Skip to main content
  1. Home
  2. Wearables
  3. Mobile
  4. News

Researchers at Carnegie Mellon have developed a wristband that can sense hand gestures

Add as a preferred source on Google

As anyone who owns a smartwatch can tell you, one-handed operation isn’t exactly their forte. Beyond the “flick-to-wake” gesture found in a number of smartwatches and Android Wear’s wrist-based notification scrolling, there’s not much you can do without a second hand and set of fingers. But a team of researchers may have developed solution: a strap called Tomo that translates subtle muscle movements into software actions.

The prototype, developed by researchers at Carnegie Mellon University’s Human-Computer Interaction group, uses tiny impulses to sense wrist muscle movements. Operating on a principle of Electrical Impedance Tomography, similar to PET and CT machines, eight metal contacts send a continuous series of tiny electrical impulses through the wearer’s wrist. Sensors measure the strength of the impulses on the other side and, over time, collect enough data to generate and analyze a digital image of the finger and hand gestures being performed.

Recommended Videos

The wristband may not be the first capable of recognizing hand and wrist gestures, but it could be the most practical. Camera-based modules are typically much bulkier, the researchers note, and accelerometer and gyroscope-based systems can’t support static gestures. Moreover, the internal nature of Tomo’s analysis means it should work through gloves and clothing. And it’s cheap ($40 in its current form), small, and has a power draw minimal enough to make “integration directly into a smartwatch” feasible.

Tomo’s not perfect, though. Differences in wrist size and thickness between wearers mean the strap’s recognition software must “learn” gestures before it can accurately recognize them. (Think training voice dictation software to recognize diction.) And thanks to the granularity of the muscle measurements, the strap’s accuracy is largely dependent on its tightness and the consistency of its positioning.

Shortcomings aside, the Tomo’s the best attempt yet at a single-handed way of controlling a smartwatch. For the sake of those who never have a hand to spare, here’s hoping it catches on.

Kyle Wiggers
Kyle Wiggers is a writer, Web designer, and podcaster with an acute interest in all things tech. When not reviewing gadgets…
Pixel Watch 5 leak bares it all, and it seems Google is playing it safe again
Leaked renders reportedly reveal both sizes and every color, but Google’s next smartwatch looks more like another careful refinement than a reinvention
Pixel Watch on Wrist

Google’s next smartwatch may have just lost what little mystery it had left. High-resolution Pixel Watch 5 renders shared by longtime device leaker Steve Hemmerstoffer, better known as OnLeaks, show both case sizes and what’s claimed to be the complete color lineup ahead of Google’s expected August 12 launch event. The images were published in partnership with TheTideChart.com.

Assuming the renders are accurate, Google isn’t straying far from its established formula. The domed display and proprietary band system both appear to be returning for another generation.

Read more
Pixel Watch permission error won’t go away, but there’s a weird fix
Turns out the fix has nothing to do with permissions, and everything to do with notifications.
Pixel Watch on Wrist

If you own a Pixel Watch, there's a chance you have seen a stubborn permission prompt carrying the Fitbit logo on your wrist. It asks for access to your sensor data and refuses to leave no matter how many times you dismiss it.

The frustrating part is that most people hit by this have already granted every permission the watch could possibly want. Everything is toggled on, and yet the warning keeps persisting. 

Read more
I tried to parody the most absurd AI products, but the tech industry beat me to it
The joke was supposed to be that every household object gets cameras, AI insights, and a premium tier. Apparently, that’s now a business plan
Imaginary AI products

I wanted to invent an AI product so silly that no founder could turn it into a seed round.

It had to solve a problem nobody had, collect far more data than the problem deserved, and turn normal behavior into an insight that sounded vaguely disappointed in its owner. Somewhere around the third feature, it would ask for a subscription.

Read more