首页期刊导航|IEEE transactions on intelligent transportation systems
期刊信息/Journal information
IEEE transactions on intelligent transportation systems
Institute of Electrical and Electronics Engineers
IEEE transactions on intelligent transportation systems

Institute of Electrical and Electronics Engineers

季刊

1524-9050

IEEE transactions on intelligent transportation systems/Journal IEEE transactions on intelligent transportation systemsEISCIISTP
正式出版
收录年代

    IEEE INTELLIGENT TRANSPORTATION SYSTEMS SOCIETY

    C2-C2页

    Table of Contents

    C1-C4页

    IEEE Intelligent Transportation Systems Society Information

    C3-C3页

    Scanning the Issue

    Azim Eskandarian
    3-13页
    查看更多>>摘要:Energy Management Strategies for Fuel Cell Vehicles: A Comprehensive Review of the Latest Progress in Modeling, Strategies, and Future Prospects

    Energy Management Strategies for Fuel Cell Vehicles: A Comprehensive Review of the Latest Progress in Modeling, Strategies, and Future Prospects

    Arash KhalatbarisoltaniHaitao ZhouXiaolin TangMohsen Kandidayeni...
    14-32页
    查看更多>>摘要:Fuel cell vehicles (FCVs) are considered a promising solution for reducing emissions caused by the transportation sector. An energy management strategy (EMS) is undeniably essential in increasing hydrogen economy, component lifetime, and driving range. While the existing EMSs provide a range of performance levels, they suffer from significant shortcomings in robustness, durability, and adaptability, which prohibit the FCV from reaching its full potential in the vehicle industry. After introducing the fundamental EMS problem, this review article provides a detailed description of the FCV powertrain system modeling, including typical modeling, degradation modeling, and thermal modeling, for designing an EMS. Subsequently, an in-depth analysis of various EMS evolutions, including rule-based and optimization-based, is carried out, along with a thorough review of the recent advances. Unlike similar studies, this paper mainly highlights the significance of the latest contributions, such as advanced control theories, optimization algorithms, artificial intelligence (AI), and multi-stack fuel cell systems (MFCSs). Afterward, the verification methods of EMSs are classified and summarized. Ultimately, this work illuminates future research directions and prospects from multi-disciplinary standpoints for the first time. The overarching goal of this work is to stimulate more innovative thoughts and solutions for improving the operational performance, efficiency, and safety of FCV powertrains.

    Evaluation Framework for Electric Vehicle Security Risk Assessment

    Soheil ShirvaniYaser BaseriAli Ghorbani
    33-56页
    查看更多>>摘要:Electric Vehicles (EVs) seem promising for future transportation to solve environmental concerns and energy management problems. According to Reuters, global car makers plan to invest over half a billion in more efficient and intelligent EVs and batteries. However, there are several challenges in EV mass production, including cybersecurity. Due to the cyber-physical nature of EVs and charging stations, their security and trustworthiness are ongoing challenges. In this study, we identify gaps in the security profiling of EVs and categorize them into five components: 1) charging station security, 2) information privacy, 3) software security, 4) connected vehicle security, and 5) autonomous driving security. Our study provides a comprehensive analysis of identified vulnerabilities, threats, challenges and attacks for different EV security aspects, along with their possible surface/subsurface and countermeasures. We develop a comprehensive security risk assessment framework by first using EV security profiles and mapping identified vulnerabilities to a well-known threat model, STRIDE. Then, we classify the risk levels associated with each vulnerability by setting ground criteria for the impact and likelihood of the threats. Finally, we validate our risk assessment framework by applying the same criteria to eight real-world EV attack scenarios. As a result, researchers can adapt the proposed risk assessment framework to discover threats and assess their risks in EVs and charging station ecosystems.

    Artificial Intelligence-Assisted Robustness of Optoelectronics for Automated Driving: A Review

    Edric John Cruz NacpilJiye HanIl Jeon
    57-73页
    查看更多>>摘要:Optoelectronic sensing systems are used in automated vehicles for in-cabin features such as driver attention and distraction monitoring. As automated driving technology continues to advance, vehicles are becoming increasingly capable of navigating driving environments with the assistance of optoelectronic sensing systems. Nevertheless, variable operating conditions, such as weather and driver behavior, can compromise driving safety by reducing the robustness of some systems. To improve the safety of automated vehicles, as well as the trust between humans and vehicle automation, this review discusses existing literature on the design and application of optoelectronic sensing in modern automobiles. Recent advancements in optoelectronics have been partly attributed to human ingenuity and the recent application of artificial intelligence to optimize sensor performance parameters. As a major contribution, we consider how artificial intelligence can be used to develop next-generation sensing systems for automated driving applications. Consideration is also given to research avenues with the potential to expand these applications. Based on a discussion of current challenges in optoelectronic sensor development, along with our recommendations to address these challenges, we draw conclusions on the state-of-the-art and the future of optoelectronic sensing.

