Skip to Content

A Robot That Knows When to Back Off

A modified Roomba tries to detect, and avoid, stressed-out users.

We all feel the urge to kick our home appliances occasionally. But what if they all rushed into another room as soon as you started getting angry?

It’s not such a far-fetched idea. At the 2009 Human-Robot Interaction conference, which took place this week in California, researchers presented a range of research on how to improve communication between humans and machines. One presentation revealed a modified vacuum-bot that can detect its owner’s emotional states.

In a paper titled “Using Bio-electrical Signals to Influence the Social Behaviors of Domesticated Robots,” researchers from the University of Calgary describe connecting a headband that reads bioelectrical signals to a humble floor-cleaning Roomba.

The headband, which is sold as a gaming device, detects muscle tension in the wearer’s face, so the researchers were able to directly control the Roomba’s speed by, for example, clenching their jaws or tensing their eyebrows. They also developed a somewhat crude way to evaluate a person’s emotional state, based on facial muscle tension (the more tension, the more stress), and programmed the Roomba to respond. If a person exhibited high stress, the Roomba continued cleaning but moved away from the user, according to the paper.

Robots that can sense human emotions could be much more responsive, the researchers say. Envision a robot cowering under the bed if a user is feeling angry and looking for something to kick. Alternatively, a robot designed to provide comfort could instinctively approach a person who is feeling particularly sad or stressed.

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.

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.

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.

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.