Page 35 - Read Online

Bernardo et al. Intell Robot 2021;1(2):116-30 I http://dx.doi.org/10.20517/ir.2021.10 Page 128

The proposed framework improves the problem specification in PDDL based on the updated information
coming from the ontology, making the generated plan more efficient. For example, if an external agent (robot
or human) launches a task for the robotic agent to collect a certain object and transport it to a specific location,
the ontology will be queried. As such, the problem in PDDL is written with specific information, such as the
relations between objects, relations between objects and the environment, the current location of the robot,
and so on.

The developed home environment ontology was validated by performing successful queries to it, using a stan-
dard reasoner in Protégé. The concepts within the home environment ontology, used to define the MongoDB
database, were experimentally validated, for semantic reasoning in the the home environment of the labora-
tory. Moreover, the ROSPlan, together with the developed interface actions, was shown to be a very efficient
approach, in interfacing the low-level control with the semantic reasoning of the robot agent.

In future work, the developed domain ontology will be aligned with upper ontologies, e.g., DOLCE. Further
developments will be pursued to speed up the ontology-based approach, by exploring ways to make querying
moreefficient bysolving the limitationpresented in other works [43] , where it is pointed out thatthese solutions
are slower than the pure database approaches.

DECLARATIONS

Authors’ contributions
Implemented the methodologies presented and wrote the paper: Rodrigo Bernardo
Developed the idea of the proposed framework: Rodrigo Bernardo, Paulo J. S.Gonçalves
Managed and supervised the research project: João M. C. Sousa , Paulo J. S.Gonçalves
All authors have revised the text and agreed to the published version of the manuscript.

Availability of data and materials
Themaindatasupportingtheresultsinthisstudyareavailablewithinthepaper. Therawdatasetsherereported
will be available upon request.

Financial support and sponsorship
This work is financed by national funds through FCT - Foundation for Science and Technology, I.P., through
IDMEC, under LAETA, project UIDB/50022/2020. The work of Rodrigo Bernardo was supported by the PhD
Scholarship BD\6841\2020 from FCT. This work has indirectly received funding from the European Union’s
Horizon 2020 programme under StandICT.eu 2023 (under Grant Agreement No.: 951972).

Conflicts of interest
All authors declared that there are no conflicts of interest.

Ethical approval and consent to participate
Not applicable.

Consent for publication
Not applicable.

Copyright
© The Author(s) 2021.