An Ontology Framework for Human-Robot Interoperability in Dynamic Construction Environments

November 22, 2024

Context

Main Contribution

Construction Sliding Work Sharing (CSWS) Ontology

  • Design and implementation of a novel ontology combining:
    1. Human-Robot Interoperability
    2. Construction Environments

Sliding Work Sharing

(AI4Work Consortium 2024)

Sliding Work Sharing

(AI4Work Consortium 2024)

Sliding Work Sharing

(AI4Work Consortium 2024)

Sliding Work Sharing

(AI4Work Consortium 2024)

Dynamic Construction Environments

  • Low adoption of I4.0 and I5.0 practices.
    • Stringent regulation.
    • Demanding safety requirements.
    • Low worker acceptability rates
  • Highly heterogeneous and dynamic application sites
    • Low solution generalizability
    • Low trust

Previous Work

Design

Methodology

Methodology

Methodology

Case Study

Data

Interviews

  • Five independent sessions
  • Semi-structured format
  • Domain industry experts
  • Technology providers from AI4Work consortium
  • Duration: 45-60 minutes
  • Transcribed and anonymized
  • Auxiliary data: project documentation, meeting observations, and pilot reports

Experts selection

Criterion Expert Attributes
Stakeholder Involvement Direct involvement in highly representative scenaria, ensuring firsthand experience and knowledge.
Expertise Relevance Expertise in critical research areas, human-robot interaction and BIM integration.
Organizational Diversity Role-specific insights, such as technical, operational, and academic.
Interdisciplinary Focus Capacity to discuss the integration of different technological and methodological approaches.

Coding

  • Following the iterative process proposed by Fernández-López, Gómez-Pérez, and Juristo Juzgado (1997)
  • Open coding \(\to\) Triangulation \(\to\) Axial coding \(\to\) Triangulation \(\to\) Selective coding

Implementation

Overview

Figure 1: Classes
Figure 2: Object Properties
Figure 3: Data Properties
Figure 4: Instances

An More Detailed Example

Evaluation

  • Logical consistency
    • Pellet, FACT++, and ELK.
  • Literature triangulation
  • Pending (subsequent pilot phases)
    • Functional evaluation

Using the Ontology

Query for non-addressed errors

SELECT ?error ?sensor 
WHERE {
  ?error a :Error .
  ?error :detectedBySensor ?sensor .

  FILTER NOT EXISTS { ?error :handledByHuman ?agent }
}
user@space$

Query for non-addressed errors

SELECT ?error ?sensor 
WHERE {
  ?error a :Error .
  ?error :detectedBySensor ?sensor .

  FILTER NOT EXISTS { ?error :handledByHuman ?agent }
}
user@space$
# Query Results:
# |   | error   | sensor   |
# | 1 | :Error2 | :Sensor1 |
user@space$

Query for agents’ safety

SELECT ?agent ?procedure
WHERE {
  ?agent a/rdfs:subClassOf* :Actor .
  ?procedure a :IfcProcedure .
  ?procedure :ensuresSafetyFor ?agent .
}
user@space$

Query for agents’ safety

SELECT ?agent ?procedure
WHERE {
  ?agent a/rdfs:subClassOf* :Actor .
  ?procedure a :IfcProcedure .
  ?procedure :ensuresSafetyFor ?agent .
}
user@space$
# Query Results:
# |   | agent   | procedure      |
# | 1 | :Human2 | :IfcProcedure2 |
# | 2 | :Robot1 | :IfcProcedure2 |
# | 3 | :Human1 | :IfcProcedure1 |
user@space$

Query for task and robot pairs

SELECT ?task ?robot ?confidenceLevel ?autonomyLevel
WHERE {
  ?task a :IfcTask .
  ?task :assignedToActor ?robot .
  ?robot a :RobotActor .
  ?robot :hasConfidence ?confidenceLevel .
  ?robot :hasAutonomy ?autonomyLevel .

  FILTER ((?confidenceLevel = :ConfidenceConfident &&
           ?autonomyLevel = :AutonomyFully) ||
          (?confidenceLevel = :ConfidenceSemiConfident &&
     ?autonomyLevel = :AutonomyPartially) ||
    (?confidenceLevel = :ConfidenceNotConfident &&
     ?autonomyLevel = :AutonomyNone))
}
user@space$

Query for task and robot pairs

SELECT ?task ?robot ?confidenceLevel ?autonomyLevel
WHERE {
  ?task a :IfcTask .
  ?task :assignedToActor ?robot .
  ?robot a :RobotActor .
  ?robot :hasConfidence ?confidenceLevel .
  ?robot :hasAutonomy ?autonomyLevel .

