Skip to Content
Artificial intelligence

An autonomous robot swarm has self-organized by acting like natural cells

December 19, 2018

Hundreds of tiny robots have been made to work as a team, inspired by the biological principles of self-organization.

The study: Researchers have managed to get swarms of 300 robots to self-organize without following a preset pattern. The only programming each coin-size robot received was some basic rules on how to communicate—via infrared—with its neighbors.

Inspiration: The robots were programmed to act like cells in a tissue. Those genetic rules mimic the system responsible for so-called Turing patterns in nature, such as a leopard’s spots.

What’s new: Of course, this isn’t the first artificial robot “swarm.” However, past swarms have had their final shape predefined by researchers. “What’s fascinating is there is no master plan; these shapes emerge as a result of simple interactions between the robots,” says Sabine Hauert from Bristol University’s robotics lab, who was part of the study. 

Early days: This is just a proof of concept (and the rather amorphous blobs the robots ended up in don’t look like much) but they're the first steps towards something rather exciting. “The swarms are adaptable, dynamic, and robust, so damage means robots can just re-swarm into new areas,” says James Sharpe, who led the project from Barcelona’s Institute of Science and Technology. The work was published in the journal Science Robotics today.

Potential applications: It isn’t too much of a stretch to see how thousands of tiny robots could help form shapes to explore a disaster environment after an earthquake, or perhaps sculpt themselves into a 3D structures such as a temporary bridge. However, there’s still a long way to go before we see such swarms outside the lab.

Deep Dive

Artificial intelligence

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.

Providing the right products at the right time with machine learning

Amid shifting customer needs, CPG enterprises look to machine learning to bolster their data strategy, says global head of MLOps and platforms at Kraft Heinz Company, Jorge Balestra.

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.