Application of the Naive Bayes Classifier for Representation and Use of Heterogeneous and Incomplete Knowledge in Social Robotics

Gabriele Trovato, Grzegorz Chrupala, Atsuo Takanishi

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    As societies move towards integration of robots, it is important to study how robots can use their cognition in order to choose effectively their actions in a human environment, and possibly adapt to new contexts. When modelling these contextual data, it is common in social robotics to work with data extracted from human sciences such as sociology, anatomy, or anthropology. These heterogeneous data need to be efficiently used in order to make the robot adapt quickly its actions. In this paper we describe a methodology for the use of heterogeneous and incomplete knowledge, through an algorithm based on naive Bayes classifier. The model was successfully applied to two different experiments of human-robot interaction.
    Original languageEnglish
    JournalRobotics
    Volume5
    Issue number1
    DOIs
    Publication statusPublished - 22 Feb 2016

    Fingerprint

    Robotics
    Classifiers
    Robots
    Human robot interaction
    Experiments

    Keywords

    • social robotics
    • statistical learning
    • human-robot interaction
    • adaptive robotics
    • incomplete knowledge

    Cite this

    @article{8d1ffc525e8f4bccac24fa4388cc3396,
    title = "Application of the Naive Bayes Classifier for Representation and Use of Heterogeneous and Incomplete Knowledge in Social Robotics",
    abstract = "As societies move towards integration of robots, it is important to study how robots can use their cognition in order to choose effectively their actions in a human environment, and possibly adapt to new contexts. When modelling these contextual data, it is common in social robotics to work with data extracted from human sciences such as sociology, anatomy, or anthropology. These heterogeneous data need to be efficiently used in order to make the robot adapt quickly its actions. In this paper we describe a methodology for the use of heterogeneous and incomplete knowledge, through an algorithm based on naive Bayes classifier. The model was successfully applied to two different experiments of human-robot interaction.",
    keywords = "social robotics, statistical learning, human-robot interaction, adaptive robotics, incomplete knowledge",
    author = "Gabriele Trovato and Grzegorz Chrupala and Atsuo Takanishi",
    year = "2016",
    month = "2",
    day = "22",
    doi = "10.3390/robotics5010006",
    language = "English",
    volume = "5",
    journal = "Robotics",
    issn = "2218-6581",
    publisher = "MDPI AG",
    number = "1",

    }

    Application of the Naive Bayes Classifier for Representation and Use of Heterogeneous and Incomplete Knowledge in Social Robotics. / Trovato, Gabriele; Chrupala, Grzegorz; Takanishi, Atsuo.

    In: Robotics, Vol. 5, No. 1, 22.02.2016.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Application of the Naive Bayes Classifier for Representation and Use of Heterogeneous and Incomplete Knowledge in Social Robotics

    AU - Trovato, Gabriele

    AU - Chrupala, Grzegorz

    AU - Takanishi, Atsuo

    PY - 2016/2/22

    Y1 - 2016/2/22

    N2 - As societies move towards integration of robots, it is important to study how robots can use their cognition in order to choose effectively their actions in a human environment, and possibly adapt to new contexts. When modelling these contextual data, it is common in social robotics to work with data extracted from human sciences such as sociology, anatomy, or anthropology. These heterogeneous data need to be efficiently used in order to make the robot adapt quickly its actions. In this paper we describe a methodology for the use of heterogeneous and incomplete knowledge, through an algorithm based on naive Bayes classifier. The model was successfully applied to two different experiments of human-robot interaction.

    AB - As societies move towards integration of robots, it is important to study how robots can use their cognition in order to choose effectively their actions in a human environment, and possibly adapt to new contexts. When modelling these contextual data, it is common in social robotics to work with data extracted from human sciences such as sociology, anatomy, or anthropology. These heterogeneous data need to be efficiently used in order to make the robot adapt quickly its actions. In this paper we describe a methodology for the use of heterogeneous and incomplete knowledge, through an algorithm based on naive Bayes classifier. The model was successfully applied to two different experiments of human-robot interaction.

    KW - social robotics

    KW - statistical learning

    KW - human-robot interaction

    KW - adaptive robotics

    KW - incomplete knowledge

    U2 - 10.3390/robotics5010006

    DO - 10.3390/robotics5010006

    M3 - Article

    VL - 5

    JO - Robotics

    JF - Robotics

    SN - 2218-6581

    IS - 1

    ER -