A dialogue approach to learning object descriptions and semantic categories

摘要

Acquiring new knowledge through interactive learning mechanisms is a key ability for humanoid robots in a natural environment. Such learning mechanisms need to be performed autonomously, and through interaction with the environment or with other agents/humans. In this paper, we describe a dialogue approach and a dynamic object model for learning semantic categories, object descriptions, and new words acquisition for object learning and integration with visual perception for grounding objects in the real world. The presented system has been implemented and evaluated on the humanoid robot Armar III.