Automakers Test In-Car Brain Sensors
Several leading carmakers are exploring whether sensors built into the driver’s headrest can tell if he or she is too drowsy to drive safely, based on the pattern of electrical activity in the brain. Manufacturers are testing a system that sounds an alarm when the sensors pick up patterns associated with sleepiness.
Many automakers are already exploring other methods of sensing driver drowsiness, as part of a wider push to introduce more sophisticated safety technologies. Fatigue causes more than 100,000 crashes and 40,000 injuries, and around 1,550 deaths, per year in the United States, according to the National Highway Traffic Safety Administration. Some studies suggest drowsiness is involved in 20 to 25 percent of all crashes on monotonous stretches of road.
The brain-sensing hardware comes from NeuroSky, a company based in San Jose, California, which makes basic electroencephalography (EEG) headsets and chips for various applications including computer gaming, interactive films, sports training, and market research. Whereas current EEG headset sensors must touch the scalp or skin to pick up the brain’s weak electrical signals, NeuroSky say its latest sensors can operate through fabric, such as the outer layer of a vehicle’s headrest. Some consumer EEG headsets, such as the Zeo, are already being used to track sleep patterns.
“We know we can distinguish between the brain waves of someone who is wide awake and alert and someone who is drowsy and at risk of falling asleep at the wheel,” says Tansy Brook, a spokeswoman for NeuroSky. “Further testing is required. However, we are far enough along to say this is absolutely viable.”
Brook says NeuroSky had been in discussions with three large automakers, which have expressed interest in adopting the fatigue-detection system and have provided seats and headrests for tests.
As well as the new noncontact sensors, the company’s researchers have developed new software to filter out interference. Brook refused to name the manufacturers involved in the research; however, General Motors representatives have had recent meetings with NeuroSky.
Although various existing technologies are intended to combat the problem of driver drowsiness, these represent only partial solutions. Some high-end cars from Ford, Volvo, and VW include systems that identify erratic driving using front-facing cameras to observe the position of the vehicle in relation to lane markings.
Volvo admits that its system, which kicks in above 40 miles per hour, does not work on roads without clear lane markings, and that snow and fog can keep it from working.
A few add-on devices use cameras to look for droopy eyelids or signs of distraction in drivers, and a number of similar systems are in the research pipeline. The add-ons have had mixed results, with the detection algorithms not working for all users or under certain lighting conditions.
“Existing technologies solve the problem to some extent but not completely, because when drivers get tired they exhibit different behavior,” says Daniel Levin, project manager of Driver Alert Control, a system included in several car models sold in Europe since late 2007 in Europe and in the U.S. since 2008.
“EEG produces a tiny signal; however, the electronics are advancing, and researchers are getting better at working out how to filter out interference, so at some point [making use of] it should be possible,” says Louise Reyner of the Sleep Research Centre at Loughborough University, in the U.K. “What remains to be seen is whether NeuroSky have reached that point yet.”
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
ChatGPT is going to change education, not destroy it
The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better.
Meet the people who use Notion to plan their whole lives
The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.
Learning to code isn’t enough
Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.