Representing and reasoning about object functionality: Towards an integrated approach

This work summarizes research which uses various aspects of functionality as a means to achieve generic object recognition. We examine several approaches which attempt to integrate computer vision and robotics for the purpose of achieving recognition of functional classes of objects. Such integrated approaches include those which incorporate both the knowledge of the potential functionality of an object and the steps to confirm said functionality through interaction. An overview of our system, GRUFF-I (Generic Recognition Using Form, Function and Interaction), is presented. This system reasons about and generates plans for interaction with 3-D shapes from the categories furniture and dishes.Book ChapterPublishedSeries in machine perception and artificial intelligence based on a workshop held 9/1-6/96, Schloss Dagstuhl, Germany