Algorithm detects drowsy driving.
During the recent MIT/New England Motor Press conference on autonomous vehicles, Sascha Simon, product manager for advanced product planning at Mercedes-Benz related an interesting story on how the automaker developed one of its advanced driver assistance systems—the drowsy driver alert (attention sensing).
The company was using its driving simulators and pushing its college student subjects to "drive" for long periods—until they became tired and distracted. With more than 70 sensors on the "car," output from these would change in values and rates when the drivers became fatigued (particularly steering, throttle, and brake inputs). Mercedes engineers then developed an algorithm to predict "tiredness" without the need for adding another sensor. Simon says the system is more effective than trying to determine drowsiness by attempting to measure eye movement.
The system can be tailored to learn the behavior of an individual for greater effectiveness. Simon adds another challenge was determining a threshold of when to issue an alert (including lighting a coffee-cup icon)—without becoming annoying.
Go to the Automotive Designline home page
for the latest in automotive electronics design, technology, trends, products, and news. Also, get a weekly highlights update delivered directly to your inbox by signing up for our weekly automotive electronics newsletter here