Analysis Of Driving Performance Based On Driver Experience And Vehicle Familiarity: A Utdrive/Mobile-Utdrive App Study

A number of studies have shown that driving an unfamiliar vehicle has the potential to introduce additional risk, especially for novice drivers. However, such studies have generally used statistical methods based on analyzing crash and near-crash data from a range of driver groups, and therefore the evaluation has the potential to be subjective and limited. For a more objective perspective, this study suggests that it would be worthwhile to consider vehicle dynamic signals obtained from the Controller Area Network (CAN-Bus) and smartphones. This study, therefore, is focused on the effect of driver experience and vehicle familiarity for issues in driver modeling and distraction. Here, a group of 20 drivers participated in our experiment, with 13 of them having participated again after a one-year time lapse in order for analysis of their change in driving performance. A clustering-based, outlier detection grading method was used to grade individual driver behavior, as well as discrepancy score, which is measured by the Euclidean distance in the vehicle dynamical feature space, to evaluate driving performance. Results show that the variation of driving performance caused by driver experience and vehicle familiarity (i.e., experienced vs. non-experienced driver, familiar vs. unfamiliar with the vehicle) was clearly observed. Additionally, among the signals examined, we found that the combination of all signals provides a better reflection of driving performance variances, which could be used for future advanced vehicle technology to reduce accidents and improve road safety.