Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects

TL;DR

This paper introduces Analytic Ontology Templates (AOT) and AOTNet to enable machines to understand and interact with articulated objects at a conceptual level, without relying on real training data.

Contribution

We propose a novel parameterized, differentiable program framework (AOT) for generalized conceptual ontologies and a baseline method (AOTNet) to discover structural and affordance knowledge of articulated objects.

Findings

AOTNet achieves concept-level understanding without real training data.

The approach provides analytic structure information.

It effectively discovers object structure and affordance for interaction.

Abstract

Human cognition can leverage fundamental conceptual knowledge, like geometric and kinematic ones, to appropriately perceive, comprehend and interact with novel objects. Motivated by this finding, we aim to endow machine intelligence with an analogous capability through performing at the conceptual level, in order to understand and then interact with articulated objects, especially for those in novel categories, which is challenging due to the intricate geometric structures and diverse joint types of articulated objects. To achieve this goal, we propose Analytic Ontology Template (AOT), a parameterized and differentiable program description of generalized conceptual ontologies. A baseline approach called AOTNet driven by AOTs is designed accordingly to equip intelligent agents with these generalized concepts, and then empower the agents to effectively discover the conceptual knowledge on the structure and affordance of articulated objects. The AOT-driven approach yields benefits in three key perspectives: i) enabling concept-level understanding of articulated objects without relying on any real training data, ii) providing analytic structure information, and iii) introducing rich affordance information indicating proper ways of interaction. We conduct exhaustive experiments and the results demonstrate the superiority of our approach in understanding and then interacting with articulated objects.