Ontology Modeling and Storage System for Robot Context Understanding

Abstract

A mobile robot that interacts with its environment needs a machine-understandable representation of objects and their usages. We present an ontology of objects, with generic shape representations obtained through form-function reasoning. Sets of objects are associated with typical human activities, which supports context understanding. We describe an efficient ontology document storage system, which is based on stable and well-known relational databases. We first design a relational data schema appropriate for Web Ontology Language (OWL) documents, and then develop a transformation mechanism from OWL documents to the relational schema.