Not even the Jetsons had one of these.
German and Japanese researchers have created a new robot that not only has a human face but can replicate realistic human expressions.
The new “Mask-bot” has a smooth, featureless face, onto which its creators can project any number of realistic human expressions. It can use any 2-D photo of a human face to create a lively 3-D face of its own, one that is capable of looking happy or sad, quiet or loud. It can also become a human avatar by projecting real-time video of a person’s face onto itself during teleconferences, or perhaps helping distant family or friends connect.
“Mask-bot will influence the way in which we humans communicate with robots in the future,” said Gordon Cheng, a neuroscientist at the Institute for Cognitive Systems at Technical University Munich in Germany.
Mask-bot doesn’t quite avoid the “uncanny valley” feeling caused by faces that only look partially human. Still, projecting realistic faces may be much easier compared with creating a fully robotic face that would require many motors to simulate different facial expressions.
This type of robot builds on a concept pioneered by Walt Disney, who created exhibits in his “Haunted Mansion” ride by projecting the scary faces of actors onto featureless busts from the front. Instead, Mask-bot researchers installed a small, strong projector inside the robot head that beams a human face onto the back of the mask.
The most immediate use of Mask-bot could arise during video conferences, where the device could be used as an alternative to having people watch one another on screens. “With Mask-bot, you can create a realistic replica of a person that actually sits and speaks with you at the conference table,” said Takaaki Kuratate, an engineer at Technical University Munich. “You can use a generic mask for male and female, or you can provide a custom-made mask for each person.”
Mask-bot can create its own face based on computer algorithms that select the best facial expressions from real human faces recorded through motion capture. And it can already speak anything typed by a keyboard in English and Japanese, with German next on the list. Emotion software helps lend the expression and voice nuances to indicate emotions.
But making Mask-bot the face for a semi-intelligent robot remains tricky, because it can’t yet interact normally through human conversation. It remains limited to certain responses based on fixed programming.
That has not stopped the German-Japanese team from pushing ahead. They are already planning their next-generation robot, which would have a mask, projector and computer control system all in one package.
And as for more personal usage? “These systems could soon be used as companions for older people who spend a lot of time on their own,” Kuratate suggested.
Mask-bot is the result of collaboration with AIST, the National Institute of Advanced Industrial Science and Technology in Japan.