Ambiguous command understanding with commonsense

Lam Trung Ngo, Yoshio Maeda, Haeyeon Lee, Makoto Mizukawa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the Bring something service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.

    Original languageEnglish
    Title of host publicationProceedings - IEEE International Workshop on Robot and Human Interactive Communication
    Pages545-550
    Number of pages6
    DOIs
    Publication statusPublished - 2012
    Event2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012 - Paris
    Duration: 2012 Sep 92012 Sep 13

    Other

    Other2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012
    CityParis
    Period12/9/912/9/13

    Fingerprint

    Robots
    Gesture recognition
    Ontology
    Robotics
    Experiments

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence
    • Human-Computer Interaction

    Cite this

    Ngo, L. T., Maeda, Y., Lee, H., & Mizukawa, M. (2012). Ambiguous command understanding with commonsense. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication (pp. 545-550). [6343808] https://doi.org/10.1109/ROMAN.2012.6343808

    Ambiguous command understanding with commonsense. / Ngo, Lam Trung; Maeda, Yoshio; Lee, Haeyeon; Mizukawa, Makoto.

    Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. p. 545-550 6343808.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ngo, LT, Maeda, Y, Lee, H & Mizukawa, M 2012, Ambiguous command understanding with commonsense. in Proceedings - IEEE International Workshop on Robot and Human Interactive Communication., 6343808, pp. 545-550, 2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012, Paris, 12/9/9. https://doi.org/10.1109/ROMAN.2012.6343808
    Ngo LT, Maeda Y, Lee H, Mizukawa M. Ambiguous command understanding with commonsense. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. p. 545-550. 6343808 https://doi.org/10.1109/ROMAN.2012.6343808
    Ngo, Lam Trung ; Maeda, Yoshio ; Lee, Haeyeon ; Mizukawa, Makoto. / Ambiguous command understanding with commonsense. Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. pp. 545-550
    @inproceedings{4f86acc4416e41f2b6541f31cb623023,
    title = "Ambiguous command understanding with commonsense",
    abstract = "This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the Bring something service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.",
    author = "Ngo, {Lam Trung} and Yoshio Maeda and Haeyeon Lee and Makoto Mizukawa",
    year = "2012",
    doi = "10.1109/ROMAN.2012.6343808",
    language = "English",
    isbn = "9781467346054",
    pages = "545--550",
    booktitle = "Proceedings - IEEE International Workshop on Robot and Human Interactive Communication",

    }

    TY - GEN

    T1 - Ambiguous command understanding with commonsense

    AU - Ngo, Lam Trung

    AU - Maeda, Yoshio

    AU - Lee, Haeyeon

    AU - Mizukawa, Makoto

    PY - 2012

    Y1 - 2012

    N2 - This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the Bring something service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.

    AB - This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the Bring something service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.

    UR - http://www.scopus.com/inward/record.url?scp=84870854740&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84870854740&partnerID=8YFLogxK

    U2 - 10.1109/ROMAN.2012.6343808

    DO - 10.1109/ROMAN.2012.6343808

    M3 - Conference contribution

    SN - 9781467346054

    SP - 545

    EP - 550

    BT - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

    ER -