Skip to Content

A Glove That Lets You Write in the Air

A prototype glove recognizes pen strokes formed in thin air and turns them into text.
December 27, 2012

Glow sticks and sparklers are terrific fun. I love drawing light patterns in the air, forming images or tracing out fleeting letters that vanish seconds after they appear.

Similar wrist-strokes can be captured now, some of them anyway, by a prototype glove being designed at the Karlsruhe Institute of Technology in Germany.

A team at the Cognitive Systems lab put together inertial sensors, an accelerometer and a gyroscope on a knit glove. The retooled mitt recognizes letter and words and even sentences as its wearer draws them in the air.

The glove doesn’t attempt to recognize everything—it won’t try to decipher letters if you were waving to a friend across the street, perhaps, or stirring a pot of soup. Christopher Amma and the developers of the glove have set up the system to pay particular attention to alphabet-like patterns among the arm movements it is continuously tracking.

When nine volunteers took the gloves for a test run, using it to write words in the air as if drawing on an imaginary blackboard, the designers found that the glove almost never missed a handwriting segment.

That is, when a tester resumed tracing letters in the air after a break, or after using their hands for some other task, the glove listened up and started tracking 99 percent of the time. They wrote the same 366 words from a previously chosen script over 4 hours, taking breaks in between.

The system is designed to recognize more than 8,000 words, and in tests was able to recognize word patterns with an average error rate of 11 percent. Also, the glove’s performance varied depending on which tester was wearing it.

There’s room for improvement in how well the glove recognizes letters and words, the authors admit in their paper describing the glove. But, they claim, it’s a healthy first step towards a gesture sensor that’s built to pick out certain kinds of movements—sequences of alphabets in this case—over others. 

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.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

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.