Welcome to the fascinating world of robotics. A world where nothing is impossible. It is just a little longer to get there, that's all! Even building an Einstein robot that teaches itself how to mimic basic facial expressions. Yes, you heard me, an Einstein robot. Why not Tesla? I have no idea, but honestly it is a pretty scary image. It seems the scientists from the Machine Perception Laboratory at the University of California have managed to teach a robot how to mimic human facial expressions using machine learning.

Why they put realistic looking skin over its steel head and a female wig on top in order to make it look like a professor Einstein with an identity issue, I have no idea. The result is as scary as it is remarkable. According to Wired Science, in order for the robot to know the right expression, a camera was wired to it and gave it a reward signal every time it made a facial movement that resembled that of a person.

Go figure, I can't help thinking this is like Project Natal for robots. Mimic a happy face, get 500 points. Collect all 10,000 points and get a real life human as your pet! I generally tend to stay away from corny Terminator jokes, but hasn't anyone figured the real use for this robot yet? Put Arnold Schwarzenegger's face on it, make it say “I'll be back” and use it in a Terminator advertisement. Make money off of it!

Jokes aside, however, social development expert Daniel Messinger at the University of Miami (a person that is involved with the group in another project) said that “The robotic approach is the ultimate in helping us understand learning and development. […] There’s so much we can learn by actually trying to make it happen instead of just watching kids try to move their faces — it’s like having a baby as opposed to just watching a baby.”

Just pray one of these things doesn't show up at your front door saying “Hasta la vista, baby!”


We are just a few, but there are many of you, Softpedia users, out there. That's why we thought it would be a good idea to create an email address for you to help us a little in finding gadgets we missed. Interesting links are bound to be posted with recognition going mainly to those who submit. The address is .