Hans Van Dongen, a researcher at Washington State University Spokane, has received a patent for technology that is designed to detect when drivers are about to go to sleep behind the wheel and thus to help catch fatigue much earlier than video-based systems currently available in some high-end cars.

Van Dongen and postdoctoral research fellow Pia Forsman developed the technology after analyzing data from laboratory experiments at WSU Spokane’s Sleep and Performance Research Center. 

In one of the center’s experiments, Van Dongen says 29 participants were on a simulated 10-day night shift schedule that caused fatigue, which was measured by their performance on an alertness test known as the psychomotor vigilance task. During each night shift, participants spent four 30-minute sessions on a high-fidelity driving simulator.  

“We captured data for 87 different variables like speed, braking, acceleration, how well you are staying in your lane, and other things,” Van Dongen says. 

He says researchers learned that what determines fatigue early on is how well drivers maintain their lane, and more importantly, the steering wheel changes they use to make course corrections as they become more fatigued.

“People who are well rested will respond with small changes. Those who are fatigued respond with less consistency and bigger changes. It turns out that variability is an early predictor of being fatigued,” he says. 

Van Dongen says researchers wanted to determine whether there was a better technique for measuring driver drowsiness before fatigue levels are critical and a crash is imminent. 

“Some car manufacturing systems already detect drowsy driving with video cameras, but those only work when you’re really tired and you’re going to crash in the next five seconds,” he says. “Ours is much more sensitive and gives earlier warning.”

Van Dongen says the technology WSU researchers developed 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,” he says.

The device, Van Dongen says, uses inexpensive, easy-to-install parts, including a sensor that measures the position of a steering wheel, and it could be included in an auto factory installation or as an aftermarket accessory. 

The research describing WSU’s work was published in the journal Accident Analysis & Prevention.