Page 51 - Read Online

Bernardo et al. Intell Robot 2021;1(2):116-30 Intelligence & Robotics
DOI: 10.20517/ir.2021.10

Research Article Open Access

Planning robotic agent actions using semantic knowl-
edge for a home environment

1
Rodrigo Bernardo 1,2 , João M. C. Sousa , Paulo J. S. Gonçalves 2
1 IDMEC, Mechanical Engineering Department, Instituto Superior Técnico, University of Lisbon, Lisbon, Lisbon 1049-001, Portugal.
2 Industrial Engineering Department, Polytechnic Institute of Castelo Branco, Castelo Branco, AV. Empresário, Castelo Branco
6000-767, Portugal.

Correspondence to: Dr. Rodrigo Bernardo, IDMEC, Mechanical Engineering Department, Instituto Superior Técnico, University of
Lisbon, Av. Rovisco Pais, 1 1049-001 Lisbon, Portugal. E-mail: rodrigo.f.bernardo@tecnico.ulisboa.pt
How to cite this article: Bernardo R, Sousa JMC, Gonçalves PJS. Planning robotic agent actions using semantic knowledge for a
home environment. Intell Robot 2021;1(2):116-30. http://dx.doi.org/10.20517/ir.2021.10

Received: 14 Sep 2021 First Decision: 28 Oct 2021 Revised: 11 Nov 2021 Accepted: 11 Nov 2021 Published: 15 Dec 2021

Academic Editors: Shaidah Jusoh, Simon X. Yang Copy Editor: Huan-Liang Wu Production Editor: Huan-Liang Wu

Abstract
Autonomous mobile robotic agents are increasingly present in highly dynamic environments, thus making the plan-
ning and execution of their tasks challenging. Task planning is vital in directing the actions of a robotic agent in
domains where a causal chain could lock the agent into a dead-end state. This paper proposes a framework that in-
tegrates a domain ontology (home environment ontology) with a task planner (ROSPlan) to translate the objectives
coming from a given agent (robot or human) into executable actions by a robotic agent.

Keywords: Ontologies, autonomous robotics, planning, knowledge representation,semantic maps

1. INTRODUCTION
Robots are increasingly present in environments shared with humans and highly dynamic environments [1,2] .
It is therefore imperative to study and develop new techniques so that robots can effectively move, locate
themselves, detect objects, perform tasks, etc. in places that can change rapidly, in an autonomous way. More
complex methodologies require systems capable of deliberating quickly and effectively. Several studies point
to the need for knowledge as way to address this challenges [3,4] . Therefore the formal conceptualization of the
robotics domain is an essential requirement for the future of robotics, to design robots that can autonomously
[5]
perform a wide variety of tasks in a wide variety of environments .

© The Author(s) 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, shar­
ing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you
give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate
if changes were made.

www.intellrobot.com