Incremental grounded language learning in robot-robot interactions — Examples from spatial language

Abstract

This paper reports on models of the grounded co-acquisition of syntax and semantics of locative spatial language in developmental robots. We instantiate theories from Cognitive Linguistics and Developmental Psychology and show how a learner robot can learn to produce and interpret spatial utterances in guided-learning interactions with a tutor robot. Particular emphasis is put on the role of the tutor. Our experiments show that the learner rapidly becomes successful in communication given the right tutoring strategy and learning operators.