Artificial Intelligence

Mitsubishi Uses Deep Learning to Detect Distracted Drivers

Pat MedinaOctober 28th 2015
The System

Mitsubishi Electric has developed a new technology that can detect when a driver is distracted while on the road. The machine-learning tech analyzes heart rate, facial orientation, and vehicle steering to determine if the driver is facing a potential danger. The company says that the system can identify if the driver is drowsy or inattentive, but has difficulty in “detecting cognitive distractions.” This challenge is rooted from the fact that these are biological or behavioral patterns rather than visible movements. “The deep learning tech uses forward and backward moving time-series data to help reduce errors in predicting driver actions,” and performed 66% better compared to a conventional algorithm that was previously tested. Mitsubishi Electric plans to install the technology in commercially sold driver sensing units by 2019.

An in-depth look at how the technology works.
An in-depth look at how the technology works.
The Relevance

According to Distracted.gov, distractions include texting, grooming, and talking to passengers – with texting being the “most alarming distraction.” In the United States alone, there are 1.6 million accidents recorded every year due to texting while driving with 6,000 deaths per year. With this becoming a serious problem, the new deep learning tech has the potential to make a huge difference once it’s released to the public.

Keep up. Subscribe to our daily newsletter.

I understand and agree that registration on or use of this site constitutes agreement to its User Agreement and Privacy Policy
Next Article
////////////