Scientists have trained AI to see through walls
No big deal, just some X-ray vision

Each week, we spotlight a cool innovation recommended by some of the industry's top tech writers. This week's pick is an AI with X-ray vision.
"Omnipresent wireless signals that keep us connected can now be used like X-rays to see and track the movements of people, even when hidden behind walls," said Andrew Liszewski at Gizmodo. Radio waves, while invisible to the eye, bounce off human bodies when wireless signals come out of broadcast antennas, and the way the signals are altered can be measured.
Researchers at MIT's Computer Science and Artificial Intelligence Laboratory trained a neural network to generate stick-figure skeletons of people walking, sitting, and talking. They then taught the AI how those skeletons corresponded to scattered radio signals. Eventually, "by analyzing just the scattered radio-signal data," the neural network was able to generate skeletons showing a person's posture and movements, even when the person was hidden behind a wall. "It's X-ray vision without the need for blasting harmful X-rays."
Subscribe to The Week
Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

Sign up for The Week's Free Newsletters
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
A free daily email with the biggest news stories of the day – and the best features from TheWeek.com
-
June 28 editorial cartoons
Cartoons Saturday's political cartoons include stupid wars, a critical media, and mask standards
-
Thai fish pie with crispy turmeric potatoes recipe
The Week Recommends Tasty twist on the Lancashire hot pot is given a golden glow
-
Palestine Action: protesters or terrorists?
Talking Point Damaging RAF equipment at Brize Norton blurs line between activism and sabotage, but proscription is a drastic step