Representing-behavior-based online driving style recognition and its road verification

—Driving style recognition (DSR) is a critical task for intelligent vehicles, providing a means to analyze drivers’ behavioral characteristics and understand their preferences. In this study, a representing-behavior-based DSR method is proposed. It is not only capable of distinguishing various driving styles but also adept at depicting their dynamic changes during a trip. Initially, three driving behavior datasets are extracted from natural driving data. Subsequently, a clustering metric called driving style distinction is introduced to assist the k-means algorithm in searching for driving style representing behaviors (DSRBs) within these datasets. Considering the impact of input features on clustering, a genetic-algorithm-based feature selection method is implemented to optimize the DSRB search. Upon completing this task, DSRB recognition models are built through supervised learning, enabling the calculation of a novel metric called the driving style index, which describes driving styles in real time. A road test demonstrates the feasibility of the proposed method, establishing it as an effective solution for DSR problems.