IEEE Open Journal of Intelligent Transportation Systems最新文献

{"title":"Realtime Multispectral Pedestrian Detection With Visible and Far-Infrared Under Ambient Temperature Changing","authors":"Masato Okuda;Kota Yoshida;Takeshi Fujino","doi":"10.1109/OJITS.2024.3507917","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3507917","url":null,"abstract":"In recent intelligent transportation systems (ITS), it is important to recognize pedestrians and avoid collisions. Various sensors are used to detect pedestrians, and some research on pedestrian detection uses a visible light (RGB) camera and a far-infrared (FIR) camera. FIR cameras are significantly affected by ambient temperatures such as summer and winter. However, few studies have focused on this property when evaluating pedestrian detection accuracy. Therefore, this paper investigates the effect of temperature change in real-time multispectral pedestrian detection. We created an original dataset with three subsets, Hot, Intermediate, and Cold, and evaluated temperature effects by changing the subsets during training and testing. We first evaluated YOLOv8s-4ch, which simply extended the input layer of YOLOv8 from 3 channels of RGB to 4 channels of RGB-FIR. To further improve detection performance, we built a new model called YOLOv8s-2stream. This model has two backbones for RGB and FIR, and fuses their feature maps in each resolution. We found that the model trained on a specific temperature subset dropped the test accuracy in other subsets. On the other hand, when training using a Mix set covering all temperature sets (Hot, Inter., Cold), the model achieved the highest accuracy through all conditions. Moreover, our YOLOv8s-2stream has improved by 3.9 points of accuracy (AP@0.5:0.95) compared to YOLOv8s-4ch, and achieved 73 FPS inference speed on Jetson.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"797-809"},"PeriodicalIF":4.6,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10770282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844534","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}

{"title":"Predictor-Based CACC Design for Heterogeneous Vehicles With Distinct Input Delays","authors":"Amirhossein Samii;Nikolaos Bekiaris-Liberis","doi":"10.1109/OJITS.2024.3493461","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3493461","url":null,"abstract":"We develop a predictor-based cooperative adaptive cruise control (CACC) design for platoons with heterogeneous vehicles, whose dynamics are described by a third-order linear system subject to actuators delays, which are distinct for each individual vehicle. The design achieves individual vehicle stability, string stability, and zero, steady-state speed/spacing tracking errors, relying on a nominal, constant time headway (CTH)-type CACC design that achieves these specifications when all actuators’ delays are zero. This is achieved owing to the delay-compensating mechanism, of the CACC law introduced, for long delays and despite the fact that each vehicle’s dynamics are subject to different input delays, which makes the available predictor-feedback CACC designs inapplicable. The proofs of individual vehicle stability, string stability, and regulation rely on employment of an input-output approach on the frequency domain. We present consistent simulation results, including an example in which we employ real traffic data for the trajectory of the leading vehicle and an example via which we compare the performance of our design with the existing, predictor-feedback CACC and predictor-based ACC laws. In addition, we study numerically the robustness properties with respect to string stability of our predictor-based CACC design to (uncertain) communication delays. Thus, our numerical results validate the performance of the design in realistic scenarios and as compared with related, existing control laws.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"783-796"},"PeriodicalIF":4.6,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10746502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713821","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}

{"title":"NLOS Dies Twice: Challenges and Solutions of V2X for Cooperative Perception","authors":"Lantao Li;Wenqi Zhang;Xiaoxue Wang;Tao Cui;Chen Sun","doi":"10.1109/OJITS.2024.3492211","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3492211","url":null,"abstract":"Multi-agent multi-sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the occluded zone of individual vehicular perception system and further enhancing the overall safety of autonomous driving system. This technique relies heavily on the reliability and availability of vehicle-to-everything (V2X) communication. In practical cooperative perception application scenarios, the non-line-of-sight (NLOS) issue causes occluded zones for not only the perception system but also V2X direct communication, especially for busy traffic scenarios. Cooperative perception can address the NLOS issue for vehicular perception systems once. However, to ensure effective real-world implementation, we must also solve the NLOS challenge a second time for the communication systems that support cooperative perception, NLOS “dies” twice. To counteract underlying communication issues, we introduce an abstract perception matrix matching method for quick sensor fusion matching procedures and mobility-height hybrid relay determination procedures, proactively improving the efficiency and performance of V2X communication to serve the upper layer application fusion requirements. To demonstrate the effectiveness of our solution, a new simulation framework is designed to consider autonomous driving, cooperative perception and V2X communication in general, paving the way for end-to-end performance evaluation and further solution derivation.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"774-782"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10745605","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713822","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}

