Intuitive Linguistic Joint Object Reference In Human-Robot Interaction

Abstract

The visionary goal of an easy to use service robot implies in-tuitive styles of interaction between humans and robots. Such natural interaction can only be achieved if means are found to bridge the gap between the forms of object perception and spatial knowledge maintained by such robots, and the forms of language, used by humans, to communicate such knowl-edge. Part of bridging this gap consists of allowing user and robot to establish joint reference on objects in the environ-ment- without forcing the user to use unnatural means for object reference. We present an approach to establishing joint object reference which makes use of natural object classification and a com-putational model of basic intrinsic and relative reference sys-tems. Our object recognition approach assigns natural cate-gories (e.g. ”desk”, ”chair”, ”table”) to new objects based on their functional design. With basic objects within the envi-ronment classified, we can then make use of a computational reference model, to process natural projective relations (e.g. “the briefcase to the left of the chair”), allowing users to refer to objects which cannot be classified reliably by the recogni-tion system alone.