As modern vehicles continue to integrate increasingly sophisticated Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AV) functions, conventional user manuals may no longer be the most effective medium for conveying knowledge to drivers. This research analysed conventional, paper and video-based instructional methods versus a Large Language Model (LLM)-based instructional tool to educate 86 participants about the operation of specific ADAS and AV functionalities. The study sampled participants aged between 20 and over 40, with driving experience ranging from one to over six years. The first group was educated using the conventional methods. In contrast, the second group received instructions via an LLM, i.e., users learn via ChatGPT interaction. Our goal was to assess the efficiency and effectiveness of these teaching methodologies based on the reaction times participants required to activate ADAS functions and the corresponding accuracies. Our findings revealed that the group trained via ChatGPT demonstrated significantly improved learning outcomes compared to conventional training. This included shorter activation times, higher consistency, and higher accuracy across examined functions. This study further proposed a framework to effectively use ChatGPT for different training scenarios and education purposes, offering a valuable resource for leveraging Artificial Intelligence (AI) in training users to handle complex systems. The framework empowers educators to tailor ChatGPT’s interactions, ensuring efficient, guided learning experiences for learners. For researchers, this study lays the foundation for exploring the role of LLM-based instructional tools in a broader range of applications.

Understanding the complexities of Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicle (AV) technologies is critical for road safety, especially concerning their adoption by drivers. Effective training is a crucial element in ensuring the safe and competent operation of these technologies. This study emphasises the critical role of training methodologies in shaping drivers’ mental models, defined as an individual’s cognitive frameworks for understanding and interacting with ADAS and AV systems. Their mental models substantially influence their interactions with those technologies. A comparative analysis of text-based and video-based training methods has been conducted to assess their influence on participants’ performance and the development of their mental models of ADAS and AV functionalities. Performance is evaluated in terms of the accuracy and reaction time of the participants as they interacted with ADAS and AV functions in a driving simulation. The findings reveal that video-based training yielded better performance outcomes, more accurate mental models, and a deeper understanding of ADAS functionalities among participants. These findings are crucial for policy makers, automotive manufacturers, and educational institutions involved in driver training. They underscore the necessity of developing tailored training programs to facilitate the proficient and safe operation of increasingly complex automotive technologies.

Our study investigates the efficacy of ChatGPT-assisted learning in enhancing the understanding of Advanced Driver Assistance Systems (ADAS) functionalities, comparing it against conventional paper-based learning methods. By employing multiple-choice questionnaires and the NASA Task Load Index to evaluate comprehension and cognitive load, we aimed to assess the impact of interactive Large Language Model (LLM)-driven learning on knowledge acquisition and learner satisfaction. Our findings indicate that participants who engaged with ChatGPT-based training scored higher (on average 11% higher) in correctness and experienced lower cognitive and physical demands, suggesting a more effective and less stressful learning process. This study contributes by highlighting ChatGPT’s potential to accommodate a wide range of learning preferences and improve the comprehension of complex systems or topics. This adaptability was evident across diverse educational backgrounds among young adult participants, showcasing the tool’s ability to bridge knowledge gaps more efficiently than conventional methods. Our research advocates the integration of LLM-driven tools in educational and policy-making frameworks to improve the effectiveness of teaching complex systems. This suggests broader applicability and necessitates further investigation into the scalability and effectiveness of ChatGPT-based training across different demographics and learning domains, potentially informing future educational strategies.

This paper investigates the importance of standardising and maintaining the transparency of advanced driver-assistance systems (ADAS) functions nomenclature, designs, and operations in all categories up until fully autonomous vehicles. The aim of this paper is to reveal the discrepancies in ADAS functions across automakers and discuss the underlying issues and potential solutions. In this pilot study, user manuals of various brands are reviewed systematically and critical analyses of common ADAS functions are conducted. The result shows that terminologies used to describe ADAS functions vary widely across manufacturers and sometimes do not reflect their fundamental functions intuitively. Operational conditions and control procedures also vary across the selected models under this study. Due to this lack of consensus across the industry, drivers are not aware or well informed about ADAS functions in their vehicles, leading to a very low utilization rate and may lead to misuse of those functions. This paper provides insightful suggestions for the transport industry, Artificial Intelligence (AI) experts, and regulators to design frameworks and guidelines in governing the naming convention, operating conditions, control procedures, and information disclosure of ADAS. Such guidelines can be the foundations for regulating future AI-based self-driving functions.

This study conducts a detailed analysis of cybersecurity threats, including artificial intelligence (AI)-driven cyber-attacks targeting vehicle-to-vehicle (V2V) and electric vehicle (EV) communications within the rapidly evolving field of connected and autonomous vehicles (CAVs). As autonomous and electric vehicles become increasingly integrated into daily life, their susceptibility to cyber threats such as replay, jamming, spoofing, and denial-of-service (DoS) attacks necessitates the development of robust cybersecurity measures. Additionally, EV-specific threats, including battery management system (BMS) exploitation and compromised charging interfaces, introduce distinct vulnerabilities requiring specialized attention. This research proposes a comprehensive and integrated cybersecurity framework that rigorously examines current V2V, vehicle-to-everything (V2X), and EV-specific systems through systematic threat assessments, vulnerability analyses, and the deployment of advanced security controls. Unlike previous state-of-the-art approaches, which primarily focus on isolated threats or specific components such as V2V protocols, the proposed framework provides a holistic cybersecurity strategy addressing the entire communication stack, EV subsystems, and incorporates AI-driven threat detection mechanisms. This comprehensive and integrated approach addresses critical gaps found in the existing literature, making it significantly more adaptable and resilient against evolving cyber-attacks. Our framework aligns with industry standards and regulatory requirements, significantly enhancing the security, safety, and reliability of modern transportation systems. By incorporating specialized cryptographic techniques, secure protocols, and continuous monitoring mechanisms, the proposed approach ensures robust protection against sophisticated cyber threats, thereby safeguarding vehicle operations and user privacy.