  FILTER ((?confidenceLevel = :ConfidenceConfident &&
           ?autonomyLevel = :AutonomyFully) ||
          (?confidenceLevel = :ConfidenceSemiConfident &&
     ?autonomyLevel = :AutonomyPartially) ||
    (?confidenceLevel = :ConfidenceNotConfident &&
     ?autonomyLevel = :AutonomyNone))
}
user@space$
# Query Results:
# |   | task   | robot   | confidenceLevel          | autonomyLevel      |
# | 1 | :Task1 | :Robot1 | :ConfidenceConfident     | :AutonomyFully     |
# | 2 | :Task2 | :Robot2 | :ConfidenceSemiConfident | :AutonomyPartially |
user@space$

An Ontology Framework for Human-Robot Interoperability in Dynamic Construction Environments

  • Design an implementation of a novel CSWS ontology for HRI in construction environments.
  • Domain knowledge from a KUKA case study.
  • Incorporates Sliding Work Sharing as a design objective.
  • Emphasizes human-centric I5.0 concepts.
  • Bridges the gap between HRI and construction specializing ontologies.

References

AI4Work Consortium. 2024. AI4Work Concept.” D1.2.
Baghalzadeh Shishehgarkhaneh, Milad, Afram Keivani, Robert C. Moehler, Nasim Jelodari, and Sevda Roshdi Laleh. 2022. “Internet of Things (IoT), Building Information Modeling (BIM), and Digital Twin (DT) in Construction Industry: A Review, Bibliometric, and Network Analysis.” Buildings 12 (10): 1503. https://doi.org/10.3390/buildings12101503.
Bayat, Behzad, Julita Bermejo-Alonso, Joel Carbonera, Tullio Facchinetti, Sandro Fiorini, Paulo Goncalves, Vitor A. M. Jorge, et al. 2016. “Requirements for Building an Ontology for Autonomous Robots.” Industrial Robot: An International Journal 43 (5): 469–80. https://doi.org/10.1108/IR-02-2016-0059.
El Asri, Hayat, Fatine Jebbor, and Laila Benhlima. 2021. “Building a Domain Ontology for the Construction Industry: Towards Knowledge Sharing.” In Digital Technologies and Applications, edited by Saad Motahhir and Badre Bossoufi, 1061–71. Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-73882-2_97.
Farghaly, Karim, Ranjith K. Soman, and Shanjing Alexander Zhou. 2023. “The Evolution of Ontology in AEC: A Two-Decade Synthesis, Application Domains, and Future Directions.” Journal of Industrial Information Integration 36 (December): 100519. https://doi.org/10.1016/j.jii.2023.100519.
Fernández-López, M., A. Gómez-Pérez, and Natalia Juristo Juzgado. 1997. METHONTOLOGY: From Ontological Art Towards Ontological Engineering.” In Proceedings of the Ontological Engineering AAAI-97 Spring Symposium Series. American Asociation for Artificial Intelligence.
Hall, Stephanie, Mandeep Dhanda, and Vimal Dhokia. 2024. “Towards an Ontology to Capture Human Attributes in Human-Robot Collaboration.” Proceedings of the Design Society 4 (May): 2585–94. https://doi.org/10.1017/pds.2024.261.
Jorge, Vitor A. M., Vitor F. Rey, Renan Maffei, Sandro Rama Fiorini, Joel Luis Carbonera, Flora Branchi, João P. Meireles, et al. 2015. “Exploring the IEEE Ontology for Robotics and Automation for Heterogeneous Agent Interaction.” Robotics and Computer-Integrated Manufacturing 33 (June): 12–20. https://doi.org/10.1016/j.rcim.2014.08.005.
Simeone, Davide. 2021. CON-TEND: An Ontology for Knowledge Reuse in Construction Tendering.” In 2021 European Conference on Computing in Construction, 115–22. https://doi.org/10.35490/EC3.2021.190.
Sun, Xiaolei, Yu Zhang, and Jing Chen. 2019. RTPO: A Domain Knowledge Base for Robot Task Planning.” Electronics 8 (10): 1105. https://doi.org/10.3390/electronics8101105.
Xing, Xuejiao, Botao Zhong, Hanbin Luo, Heng Li, and Haitao Wu. 2019. “Ontology for Safety Risk Identification in Metro Construction.” Computers in Industry 109 (August): 14–30. https://doi.org/10.1016/j.compind.2019.04.001.
Zhou, Zhipeng, Yang Miang Goh, and Lijun Shen. 2016. “Overview and Analysis of Ontology Studies Supporting Development of the Construction Industry.” Journal of Computing in Civil Engineering 30 (6): 04016026. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000594.