A robot that can be controlled using thoughts has been created by researchers at MIT
The mind control robot responds to commands triggered by thinking, rather than electronic or voice commands.
The robot, designed by researchers at MIT’s Computer Science and Artificial Intelligence Laboratory, can understand signals from a human connected to an ECG machine and respond to negative signals regarding its actions.
The MIT CSAIL researchers designed the robot, called Baxter, to sort objects into two categories, paint and wire, with instruction from a human’s brain. It chose to place objects into the two boxes, but changed its mind when it received feedback from the connected human that it was doing something wrong.
“As you watch the robot, all you have to do is mentally agree or disagree with what it is doing,” said Daniela Rus, director of MIT CSAIL. “You don’t have to train yourself to think in a certain way, the machine adapts to you.”
The researchers hope the though-control technology could be applied to a range of robotics, including manufacturing robots and self-driving cars. It could also be used to control prosthetic limbs or in communications tools.
“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,” said Rus. “A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars and other technologies we haven’t even invented yet.”
The system also includes the ability for the robot to ask a human for advice if it’s unsure about its decision; ‘The robot gets embarrassed when it makes an incorrect decision’. This opens up a dialogue between the human and machine through constant yes or no feedback.Connected to the robot via an ECG machine, a negative thought from the human triggered an almost instantaneous reaction.
“This work brings us closer to developing effective tools for brain-controlled robots and prostheses,” said Wolfram Burgurd, an independent computer science professor 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.”
By Cara McGoogan