An Object Ontology Using Form-Function Reasoning to Support Robot Context Understanding

A robot that acts within an everyday environment needs a machine-understandable representation of objects and their features, shapes, and usages. We report on the development of a generic ontology of objects, and the use of this ontology to instantiate a knowledge base of everyday physical objects. Generic shape representation of objects and features is obtained through formfunction reasoning to deduce geometric shape requirements from an object’s mechanical and other functions, which supports object recognition. Associational knowledge between objects captures typical associations among groups of objects that are commonly used together, and associations between sets of objects and typical human activities, which supports context understanding.