A robot at MIT can successfully sort objects (in this case, cans of spray paint vs spools of wire) by analyzing the brain of a person watching for a particular brainwave that indicates you think it's about to make a mistake. Me? I think robots are always making mistakes. "By existing." Exactly, robots should have never been allowed to develop past those little mechanical claws-on-a-stick you can use to pick up things without bending over.
MIT...focused on measuring one particular type of brainwave: error-related potentials (or ErrP) signals. These faint electrical impulses appear when we recognize something is wrong. Researchers placed subjects in front of a robot arm, tasked with grabbing one of two objects. The correct object would illuminate with an LED that the robot didn't see. And as the robot reached, the subject would automatically think whether that was the right decision or wrong one.
In just 10-30ms, researchers were able to recognize the person's ErrPs about 65% of the time. In other words, they could feasibly stop a robot from making a bad decision in its tracks a majority of the time--simply by watching its behavior.
Wait -- so they're only accurate 65% of the time? That's barely over half. The robot might as well just flip a coin. And let's say researchers are able to push the robot's accuracy higher -- it's only a matter of time before these robots learn to actually DO the thing we think is wrong (i.e. kill you), and TA-DA, we're knee deep in the robot apocalypse wading through the bodies of our fallen neighbors, trying to find safe passage out of the city. I've seen movies before, I know how this shit works.
Keep going for a video of the robot doing its thing (in this case constantly questioning if it's making the right decision, just like us).
Thanks to hairless, who agrees the only use of a mind-controlled robot is convincing it to self destruct itself from a safe distance.