In the field of domestic robotics, having a rich representation of knowledge offers flexibility to the robotic platform. It is important for the robotic platform to have capabilities that use semantic knowledge about how household objects are related to each other and with respect to a human action. In this paper, we present a domain dependent framework for household environments which was constructed by extracting concepts and knowledge from the VirtualHome dataset. The framework recommends sequences of actions on how to perform human scaled tasks in a dynamic environment, answers questions about semantically related household objects, and performs semantic matching between entities from the web knowledge bases DBpedia, ConceptNet, and WordNet, with the ones existing in the local knowledge base. We offer a set of predefined SPARQL templates that directly address the ontology on which our framework is built, and querying capabilities through SPARQL. We evaluated our framework via two different user evaluations.
