Classification of Driving Style in Relation to Risk Level Based on G-G Diagram

This paper proposes a novel method to classify drivers' driving styles based on G-G diagrams that display the lateral and longitudinal accelerations on the x- and y-axes. A data-based safe driving area was defined to distinguish risky acceleration points from safe acceleration points. The Jensen–Shannon divergence was used to measure the similarity between the distributions of data points outside the safe driving area. A hierarchical clustering algorithm was used to classify the drivers into two groups based on similarity: non-aggressive and aggressive groups. To verify the proposed method, we used the naturalistic driving data of 71 drivers. The results indicated that the proposed method could help understand the risk level of drivers and individual differences in their driving styles. Drivers in the aggressive group exhibited diverse types of risky driving styles, and the percentage of points outside the safe driving area was much higher than that for the low-risk group. The proposed method can be applied in driving performance feedback provision, fleet management, and usage-based insurance.