First International Symposium on
30th - 31st January 2004, Villa Nobel, Sanremo, Italy

Social Robots: Balancing Function & Form

Brian Duffy
MIT-Media Lab Europe, Dublin, Ireland

Unquestioningly, the holy grail for roboticists has been to realise a humanoid robot that is indistinguishable from ourselves. Intuitively, social robots may seem more socially acceptable if they are built in our own image.

However, this does not necessarily imply that they must be indistinguishable from ourselves. As yet, given the limitations of the state of the art in social robotics, we can easily feel more comfortable with a cartoon-like appearance than imperfect realism. While anticipating that future technologies may allow us to achieve more human-like function and form, is this really the ultimate design goal that we would like to achieve? From a technological standpoint, can building a mechanistic digital synthetic version of man be anything less than a cheat when man is not mechanistic, digital nor synthetic?

We know we tend to anthropomorphise and project onto entities that may bear only the slightest resemblance to ourselves. Thus a successfully designed social robot may be one that maximises both its mechanical advantages and the minimum aspects required for their social acceptance. Our future interaction with robots will undoubtedly use alternate features than those we are familiar with in our interactions with people.

The ability of a robot to garner bio information and use sensor fusion in order to augment its diagnosis of the human's emotional state through for example, a "techno handshake" illustrates how a machine can obtain social information about people in its social space. This strategy effectively increases people's perception of the social robot's "emotional intelligence", and consequently its social integration.

Draft 18th Jan '04