Abstract The automotive industry is transforming because of the incorporation of cutting-edge technologies like Big Data, deep learning (DL), machine learning (ML), and the Internet of Things (IoT). This is especially true regarding improving driver behaviour analysis and vehicle performance. Road safety and car diagnostics are greatly aided by real-time monitoring and predictive analytics, made possible by connected vehicles’ massive data generation via onboard sensors, IoT devices, and telematics. Previous studies have mainly focused on individual technologies and lacked comprehensive discussions on the integration of generative AI. This paper covers the literature on driving behaviour analysis, generative AI, predictive maintenance and profiling. It emphasizes how well ML and DL models categorize driver behaviour, spot dangerous driving habits, and forecast when a car requires maintenance. Furthermore, the function of Generative AI is examined in terms of giving drivers personalized and dynamic feedback, enhancing overall driving performance, safety, and fuel efficiency. The paper also addresses data privacy challenges, real-time monitoring, and combining various data sources. Emerging trends in hybrid AI models and large language models are discussed as promising directions for improving predictive maintenance systems and optimizing vehicle performance.
A comprehensive review on data-driven driver behaviour scoring in vehicles: technologies, challenges and future directions
2025
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Review of Connected Autonomous Vehicles Platooning: Technologies, Challenges, and Future Directions
Trans Tech Publications | 2024
|Advances in UAV Path Planning: A Comprehensive Review of Methods, Challenges, and Future Directions
DOAJ | 2025
|