A Pattern-Recognition Approach for Driving Skill Characterization

Information about a driver´s driving skill can be used to adapt vehicle control parameters to facilitate the specific driver´s needs in terms of vehicle performance and safety. This paper presents an approach to driving skill characterization from a pattern-recognition perspective. The basic idea is to extract patterns that reflect the driver´s driving skill level from the measurements of the driver´s behavior and the vehicle response. The experimental results demonstrate the feasibility of using a pattern-recognition approach to characterize a driver´s handling skill. This paper concludes with the discussions of the challenges and future works to bring the proposed technique to practical use.