Audi TT Drivers Put to the Test: Bluekeye’s Machine Learning Algorithms Detect Driver Drowsiness with 40% Sensitivity in Real-Time

In the Group’s driving simulator, an Audi TT car surrounded by an immersive curved screen, twenty drivers participated in a validation test for driver drowsiness and attention. The test involved spending up to an hour following a car on a motorway while engaging in a monotonous driving task. At five-minute intervals, they were asked to assess their level of tiredness using the Karolinska Sleepiness Scale.

The self-assessments of tiredness from the drivers were compared to assessments generated by Blueskeye’s machine learning algorithms, following the official EU testing protocol. The algorithms utilized Near Infra-Red cameras mounted in the car’s left and right pillars to capture and analyze eye, head, and facial muscle movement multiple times per second, identifying early signs of fatigue. Reports suggest that the machine assessments of tiredness met the EU’s threshold of 40% sensitivity, indicating that the system can detect when a driver is drowsy and meets the standard required by the EU for new cars.

Blueskeye’s Chief Scientific Officer, Professor Michel Valstar, spoke about their ultimate goal of aiding automotive manufacturers in developing vehicles that can respond to occupants’ emotions using AI face and voice analysis through existing vehicle cameras and microphones. This technology validation for driver drowsiness and attention shows the effectiveness of their underlying technology positioning them well to assist clients in meeting future legislative demands like the EU’s Euro NCAP Vision 2030.

Dr. David R Large, a Senior Research Fellow in Human Factors Research Group at Group pointed out benefits of collaboration with commercial companies like Blueskeye as an opportunity to apply academic expertise and facilities to solve real-world challenges. This collaboration reflects ongoing evolution of automotive industry with need for new technology enhancing safety and sustainability. Participants responded positively towards idea of their cars monitoring them for signs of drowsiness intervention if necessary indicating potential receptiveness towards such safety measures in future.