Samsara Releases AI-Enabled Drowsy Driving Detection
[Stay on top of transportation news: Get TTNews in your inbox.]
Fleet technology provider Samsara has released a new safety feature that proactively detects and mitigates drowsy driving through artificial intelligence.
The company’s Drowsiness Detection feature uses its AI Dash Cams to monitor factors, such as eye movement and yawning, and then alerts drivers when they are dangerously fatigued.
The new capability, which the company previewed in June at its 2024 Beyond conference in Chicago, is now generally available to customers globally.
When the system determines that a driver has become drowsy, it triggers in-cab audio alerts for drivers while also notifying fleet managers via text or email.
Samsara's Evan Welbourne at a recent industry conference. He says it is difficult to detect when someone is drowsy, and multiple factors are involved. (John Sommers II for Transport Topics)
Managers also can view aggregated reports within the Samsara platform to analyze fatigued driving patterns across their fleet to support driver coaching and improve road safety.
Training AI models to accurately detect drowsiness involves a great deal of nuance, Samsara said.
“It’s hard to detect when someone is truly drowsy. It’s more than a single behavior, like yawning or having your eyes closed,” Evan Welbourne, Samsara’s vice president of AI and data, said in the Oct. 22 announcement. “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.”
McLeod Software CEO Tom McLeod explores the potential for artificial intelligence to boost efficiency and build resilience. Tune in above or by going to RoadSigns.ttnews.com.
Samsara trains its AI models on more than 38 billion minutes of video footage within its platform, he said.
The Drowsiness Detection feature is trained to consider multiple fatigue indicators, including head nodding, slouching, prolonged eye closure, yawning and rubbing eyes.
Yawning alone is often not enough to accurately detect fatigued driving, Samsara said. An analysis of early adopters of Samsara’s Drowsiness Detection feature found that about 77% of drowsy driving events were detected by behaviors other than yawning alone, the company said.
Want more news? Listen to today's daily briefing below or go here for more info:
