Researchers at Washington State University have developed an interesting approach to detecting drowsy driving. Until now, the majority of drowsy driver detection mechanisms are video-based, and are often bulky and expensive. The new approach, however, is both inexpensive and more effective at detecting drowsy driving:

Their recently patented technology is based on steering wheel movements—which are more variable in drowsy drivers—and offers an affordable and more reliable alternative to currently available video-based driver drowsiness detection systems.¹

The video-based systems are inherently flawed. According to Hans Van Dongen, research professor at the WSU Sleep and Performance Research Center who pioneered the new detection system, “They don’t work well on snow-covered or curvy roads, in darkness or when lane markers are faded or missing.”² Van Dongen and several other researchers performed rigorous tests and experiments to find out if there was a better way to predict driver drowsiness. During this research, Von Dongen and his team found that there were two major factors that best predicted driver fatigue: variability in lane position – which is the main factor measured in the video-based solutions – and variability in steering wheel movements. However, the team found that not only is measuring variability in steering wheel movements cheaper to do, but it is a better indicator of driver fatigue: “Researchers then showed that data on steering wheel variability can be used to predict variability in lane position early on, making it possible to detect driver drowsiness before the car drifts out of its lane.”³

Van Dongen noted that the goal of the research was to find if there was an better indicator of fatigue, one that could be spotted sooner, than the variability in lane position:

We wanted to find out whether there may be a better technique for measuring driver drowsiness before fatigue levels are critical and a crash is imminent…Our invention provides a solid basis for the development of an early detection system for moderate driver drowsiness. It could also be combined with existing systems to extend their functionality in detecting severe driver drowsiness.⁴

Van Dongen spoke to WSU news about how the new system works, and why it is a better predictor of driver drowsiness: