In a not-so-distant future, humans could soon control robot avatars with their mind, completely eliminating the need to complete manual labor or even, really, to leave your house. The foundational research for such a concept has already been pulled off by the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory.
Robotics Ph.D. student Joseph DelPreto and his colleagues devised a system that allowed a human and robot named Baxter to collaborate on a multiple choice test using nothing but brain waves. DelPreto told Inverse back in June that his research could mark the beginning of a revolution in how humans dictate how robots act.
This is #7 on Inverse’s list of the 20 Ways A.I. Became More Human in 2018.
“Right now when we want to work with robots or with our tech there’s sort of a language barrier, where we need to adapt to the robot,” he said. “We need to learn its language, we need to learn keywords, use controls, buttons, or learn programming but we’d like to be able to interact with robots more similarly with how we interact with other people.”
In the paper, presented at the Robotics: Science and Systems conference in June 26, the team detailed how they strapped a brain-signal sensing helmet to a subject’s head and then had the subject command Baxter’s actions.
The helmet picks up on signals known as “error-related potentials,” or ErrPs. The robot basically acts autonomously until it senses ErrPs, at which point it would then stop what it was doing and wait for a hand motion to direct it. It’s crude for now — this system is still in its early stages — but DelPreto sees a lot of potential in fields like developing household robots and worker bots.
Could you correct a robot with just the power of your brain?
“You can imagine developing that further to be more continuous with more fluid motions,” he said. “Down the line, you could have robotic assistants with personal care or in construction and factories.”
Further down the line, technology like this might preclude the need speak to the helper robots of the future at all. They’ll just pick up on what we’re thinking and act accordingly.
