Robots are known for their precision, hence their proliferation in factory assembly lines. When something goes wrong, programmers are usually called in to fix the robots’ programming, to prevent it from messing up again.
But what if you could just tell the robot that it did a bad job? TechCruch reports that this is exactly what researchers from MIT’s CSAIL department are working on.
In the demonstration video, a human observer wears an EEG cap to measure his brainwaves. The robot then monitors these brainwaves before making a decision regarding its given task.
In this case, it’s segregating the paint cans from the spools of wire, and into their respective containers. The robot will monitor for signs that the human is doubting its choice, then adjust accordingly.
CSAIL research scientists Stephanie Gil says, “Being able to read the EG signals of the human and using that as a control signal to the robot will have an effect on the robot’s choice.”
“Whether or not the robot makes the right choice will have an effect on the human’s reactions,” she adds. “That’s a natural two-way communication or a conversation between humans or robots.”
It’s still far from a human having a witty repartee with an android butler, but it looks like the science for that is heading in the right direction. Alfred Bayle/JB