Search Results

In the stage of automobile industry transition from SAE level “0,1” low autonomous through “2,3,4” human-in-the-loop and ultimately “5” fully autonomous driving, advanced driving monitor system is critical to understand the status, performance, and behavior of drivers for next-generation intelligent vehicles. By making necessary warnings or adjustments, they could operate collaboratively to ensure a safe and efficient traffic environment. The performance and behavior can be viewed as a reflection of the driver’s cognitive workload, which corresponds as well to the environment of their driving scenarios. In this study, image features extracted from driving scenarios, as well as additional environmental features were utilized to classify driving workload levels for different driving scenario video clips.

A number of studies have shown that driving an unfamiliar vehicle has the potential to introduce additional risks, especially for novice drivers. However, these studies have generally used statistical methods in analyzing crash and near-crash data from different driver groups, and therefore the evaluation might be subjective and limited. For a more objective perspective, we suggested that it would be worthwhile to consider the vehicle dynamic signals from the CAN-Bus. In this study, 20 drivers participated in our experiment, where a Gaussian model was used to model individual driver behavior, as well as using a dissimilarity score, which is measured by the squared 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., driver experienced vs. non-experienced; familiar vs. unfamiliar with vehicle) was clearly observed.