Assessment of distractions inferred by in-vehicle information systems on a naturalistic simulator

Abstract

Driving inattention is a major factor to highway crashes. The National Highway Traffic Safety Administration (NHTSA) estimates that approximately 25% of police-reported crashes involve some form of driving inattention. Increasing use of in-vehicle information systems (IVISs) such as cell phones or GPS navigation systems has exacerbated the problem by introducing additional sources of distraction. Enabling drivers to benefit from IVIS without diminishing safety is an important challenge. In this paper, an automatic distraction monitoring system based on gaze focalization for the assessment of IVISs induced distraction is presented. Driver's gaze focalization is estimated using a non-intrusive vision-based approach. This system has been tested in a naturalistic simulator with more than 15 hours of driving in different scenarios and conditions and 12 different professional drivers. The purpose of this work is, on the one hand, to assess the detection capacity of the monitoring system and, in the other hand, to study drivers reactions to different IVISs. Gathering this information the optimal IVISs location and the way the indications should be delivered to the drivers can be studied to reduce the interference with their driving.