Research on evaluation model for secondary task driving safety based on driver eye movements

Abstract

This study was designed to gain insight into the influence of performing different types of secondary task while driving on driver eye movements and to build a safety evaluation model for secondary task driving. Eighteen young drivers were selected and completed the driving experiment on a driving simulator. Measures of fixations, saccades, and blinks were analyzed. Based on measures which had significant difference between the baseline and secondary tasks driving conditions, the evaluation index system was built. Method of principal component analysis (PCA) was applied to analyze evaluation indexes data in order to obtain the coefficient weights of indexes and build the safety evaluation model. Based on evaluation scores, the driving safety was grouped into five levels (very high, high, average, low, and very low) using K-means clustering algorithm. Results showed that secondary task driving severely distracts the driver and the evaluation model built in this study could estimate driving safety effectively under different driving conditions. © 2014 Lisheng Jin et al.