Humanoid robots freak people out!

“Regarding appearance, as other studies already showed, the humanoid option is not a good one”

Ok, so this is a study from 2008, which immediately makes me think I should have found it ages ago, but BotJunkie only got hold of it this year, so maybe I’m not that far behind the times.  In common with the Evan Ackermann I have been spending a lot of time (a LOT of time, some would say too long) “wondering why robotics researchers persist in designing humanoid robots specifically for domestic applications…” and, of course, my answer is becoming tinged with communication theory.

I would therefore argue that one of the drivers behind the design of humanoid robots is the expectation, which was identified in this research paper, that robots need to communicate in humanlike ways.  In terms of the effect on robot design, this assumption encourages the development of robot with expressive faces, although these faces can range from being very humanlike (as seen in Jules, erm, and Eva, although you may have some misgivings there) to more of a mechanical cartoon (as seen in Kismet pictured below).

Kismet

Maybe this design decision is popular because developing robots that can understand and produce human language really well is still pretty hard to achieve, and the provision of facial expressions offers an alternative way to provide more humanlike communication.  Maybe even with more complete language capabilities roboticists will still think expressive faces add value.

From a personal perspective I’m really not drawn in by such faces on robots.  In many ways I find them pretty off-putting, and I’d be really interested to see more designs that work with movement and sound (and possibly even light) to provide a more “machinelike” communicative feedback that is nonetheless understandable to humans.