Skip to Content
Uncategorized

Hold that Call, and Focus on the Road

A system that automatically puts drivers on hold while they negotiate hazards could save lives.

An in-car warning system being developed by Microsoft researchers could help prevent accidents by automatically putting calls on hold when the road demands more attention. The researchers found that the system could significantly reduce the risk of an accident while driving.

Drive carefully: A volunteer uses a driving simulator while answering questions on a speakerphone.

According to the National Highway Traffic Safety Administration (NHTSA), using a cell phone while driving impairs a driver’s reaction time by as much as having a blood alcohol concentration at the legal limit of .08 percent. Most U.S. states have banned the use of handheld phones while driving, and more than half forbid novice drivers and school bus drivers from any cell phone use at all while driving.

Shamsi Iqbal and Yun-Cheng Ju at Microsoft Research in Redmond, Washington, and Ella Mathews at Caltech had 18 pairs of volunteers use a highly realistic driving simulator. One person from each pair was asked to drive a virtual route, while the other asked them questions over a speakerphone. The virtual route featured  construction zones, heavy traffic, and busy residential areas.

In part of the experiment, when the road conditions became tricky—for example, when traffic became denser—the system would cut in, giving an audio alert to both the driver and the caller.  If they failed to stop talking, it would place the conversation on hold. The researchers found that with the system in use, the number of errors made by drivers decreased dramatically, from once every 1.4 minutes to once every 7.1 minutes—a rate even lower than the rate for drivers who weren’t on the phone but received no warning.

“This suggests that inventions may not only make driving safer while conversing, but may make driving safer, period,” says Iqbal. The results were presented in Vancouver this week at the ACM Conference on Human Factors in Computing Systems.

The technology needed to automatically detect trouble spots on the road is still in development, says Eric Horvitz, a Microsoft Research scientist who led the study. “The eventual idea is to have a system that can continue to monitor speed and location with GPS and compute forthcoming driving risk based on prior statistics on each roadway and on the current context,” he says.

Horvitz and colleagues are developing such a system using traffic accident data from the NHTSA and local authorities. “We splatted that data onto the road network to generate a heat map of trouble spots by densities of points of accidents and fatalities,” he says.  “We’d like to one day add data on current traffic conditions,” he adds. Horvitz says some of the technology could perhaps be incorporated into a mobile app so that anyone could use it.

There is a lot of interest in developing technologies to address the problem of driver distraction. “People are under tremendous pressure to work as much as they can, and they see driving as wasted time,” says Paul Green head of driver distraction at the University of Michigan Transportation Research Institute in Ann Arbor. “So if they can work by talking to someone on the phone while driving, then they will just do it.”

Having a system that alerts drivers when necessary is less likely to be ignored, says Green. But the flip side is that drivers may become complacent.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.