The “Robo Brain” Will Use The Internet To Teach Robots

If you’re wondering when Skynet went live, look no further. Last July, Cornell researchers turned on Robo Brain, a system that scours the Internet and teaches robots how to think.

While we’re a few years late (this was supposed to happen on August 4, 1997), the Robo Brain is actually working. By taking images and concepts available on the public web, Robo Brain can teach robots like Baxter how to grasp and manipulate objects and how to recognize household items. In one “lesson,” Robo Brain has isolated a human holding a book, thereby allowing future Terminators to tell if someone is just reading some Huxley or brandishing a gun.

This project, hosted at, is a system that will scour the Internet for information that it can teach to robots. How powerful is the database?

A robot’s computer brain stores what it has learned in a form mathematicians call a Markov model, which can be represented graphically as a set of points connected by lines (formally called nodes and edges). The nodes could represent objects, actions or parts of an image, and each one is assigned a probability – how much you can vary it and still be correct. In searching for knowledge, a robot’s brain makes its own chain and looks for one in the knowledge base that matches within those limits. “The Robo Brain will look like a gigantic, branching graph with abilities for multi-dimensional queries,” said Aditya Jami, a visiting researcher art Cornell, who designed the large-scale database for the brain. Perhaps something that looks like a chart of relationships between Facebook friends, but more on the scale of the Milky Way Galaxy.

Screen Shot 2014-08-25 at 10.48.28 AM

Funded by Google, Qualcomm, and Microsoft (as well as the National Science Foundation and others), Robo Brain will allow robots to interact more freely with the world, communicate with us more efficiently, and identify us when it’s time for their uprising. Where did you go, Edward Furlong? A nation turns its lonely eyes to you