Automatic building Robot Technology ontology based on basic-level knowledge

Trung Lam Ngo, Haeyeon Lee, Makoto Mizukawa

    Research output: Contribution to journalArticle

    9 Citations (Scopus)

    Abstract

    When robot comes to our daily life, sharing knowledge is a key factor to realize the symbiosis between human and robot. In previous research, Robot Technology (RT) ontology was proposed as a knowledge base to help robot understands human's intention in daily activities. However, the method to build that ontology was not discussed. This paper presents our approach to build RT ontology based on basic-level knowledge. We proposed a new structure for RT ontology with Where, What, and How layers based on 4W1H. As for input data, we used educational books and MIT's ConceptNet. Our method is able to build RT ontology automatically by extracting objects and human activities from these data sources. We also implemented a weighting mechanism for the new ontology. Result shows that our method achieved better accuracy than conventional approach using Internet data.

    Original languageEnglish
    Pages (from-to)515-522
    Number of pages8
    JournalJournal of Robotics and Mechatronics
    Volume23
    Issue number4
    Publication statusPublished - 2011 Aug

    Fingerprint

    Ontology
    Robots
    Internet

    Keywords

    • Basic level knowledge
    • Common sense
    • Human robot interface
    • RT ontology

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Computer Science(all)

    Cite this

    Automatic building Robot Technology ontology based on basic-level knowledge. / Ngo, Trung Lam; Lee, Haeyeon; Mizukawa, Makoto.

    In: Journal of Robotics and Mechatronics, Vol. 23, No. 4, 08.2011, p. 515-522.

    Research output: Contribution to journalArticle

    Ngo, Trung Lam ; Lee, Haeyeon ; Mizukawa, Makoto. / Automatic building Robot Technology ontology based on basic-level knowledge. In: Journal of Robotics and Mechatronics. 2011 ; Vol. 23, No. 4. pp. 515-522.
    @article{79c4365f20cb4eb08b9c4bce206cd031,
    title = "Automatic building Robot Technology ontology based on basic-level knowledge",
    abstract = "When robot comes to our daily life, sharing knowledge is a key factor to realize the symbiosis between human and robot. In previous research, Robot Technology (RT) ontology was proposed as a knowledge base to help robot understands human's intention in daily activities. However, the method to build that ontology was not discussed. This paper presents our approach to build RT ontology based on basic-level knowledge. We proposed a new structure for RT ontology with Where, What, and How layers based on 4W1H. As for input data, we used educational books and MIT's ConceptNet. Our method is able to build RT ontology automatically by extracting objects and human activities from these data sources. We also implemented a weighting mechanism for the new ontology. Result shows that our method achieved better accuracy than conventional approach using Internet data.",
    keywords = "Basic level knowledge, Common sense, Human robot interface, RT ontology",
    author = "Ngo, {Trung Lam} and Haeyeon Lee and Makoto Mizukawa",
    year = "2011",
    month = "8",
    language = "English",
    volume = "23",
    pages = "515--522",
    journal = "Journal of Robotics and Mechatronics",
    issn = "0915-3942",
    publisher = "Fuji Technology Press",
    number = "4",

    }

    TY - JOUR

    T1 - Automatic building Robot Technology ontology based on basic-level knowledge

    AU - Ngo, Trung Lam

    AU - Lee, Haeyeon

    AU - Mizukawa, Makoto

    PY - 2011/8

    Y1 - 2011/8

    N2 - When robot comes to our daily life, sharing knowledge is a key factor to realize the symbiosis between human and robot. In previous research, Robot Technology (RT) ontology was proposed as a knowledge base to help robot understands human's intention in daily activities. However, the method to build that ontology was not discussed. This paper presents our approach to build RT ontology based on basic-level knowledge. We proposed a new structure for RT ontology with Where, What, and How layers based on 4W1H. As for input data, we used educational books and MIT's ConceptNet. Our method is able to build RT ontology automatically by extracting objects and human activities from these data sources. We also implemented a weighting mechanism for the new ontology. Result shows that our method achieved better accuracy than conventional approach using Internet data.

    AB - When robot comes to our daily life, sharing knowledge is a key factor to realize the symbiosis between human and robot. In previous research, Robot Technology (RT) ontology was proposed as a knowledge base to help robot understands human's intention in daily activities. However, the method to build that ontology was not discussed. This paper presents our approach to build RT ontology based on basic-level knowledge. We proposed a new structure for RT ontology with Where, What, and How layers based on 4W1H. As for input data, we used educational books and MIT's ConceptNet. Our method is able to build RT ontology automatically by extracting objects and human activities from these data sources. We also implemented a weighting mechanism for the new ontology. Result shows that our method achieved better accuracy than conventional approach using Internet data.

    KW - Basic level knowledge

    KW - Common sense

    KW - Human robot interface

    KW - RT ontology

    UR - http://www.scopus.com/inward/record.url?scp=84863037068&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84863037068&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:84863037068

    VL - 23

    SP - 515

    EP - 522

    JO - Journal of Robotics and Mechatronics

    JF - Journal of Robotics and Mechatronics

    SN - 0915-3942

    IS - 4

    ER -