Quantitative Evaluation of Distracted Driving by Using a PrARX Model

This research develops a metric for the evaluation of an automobile driver's distraction based on a mathematical driving behavior model. Driving data was collected in a driving simulator. The primary task was to maintain a constant following distance behind a lead vehicle. The secondary task, which brings about the distraction, is to operate the in-car touch panel. A PrARX model is used to describe the vehicle-following behavior. In the PrARX model, the weighting parameter represents the driver's logical decision making and the auto-regressive exogenous models characterize the driver's continuous-time motion control behavior. By calculating the entropy of the PrARX model, the driver's distraction, which is considered a degradation of decision-making ability, is assessed in a quantitative manner.