01661264

Component

Distracted driving behavior and driving inattention are two leading causes of roadway crashes. The state-of-the-art safety research provides a few attempts to understand and quantify distracted driving and driver inattention. While each attempt had its limitation, there was a consensus on the importance of eye glance behavior as a promising parameter in understanding distracted driving. This study introduces a novel approach to analyze eye glance and quantify distracted driving behavior under normal and Safety Critical Events (SCEs). The proposed approach applies a renewal cycle concept that is inspired by psychological research. The Naturalistic Engagement in Secondary Tasks (NEST) dataset is used to analyze eye glance patterns and determine the relationship between visual behavior and different types of secondary tasks. The analysis revealed that distracted driving behavior can be well characterized using two new measures: the number of renewal cycles per event (NRC) and a distraction level index (DI). Statistical distribution analyses showed that the two measures increase significantly for SCE compared to normal driving events. Consequently, an artificial neural network (ANN) model was developed to test the SCEs predictability power when accounting for NRC and DI. The ANN model was able to predict the SCEs with an overall accuracy of 97.1%. Furthermore, the ANN model indicated that traffic density, NRC, driver behavior, and DI are the most important variables in prediction of SCEs. The findings in this paper can help build reliable algorithms for in-vehicle driving assistance systems to alert drivers before SCEs.

This paper was sponsored by TRB committee AND10 Standing Committee on Vehicle User Characteristics.

18-03714

English

15p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

Figures; References (30) ; Tables

Attention lapses; Automatic data collection systems; Behavior; Distraction; Eye movements; Task analysis

Highways; Safety and Human Factors

Transportation Research Board Annual Meeting 2018 Paper #18-03714

TRIS, TRB, ATRI

Jan 8 2018 10:55AM