Skip to Content
Artificial intelligence

Facebook has built stunning virtual spaces for its AI programs to explore

June 14, 2019
FacebookFacebook

Researchers at Facebook have created a number of extremely realistic virtual homes and offices so that their AI algorithms can learn how the real world works.

Real deal: A team at Facebook Reality Labs created 18 “sample spaces” through a program known as Replica. The idea is for AI agents to learn about real-world objects through exploration and practice. In theory, this could make chatbots and robots smarter, and it could make it possible to manipulate VR in powerful ways. But the virtual spaces need to be extremely lifelike for this to be transferable to the real world.

Mirror world: The environments were created by mapping real offices and homes using a high-definition 3D camera rig. The researchers also developed new software to deal with reflections, which can easily confuse such scanning systems. Whereas other simulation engines run at around 50 to 100 frames per second, Facebook says AI Habitat runs at over 10,000 frames per second, which makes it possible to test AI agents rapidly.

Home alone: These virtual spaces can be loaded into a new environment called AI Habitat, inside which AI programs can explore and learn. The algorithms will first be trained to recognize objects in different settings. But over time they should build some common-sense understanding about the conventions of the physical world—like the fact that tables typically support other objects.

Uncommon sense: A lack of common sense is a glaring problem for today’s AI systems. Unlike a person, a chatbot or robot cannot rely on an understanding of the world—things like physics, logic, and social norms—to figure out the intent of an ambiguous command. The complexity and ambiguity of language makes this situation all too common.

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.

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.

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.