Citation

Przybyla J, Taylor J, Jupe J, Zhou X. Transp. Res. C Emerg. Technol. 2015; 50: 117-129.

Copyright

(Copyright © 2015, Elsevier Publishing)

DOI

10.1016/j.trc.2014.07.013

PMID

unavailable

Abstract

This paper aims to estimate the risk effects of distracted driving, by incorporating a dynamic, data-driven car-following model in an algorithmic framework. The model was developed to predict the situational risk associated with distracted driving. To obtain longitudinal driving patterns, this paper analyzed and synthesized the NGSIM naturalistic driver and traffic database, through a dynamic time warping algorithm, to identify essential driver behavior and characteristics. Cognitive psychology concepts, distracted driving simulator, and experimental data were adapted to examine the probabilistic nature of distracted driving due to internal vehicle distractions. An extended microscopic car-following model was developed and validated, which can be fully integrated with the naturalistic data and incorporate the probabilities of driver distraction.


Keywords: Driver distraction;