Mind-Reading Robots Can Fix Its Own Mistakes With Your Brain Waves
Imagine a world where physical buttons and verbal commands are no longer necessary to control robots or cars or Siri -- one only needs the power of your mind. Well, scientists have come up with the system for it now.
Researchers from the Massachusetts Institute of Technology's (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University (BU) developed a feedback system that actually lets people control robots -- specifically, correct their mistakes -- with just their brain waves, according to a report from MIT News. The team published their findings in a paper online.
This newly-created system gets its data from an electroencephalography (EEG) monitor that tracks brain activity. In particular, the system is focused on brain signals generated when the brain sees a mistake. These signals are called "error-related potentials" (ErrPs) and in this system, they're used to determine whether the person agrees with the decision or not. It's also reading the mind in real time as the team's algorithms can classify brain waves within 20 to 30 milliseconds.
"As you watch the robot, all you have to do is mentally agree or disagree with what it is doing," CSAIL Director Daniela Rus explained. "You don't have to train yourself to think in a certain way - the machine adapts to you, and not the other way around."
Read Also: Meet the AI That Can Write Its Own Code
For now, the system just deals with simple binary-choice tasks, but the future offers endless of possibilities. The team expects more complex multiple-choice activities to come, and BU PhD candidate Andres F. Salazar-Gomez even suggested that the system can help people who cannot communicate verbally.
The team's intuitive approach to controlling robots is ground-breaking with many potential uses across different technological industries.
"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 said. "A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars, and other technologies we haven't even invented yet."