    CVAR: Distributed and Extensible Cross-Region Vehicle Authentication With Reputation for VANETs

    Jing ZhangHong ZhongJie CuiLu Wei...
    74-89页
    查看更多>>摘要:This study proposes a distributed and extensible cross-region vehicle authentication scheme with the reputation for improving the security and efficiency of cross-region vehicle authentication. The existing authentication schemes demonstrate the following drawbacks: 1) Each vehicle is preloaded with the same system private key, which may be leaked so that the entire system would be destroyed; 2) Other schemes rely on trusted authority to aid in selecting some cluster head nodes; 3) The existing cross-region authentication schemes are not flexible and scalable since they depend on the infrastructure fixed on the roadside. With the proposed scheme, each vehicle stores a long-term private key that is different from those of other vehicles, thereby avoiding a system crash when destroying a vehicle. When the cross-region vehicle enters a new region, it can verify the reputation value of the surrounding vehicles to select the edge computing vehicle. The formal security proof shows that the proposed scheme has adequate security under the real-or-random model. The performance evaluation of our scheme with several related schemes reveals that it generates relatively low computation and communication overhead, is more robust, and achieves minimum packet loss ratio and delay.

    Single Traffic Image Deraining via Similarity-Diversity Model

    Youxing LiRushi LanHuiwen HuangHuiyu Zhou...
    90-103页
    查看更多>>摘要:Single traffic image deraining technology based on deep learning is a vital branch of image preprocessing, which is of great help to intelligent monitoring systems and driving navigation system. It is well understood that established deraining methods are derived based on one specific imaging model, neglecting the underlying correlations between different weather models and thereby limiting the applicability of these standard methods in real scenarios. To ameliorate this issue, in this work, we first explore the inherent relationship between a rain model and the haze one established up to date. We discover that these two models experience similar degradations in the low-frequency components (i.e., similarity) but diverse degradations in the high-frequency areas (i.e., diversity). Based on these observations, we develop a Similarity-Diversity model to describe these characteristics. Afterwards, we introduce a novel deep neural network to restore the rain-free background embedding the similarity-diversity model, namely deep similarity-diversity network (DSDNet). Extensive experiments have been conducted to evaluate our proposed method that outperforms the other state of the art deraining techniques. On the other hand, we deploy the proposed algorithm with Google Vision API for object recognition, which also obtains satisfactory results both qualitatively and quantitatively.

    A Multilevel Electronic Control Unit Re-Encryption Scheme for Autonomous Vehicles

    Jie CuiYun ShenHong ZhongJing Zhang...
    104-119页
    查看更多>>摘要:Electronic control units (ECUs) connected by a controller area network (CAN) are used to perform various functions in modern vehicles. In the latest autonomous vehicles, redundant ECUs and a backup bus (different from CAN) are always equipped to prevent a single point of failure or network attack. However, due to the lack of protection measures of CAN bus, attackers can remotely intrude into the vehicle. Many schemes have proposed to use encryption to solve the security problem of CAN bus. Considering the current ECU storage space is limited, it is impossible to store all ECUs’ keys. When a single point of failure or network attack against an ECU occurs, it is necessary for the backup ECU to process the messages related to the failed ECU. How to ensure that the backup ECU can decrypt the encrypted messages and at the same time securely isolates the backbone network from the backup network is an urgent issue to be solved. In order to solve the problem of forwarding and processing such messages under encryption conditions, we propose an efficient re-encryption scheme based on proxy re-encryption. The scheme is also suitable for cross-bus communication without backup networks. Burrows-Abadi-Needham (BAN) logic, random oracle model and Automated Validation of Internet Security Protocols and Applications (AVISPA) tool are utilized to prove that the scheme is secure. The scheme is simulated based on the MIRACL cryptography library on the computer and Raspberry Pi. The simulation results demonstrate that the proposed scheme is secure compared with the existing scheme.