Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory and Boston University have developed a robot that can be controlled by your mind, using artificial intelligence and machine learning to understand exactly what you want it to do.
Baxter works by tapping into a human’s brain and will be able to correct mistakes using the power of a human’s brain. They simply have to think about how to fix it and the robot will carry out the task.
It works by hooking up to the human’s brain via an electroencephalography (EEG) monitor, which records brain activity.
For example, Baxter can sort shapes while being watched by a researcher wearing the monitor. When the researcher identifies the wrong shape is being placed in the wrong place, the robot can detect the problem, or “error-related potentials” (ErrPs) in the signals being sent to it.
After using this process to control the robot, the researchers moved onto their next challenge, which was creating machine leaning algorithms that can detect brain waves in less than 30 milliseconds.
“As you watch the robot, all you have to do is mentally agree or disagree with what it is doing,” says Rus. “You don’t have to train yourself to think in a certain way — the machine adapts to you, and not the other way around.”
Because the brain waves are so faint, explains, ZDNet, it sometimes struggles to understand what’s expected of it, so send a query for more information. Although it can’t make right these issues yet, that’s the next step in the universities’ research.
“Imagine being able to instantaneously tell a robot to do a certain action, without needing to type a command, push a button or even say a word,” Rus says. “A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars and other technologies we haven’t even invented yet.”