Functional Object-Oriented Network: Construction & Expansion

TL;DR

This paper enhances the functional object-oriented network (FOON) by introducing methods for generalizing knowledge through object similarity and category-based compression, improving retrieval performance across diverse sources.

Contribution

It proposes two novel generalization techniques—network expansion via object similarity and functional unit compression by categories—to improve FOON's knowledge retrieval.

Findings

Expansion improves retrieval accuracy with similar objects.

Category-based compression reduces network complexity.

Generalization methods outperform manual annotation approaches.

Abstract

We build upon the functional object-oriented network (FOON), a structured knowledge representation which is constructed from observations of human activities and manipulations. A FOON can be used for representing object-motion affordances. Knowledge retrieval through graph search allows us to obtain novel manipulation sequences using knowledge spanning across many video sources, hence the novelty in our approach. However, we are limited to the sources collected. To further improve the performance of knowledge retrieval as a follow up to our previous work, we discuss generalizing knowledge to be applied to objects which are similar to what we have in FOON without manually annotating new sources of knowledge. We discuss two means of generalization: 1) expanding our network through the use of object similarity to create new functional units from those we already have, and 2) compressing the functional units by object categories rather than specific objects. We discuss experiments which compare the performance of our knowledge retrieval algorithm with both expansion and compression by categories.