The Talking AIBO
project investigates the mechanism that enables an autonomous robot to
learn how to use words in appropriate situations based on its social
and perceptual history. In the current experiments, an enhanced version
of AIBO -- Sony's four-legged robot -- tries to construct from scratch
the meaning of simple words uttered by humans. These words concern the
presence of objects (ball, red, etc), the behavior of the robot (walk,
sit) and the robot's body part (leg, head). These experiments show the
importance of grounding each word in its social and perceptual context
Related Publications
Steels, L. and Kaplan, F. (2000) AIBO's first words, the social
learning of language and meaning, Evolution of Communication, 4 (1):
3--32. [pdf]
This
paper explores the hypothesis that language communication in its very
first stage is bootstrapped in a social learning process under the
strong influence of culture. A concrete framework for social learning
has been developed based on the notion of a language game.
Autonomous robots have been programmed to behave according to this
framework. We show experiments that demonstrate why there has to be a
causal role of language on category acquisition; partly by showing that
it leads effectively to the bootstrapping of communication and partly
by showing that other forms of learning do not generate categories
usable in communication or make information assumptions which cannot be
satisfied.
)