{"title":"Control Allocation Approach Using Differential Steering to Compensate for Steering Actuator Failure","authors":"Alexander Seiffer;Michael Frey;Frank Gauterin","doi":"10.1109/OJITS.2024.3492115","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3492115","url":null,"abstract":"Wheel-selective drives on the steered axle of a vehicle with Ackermann steering allow for the generation of steering torque without the use of a steering actuator. If different drive torques are applied to the left and right driven wheels, their effect on the steering torque is not balanced, and a resulting steering torque remains (differential steering). Thus, the function of a steering actuator can be replaced, e.g., in case of a failure. Previous studies have demonstrated the effectiveness of controlling a vehicle using differential steering. However, the vehicle dynamics during the failure-induced transition from actuator-based to differential steering control have not been thoroughly investigated. In this work, we utilize a cascaded vehicle dynamics control approach with control allocation to distribute the total drive and steering torques to the available actuators in an overactuated chassis system. Based on both simulation studies and validation experiments with a demonstrator vehicle, we investigate the vehicle dynamics immediately following actuator failures. Our cascaded approach ensures precise vehicle guidance in both nominal and redundancy mode via differential steering. After a sudden actuator failure, vehicle guidance is reliably maintained, even in dynamic driving conditions, as the approach also considers the effect of drive torque distribution on the total yaw torque (torque vectoring). The analyses conducted using the proposed approach demonstrate that a safe transition to cross-actuator functional redundancy after an actuator failure is achievable. Consequently, differential steering can be evaluated as a suitable basis for cross-actuator functional redundancy concepts to enable fault-tolerant operation of steer-by-wire systems.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"756-773"},"PeriodicalIF":4.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10742943","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713878","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}

{"title":"Path Planning Optimization of Smart Vehicle With Fast Converging Distance-Dependent PSO Algorithm","authors":"Muhammad Haris;Haewoon Nam","doi":"10.1109/OJITS.2024.3486155","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3486155","url":null,"abstract":"Path planning is a crucial technology and challenge in various fields, including robotics, autonomous systems, and intelligent transportation systems. The Particle Swarm Optimization (PSO) algorithm is widely used for optimization problems due to its simplicity and efficiency. However, despite its potential, PSO has notable limitations, such as slow convergence, susceptibility to local minima, and suboptimal efficiency, which restrict its application. This paper proposed a novel strategy called the Distance-Dependent Sigmoidal Inertia Weight PSO (DSI-PSO) algorithm to address slow convergence in path planning optimization. This innovative algorithm is inspired by neural network activation functions to achieve faster convergence. In DSI-PSO, each particle computes a distance metric and leverages a sigmoid function to adaptively update its inertia weight. Beyond improving convergence speed, this approach also addresses path-planning challenges in autonomous vehicles. In intelligent transportation systems, effective path planning enables smart vehicles to navigate, select optimal routes, and make informed decisions. The goal is to identify a collision-free path that satisfies key criteria such as shortest distance and smoothness. This methodology not only accelerates convergence but also maintains a balance between exploration and exploitation. The effectiveness of the DSI-PSO algorithm is tested using thirteen distinct unimodal and multimodal benchmark functions, serving as rigorous test cases. Additionally, the algorithm’s realworld applicability is evaluated through a smart vehicle simulation, assessing its ability to identify safe and efficient paths while minimizing overall path length. The results demonstrate the superiority of the DSI-PSO algorithm over conventional PSO approaches, with significantly enhanced convergence rates and robust optimization performance.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"726-739"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10734364","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679255","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}

{"title":"An Extensible Python Open-Source Simulation Platform for Developing and Benchmarking Bus Holding Strategies","authors":"Minyu Shen;Chaojing Li;Yuezhong Wu;Xiaowen Bi;Feng Xiao","doi":"10.1109/OJITS.2024.3481506","DOIUrl":"https://doi.org/10.1109/OJITS.2024.3481506","url":null,"abstract":"Inefficient and unreliable public transportation systems remain a significant challenge in growing cities, with bus bunching being a key contributor to passenger dissatisfaction. Despite numerous proposed holding strategies to mitigate this issue, there is a lack of a standardized testbed for their comprehensive evaluation. This paper presents an open-source, extensible simulation platform that enables the development and benchmarking of bus holding strategies in a unified environment. It accommodates both model-based and model-free reinforcement learning (RL) control strategies, providing a systematic approach to assess their performance under various operating conditions. Holding control strategies can be customized by users within our platform, provided they create a class that fulfills the basic requirements of the exposed application programming interface (API). The platform is designed to be easily extensible, allowing users to incorporate real-world datasets and customize detailed operational features. We demonstrate the platform’s capabilities by comparing three holding strategies: a modelbased forward headway control method and two RL-based approaches. Experimental results highlight the importance of comprehensive evaluations, as the relative performance of different strategies varies under different holding time budgets. The proposed simulation platform aims to facilitate more robust, comparable, and reproducible research in bus operation control strategies, ultimately leading to improved bus service reliability in real-world implementations.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"5 ","pages":"711-725"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720165","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645570","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}

{"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}

{"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}

{"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}

{"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}