Automated ontology framework for service robots

Abstract

Abstract-This paper presents an automated ontology framework for service robots. The framework is designed to automatically create an ontology and an instance of concept in dynamic environment. Ontology learning from text is applied to build a concept hierarchy using WordNet which provides a rich semantic processing for physical objects. The Automated Ontology is composed of four modules: Concept Creation, Property Creation, Relationship Creation and Instance of Concept Creation. The automated ontology algorithm was implemented in order to create the concept hierarchy in the Robot Ontology. The Semantic Knowledge Acquisition represents knowledge of physical objects in dynamic environments. In simulation experiments, the list of object names and property names was identified. The result shows the concept hierarchy which represents explicit terms and the semantic knowledge of physical objects for performing everyday manipulation tasks.

Commonsense knowledge in cognitive robotics: a systematic literature review

“…Generate and execute a cooking plan based on the current environment and a requested meal • Environment Exploration (Pangercic et al, 2012;Kanjaruek et al, 2015;Jäger et al, 2018;Vassiliades et al, 2020;Zhang et al, 2021): Interacting with parts of the environment (objects, doors, cupboards, etc.) to gather (new) knowledge • Hole Digging (Javed et al, 2016): Dig a hole in the garden • Intention Inference (Liu et al, 2015;Liu and Zhang, 2016;De Silva et al, 2022): Identify the intention of a human with a certain object/command to react fittingly when the command cannot be executed (e.g., the robot should fetch the human some juice, which is not available.…”