  GO BACK
Share this issue of the Magazine:
SEE ALL ISSUES
Contents
Your weekly briefing on the state of 
humanity
SEE ALL ISSUES
EDITOR'S LETTER
{{magazine.editorsLetter.title}}
Feature
{{article.title}}

Brain-controlled robots are no longer science-fiction | The World Weekly

Imagine being able to communicate telepathically with a robot. No need to push a button or speak - just think, and the android responds.

This is no longer the realm of science fiction. A team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University is developing a system that allows human operators to correct a robot’s decisions in real time using only their minds.

The researchers used data stored in an electroencephalography (EEG) monitor, which records brain activity and can sense if the operator notices the robot making a mistake in less than 30 milliseconds.

“A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars, and other technologies we haven’t even invented yet,” said CSAIL director Daniela Rus.

Previous research on EEG-controlled robotics required individuals to choose between  preconceived responses. But this study allowed participants to think without following set patterns. Faint brain signals called “error-related potentials”, which are generated whenever the mind notices a mistake, are registered using machine-learning algorithms.

“As you watch the robot, all you have to do is mentally agree or disagree with what it is doing,” said Dr. 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.”

So far the system can only handle activities which involve a binary choice, but the study suggests humans will soon be able to interact with robots in more intuitive ways. This could help give a voice to people unable to communicate verbally.

“This work brings us closer to developing effective tools for brain-controlled robots and prostheses,” said Wolfram Burgard, a computer scientist at the University of Freiburg. “Given how difficult it can be to translate human language into a meaningful signal for robots, work in this area could have a truly profound impact on the future of human-robot collaboration.”

A journalistic initiative
sponsored by:
  GO BACK