"10.1109/OJITS.2024.3458987","DOIUrl":"10.1109/OJITS.2024.3458987","url":null,"abstract":"Vehicular transportation design and control are critical topics of research. In two-dimensional topological systems, edge states exist at the boundary and support transport along the system edges. In this study, we demonstrate the directional flow of vehicular traffic in a hexagonal street network with a two-dimensional topological structure. We model the network structure by the topology of vertices and edges, and vehicular transport as a symmetric random walk between the vertices. We show that the proposed structure provides a macroscopically unidirectional traffic flow to a group of vehicles. Furthermore, we note that such unidirectional properties deteriorate because of the decay of the topological edge mode. To overcome the disappearance of traffic unidirectionarity, we propose a strategy for controlling the entry–exit timing of vehicles in a street network and confirm its effectiveness through simulations. The proposed vehicle management strategy sustainably allows unidirectional traffic in street networks. Our work thus provides a critical building block for designing and controlling transportation networks.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"581-588"},"PeriodicalIF":4.6,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10679227","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184247","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 : 2024-09-02DOI: 10.1109/OJITS.2024.3453666
Maria Drolence Mwanje;Omprakash Kaiwartya;Abdallah Naser
Position verification is essential in connected and autonomous vehicle technology to enable secure vehicle-to-everything communication. Previous attempts to verify location information have used specific hardware, traffic parameters, and statistical model-based techniques dependent on neighbouring vehicles and roadside infrastructure and whose judgements can be influenced by untrustworthy entities. Considering the back-and-forth communications during verification, these techniques are also unsuitable in the dynamic vehicular networking environment. In this context, this paper proposes a self-reliant trustbased position verification technique using dynamic geofencing, neural network, and Mamdani fuzzy logic controller. The method uses vehicular dynamics, such as distance between the sender and receiver vehicles, magnitude of the speed difference, and direction, to verify the trustworthiness of vehicle positions. An experimental analysis of a dataset of simulated driving scenarios in MATLAB demonstrates that the feedforward neural network records the highest direction classification performance at 99.8% in conjunction with the centroid defuzzification method. Subsequently, further quantitative analysis, including the Receiver Operating Characteristic curve with Area Under Curve and trust level distribution histograms, indicates that the suggested classification model outperforms a random classifier and effectively identifies false position data from the actual during trust computation.
{"title":"Position Verification in Connected Vehicles for Cyber Resilience Using Geofencing and Fuzzy Logic","authors":"Maria Drolence Mwanje;Omprakash Kaiwartya;Abdallah Naser","doi":"10.1109/OJITS.2024.3453666","DOIUrl":"10.1109/OJITS.2024.3453666","url":null,"abstract":"Position verification is essential in connected and autonomous vehicle technology to enable secure vehicle-to-everything communication. Previous attempts to verify location information have used specific hardware, traffic parameters, and statistical model-based techniques dependent on neighbouring vehicles and roadside infrastructure and whose judgements can be influenced by untrustworthy entities. Considering the back-and-forth communications during verification, these techniques are also unsuitable in the dynamic vehicular networking environment. In this context, this paper proposes a self-reliant trustbased position verification technique using dynamic geofencing, neural network, and Mamdani fuzzy logic controller. The method uses vehicular dynamics, such as distance between the sender and receiver vehicles, magnitude of the speed difference, and direction, to verify the trustworthiness of vehicle positions. An experimental analysis of a dataset of simulated driving scenarios in MATLAB demonstrates that the feedforward neural network records the highest direction classification performance at 99.8% in conjunction with the centroid defuzzification method. Subsequently, further quantitative analysis, including the Receiver Operating Characteristic curve with Area Under Curve and trust level distribution histograms, indicates that the suggested classification model outperforms a random classifier and effectively identifies false position data from the actual during trust computation.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"540-554"},"PeriodicalIF":4.6,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10663467","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184248","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：