Driving style classification and recognition methods for connected vehicle control in intelligent transportation systems: A review

Abstract

Advancements in intelligent vehicle technology have spurred extensive research into the impact of driving style (DS) on intelligent transportation systems (ITS), aiming to enhance vehicle safety, comfort, and energy efficiency. Accurate DS identification is pivotal for accelerating ITS adoption, especially in regions where its implementation is still in its infancy. This paper investigates the role of DS recognition methods, particularly clustering and classification techniques, in influencing connected vehicle control and optimizing speed planning within ITS. While traditional speed planning approaches focus on general traffic models, this study emphasizes the critical role of DS in shaping personalized and adaptive speed planning. The paper highlights three primary DS recognition approaches: rule-based, model-based, and learning-based methods, and introduces a framework for integrating DS recognition with speed planning, addressing aspects such as data collection, preprocessing, and classification techniques. This focus provides a novel perspective on leveraging DS recognition to enhance ITS adaptability.