Predicting drowsiness-related driving events: a review of recent research methods and future opportunities

Drowsy driving remains a significant contributing factor to road crashes. The aim of this current paper is to assess the recent developments in the detection and prediction of drowsiness-related driving events. Nineteen research papers met the review inclusion criteria. The research reviewed here has confirmed that drowsiness can have a serious impact on driving performance in controlled, experimental settings, as would be expected on the basis of crash studies and previous research, although new findings from on-road studies show different impacts on performance. While there is substantial literature on the topic, few studies have characterised precise relationships between drowsiness and driving performance. The measurement of drowsiness-related events has progressed and recent research suggests that subjective ratings, blink duration and steering metrics show promise in being effective predictors of drowsiness-related driving events.