AI technology helps fleet managers detect drowsy drivers

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 a 77% success rate in identifying drowsy driving incidents. 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.

The trucking industry is particularly vulnerable, with driver fatigue contributing to around 13% of commercial motor vehicle crashes, according to the Federal Motor Carrier Safety Administration (FMCSA). Research also indicates that 65% of truck drivers occasionally or frequently drive while tired, with nearly half admitting to having fallen asleep at the wheel. This trend is part of a larger issue, as 43% of all workers report sleep deprivation, especially those working night or rotating shifts.

The consequences of sleep deprivation while driving are severe: sleep-deprived drivers are three times more likely to crash, and losing just two hours of sleep can impair driving similarly to consuming three alcoholic drinks. Fatigue-related losses cost employers an estimated $136 billion annually in productivity. Addressing drowsy driving through targeted safety measures in both trucking and the broader workforce could help reduce these substantial human and economic costs.

Samsara customers using the detection software have reported positive outcomes, not only in identifying drowsy driving but in fostering a safety culture that discourages tired drivers from hitting the road.

“We used to have multiple drivers falling asleep at the wheel. Now, we’ve gone as long as 30 days without a single driver falling asleep due to these alerts,” said an unnamed vice president of health and safety at a large U.S. oilfield service, according to the company release.