Flexible Wearable Detects Hand Gestures, Interacts with Electronics

SEE ALSO: BRAIN IMPLANT ALLOWS MAN TO SIMULTANEOUSLY CONTROL PROSTHETIC LIMBS

This device wouldn't be the first one to help human-computer interactions, however, it would be one of the first built in such a way.

"Reading hand gestures is one way of improving human-computer interaction. And, while there are other ways of doing that, by, for instance, using cameras and computer vision, this is a good solution that also maintains an individual’s privacy," explained Ali Moin, a doctoral student in UC Berkeley’s Department of Electrical Engineering and Computer Sciences.

So how does the device work? 

The team created a flexible armband that reads electrical signals from 64 points on the forearm. These electrical signals are then sent to an electrical chip that's programmed with an AI algorithm that's been taught to associate these signal patterns with hand gestures. 

The AI system the team used is called a hyperdimensional computing algorithm, which can update itself with new information.

So far, the device can read 21 different hand gestures, including a thumbs up, a fist, a flat hand, and individual fingers.

As Moin further explained, "When you want your hand muscles to contract, your brain sends electrical signals through neurons in your neck and shoulders to muscle fibers in your arms and hands."

"Essentially, what the electrodes in the cuff are sensing is this electrical field."

The researchers also pointed out that their device works more quickly than many other systems, and keeps personal data more private. All of the computing is done locally on the chip in the device, so none of the personal data has to be transmitted to a nearby computer or device. 

It's not quite ready to be commercialized, but the team just needs to do a few more tweaks and it should be good to go. 

"Most of these technologies already exist elsewhere, but what’s unique about this device is that it integrates the biosensing, signal processing and interpretation, and artificial intelligence into one system that is relatively small and flexible and has a low power budget," Jan Rabaey, the Donald O. Pedersen Distinguished Professor of Electrical Engineering at UC Berkeley and senior author of the paper, said.