Disclaimer:
The information provided by Dirt Legal is for general informational purposes only and does not constitute legal or financial advice. Please consult your CPA or attorney for guidance on all financial and legal matters.

Flashing emergency lights can interfere with advanced driver-assistance features, decreasing their accuracy, according to a study from Ben Gurion University of the Negev in Israel and Japanese technology company Fujitsu. 

The study found sixteen recorded mishaps where Teslas, with the Autopilot feature engaged, had collided with parked police cars, ambulances, and fire trucks, according to Automotive News. 

The research provides more scrutiny to self driving technologies but also aids with solutions, Automotive News said. 

“It was pretty clear to us from the beginning that the crashes might be related to the lighting of the emergency flashers,” Ben Nassi, a cybersecurity and machine learning researcher at Ben-Gurion University who worked on the paper, said. 

“Ambulances and police cars and fire trucks are different shapes and sizes, so it’s not the type of vehicle that causes this behavior,” Nassi added. 

Carmakers say their automated driving systems enhance safety while driving, although new research suggests some of these systems may do the opposite at the worst moment, Wired said. 

The researchers are calling this issue a “digital epileptic seizure,” EpileptiCar for short.

The researchers additionally said that the issue “poses a significant risk” because it could cause vehicles with automated driving systems enabled to “crash near emergency vehicles" and “be exploited by adversaries to cause such accidents.”

“Emergency vehicle flashers are a challenge because they dramatically change how an object looks in a very short period of time,” said Philip Koopman, associate professor of electrical and computer engineering at Carnegie Mellon University.

“It is common for computer vision systems to process a single image at a time and then track objects across a series of video images with each image processed as they arrive,” He said. 

Factors that influence the severity of the EpileptiCar phenomenon include ambient light conditions, emergency flasher patterns, camera settings, and distance to the emergency vehicle, the Ben Gurion University of the Negev and Fujitsu Limited said. 

These findings have been disclosed with NHTSA, Tesla and five manufacturers of the ADAS analyzed in the study.

“Unfortunately, object trackers, which are often employed in ADAS to track the presence of multiple objects, have not been successful in mitigating the detection loss caused by the EpileptiCar phenomenon,” the FAQ page on the study said.

The Insurance Institute for Highway Safety has also found shortcomings in ADAS platforms outside of flashing lights, according to Wired. 

Automakers need “repeatable, robust validation” to uncover blind spots like susceptibility to emergency lights, researcher Bryan Reimer, who studies vehicle automation and safety at the MIT AgeLab said. 

He worries some automakers are “moving technology faster than they can test it,” Wired said.