Situated Structure Learning of a Bayesian Logic Network for Commonsense Reasoning

TL;DR

This paper presents an algorithm for automatically creating a context-aware Bayesian Logic Network to enhance robotic commonsense reasoning, enabling better object understanding and task repair in household environments.

Contribution

It introduces a situated structure learning method combining ConceptNet and WordNet to generate context-relevant knowledge networks for robots.

Findings

Accurately predicts object categories, locations, and properties

Effective in three household scenarios

Enhances robotic reasoning and task repair

Abstract

This paper details the implementation of an algorithm for automatically generating a high-level knowledge network to perform commonsense reasoning, specifically with the application of robotic task repair. The network is represented using a Bayesian Logic Network (BLN) (Jain, Waldherr, and Beetz 2009), which combines a set of directed relations between abstract concepts, including IsA, AtLocation, HasProperty, and UsedFor, with a corresponding probability distribution that models the uncertainty inherent in these relations. Inference over this network enables reasoning over the abstract concepts in order to perform appropriate object substitution or to locate missing objects in the robot's environment. The structure of the network is generated by combining information from two existing knowledge sources: ConceptNet (Speer and Havasi 2012), and WordNet (Miller 1995). This is done in a "situated" manner by only including information relevant a given context. Results show that the generated network is able to accurately predict object categories, locations, properties, and affordances in three different household scenarios.