Drowsiness while driving is a critical risk, contributing to thousands of crashes and hundreds of deaths each year, with drowsy drivers being three times more likely to cause accidents. To mitigate these scenarios fleet managers have turned to artificial intelligence to monitor driver fatigue over the road.
A newly launched Drowsiness Detection technology by Samsara, tested by 50 early adopters since July, is now available industry-wide and shows that 77% of drowsy driving events are detected by behaviors other than yawning alone. This software uses extensive training on over 10 trillion data points and 38 billion minutes of video footage to power its AI-driven fatigue detection.
“It’s hard to detect when someone is truly drowsy. It’s more than a single behavior, like yawning or having your eyes closed. Drowsiness can be less common than other risky driving behaviors, so accurate detection is only as good as the data that feeds and trains AI models,” said Evan Welbourne, vice president of AI and Data at Samsara, in the release.
Samsara’s Drowsiness Detection technology. (GIF: Samsara)
Drowsy driving is a safety concern. The National Highway Traffic Safety Administration (NHTSA) links it to approximately 91,000 crashes annually, resulting in about 50,000 injuries and 800 deaths. This number likely underestimates the problem, as recent studies suggest that up to 17.6% of fatal crashes from 2017 to 2021 involved fatigued drivers, leading to an estimated 29,834 fatalities.