Page 27 - Read Online
P. 27
Bernardo et al. Intell Robot 2021;1(2):116-30 I http://dx.doi.org/10.20517/ir.2021.10 Page 120
thus to longer live an independent life in their known surroundings. They are also there to help better maintain
social contacts, which is known to have a very positive influence on the mental and physical health of elderly
people. An initial and extensible list of tasks that these robots are eventually supposed to perform includes the
following activities:
• Help elderly people out of bed and or the couch.
• Serve the breakfast.
• Supply elderly people medicine.
• Bring books or operate media (entertainment).
• Make up the bedroom.
• Play games.
• Adjust settings: shades, light, and heat.
• Serve drinks.
• Assist during bathing.
• Clean the rooms.
When developing the ontology, several concepts were searched in databases such as dictionaries on the web.
The search was carried out on specific sections on the different concepts of a house (https://www.enchantedlea
rning.com/wordlist/house.shtml, https://dictionary.cambridge.org/pt/topics/buildings/houses-and-homes/).
It was also extracted from the documentation of the project RoCKIn@Home challenge (http://rockinrobotcha
llenge.eu/home.php, http://rockinrobotchallenge.eu/RoCKIn_D2.1.1.pdf), concepts and typical tasks for a do-
mestic robot. The concepts were chosen in order to characterize the simplified environment of a house, based
on a smart-home environment, built on the robotics laboratory of Instituto Politécnico de Castelo Branco. A
challenge arose in the choice of concepts due to the great complexity of objects that can be found in a given
room. To simplify the process, the concepts were defined for characterizing the simplified environment that
is found in the laboratory.
3.1. Knowledge Engine
Figure 1 depicts the global knowledge engine conceptual framework, designed to achieve the main objective
of the paper: the integration of a domain specific home environment ontology, with a task planner (ROSPlan),
transformingthegoalscomingfromthereasoningintoexecutableactionsbytheroboticagent. Theframework
have three main parts: reasoning (which includes the ontologies), planning, and the robot. These parts are
presented in the remainder of the paper.
A domain specific home environment ontology, aligned with a MongoDB database, encapsulate the important
concepts of the domain to be considered (space of a house, objects, etc.). Indeed, the main benefit of a domain
ontology is to set standard definitions of shared concepts identified in the requirement phase and to define
appropriate relations between the concepts and their properties [40] . The ontology contain concepts of Core
Ontology for Robotics and Automation (CORA), with the representation of fundamental concepts of robotics
and automation [41] .
Theontologymodelisbasedontheconceptsandrelationshipsbetweendifferententities, andthenalignedwith
the MongoDB database. The basic concept of the reasoning process is based on the premises that: a relational
database contains both the entities of the conceptual hierarchy and the instances of the physical hierarchy, this
information is stored in lists, and these lists are related to each other, as in the entity–relationship model of the
environment [42,43] .
The domain specific ontology home environment is defined with the Protégé software. Protégé version 5.5.0
was used [44] . The the domain ontology was verified through version 1.4.3 of HermiT Reasoner to ensure that
it is free of inconsistencies [45] . Protégé is a free, open-source editor for developing the ontologies produced by