Going face-to-face with Mask-bot. Is this what the video conference of the future will look like?
(Credit: Uli Benz/TU Muenchen)
Let's face it. Disembodied robot heads have not yet reached their maximum potential. They can sing and chat and channel your personality post-mortem, but they don't always look particularly human doing so.
Uncanny-Valley problem meet solution--in the form of a plastic head called Mask-bot.
To make Mask-bot, researchers from the Technische Universitat Munchen in Germany, along with Japanese and Australian scientists, eschewed traditional robotic-realism methods of placing motors under artificial skin. Instead, they used a small, powerful projector to beam the 3D image of a face onto the back of a transparent mask, and a computer to control the voice and facial expressions.
Foremost, the researchers hope to give future robots a more human face. But they also imagine their method being used to create avatars for video conferences, and possibly even to keep isolated seniors company.
The real terror fun here, of course, is that the projected face can belong to anyone, even you. All it really takes is a 2D photo, which a new program developed by the researchers can convert into a properly proportioned projection for a 3D mask.
Here, a projector beams a 3D image of a face onto the back of a transparent plastic mask, while a computer controls the voice and facial expressions.
(Credit: Uli Benz/Technical University of Munich)
You may have seen faces projected onto the front of masks before (in Walt Disney's Haunted Mansion, for example, or in your nightmares). The makers of Mask-bot, however, use on-board rear projection positioned behind the mask to create more realistic, less cartoon-ey features that can be seen from various angles, including the side.
Take video conferences. While participants in such sitdowns are usually displayed onscreen, 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, one of the researchers who worked on the project. "You can use a generic mask for male and female, or you can provide a custom-made mask for each person." Think head on a platter.
But how does the head do the talking and reacting? A text-to-speech setup converts text to audio signals with the touch of a button. A "talking head animation engine" uses data collected by a motion capture system to match nuanced facial expressions to a male or female voice set to quiet, loud, happy, or sad--or in our case, a tad flummoxed.
This is dummy text. It is not meant to be read. Accordingly, it is difficult to figure out when to end it. But then, this is dummy text. It is not meant to be read. Period.
ConversionConversion EmoticonEmoticon