Attractor representations of language-behavior structure in a recurrent neural network for human-robot interaction

Tatsuro Yamada, Shingo Murata, Hiroaki Arie, Tetsuya Ogata

    研究成果: Conference contribution

    4 被引用数 (Scopus)

    抄録

    In recent years there has been increased interest in studies that explore integrative learning of language and other modalities by using neural network models. However, for practical application to human-robot interaction, the acquired semantic structure between language and meaning has to be available immediately and repeatably whenever necessary, just as in everyday communication. As a solution to this problem, this study proposes a method in which a recurrent neural network self-organizes cyclic attractors that reflect semantic structure and represent interaction flows in its internal dynamics. To evaluate this method we design a simple task in which a human verbally directs a robot, which responds appropriately. Training the network with training data that represent the interaction series, the cyclic attractors that reflect the semantic structure is self-organized. The network first receives a verbal direction, and its internal state moves according to the first half of the cyclic attractors with branch structures corresponding to semantics. After that, the internal state reaches a potential to generate appropriate behavior. Finally, the internal state moves to the second half and converges on the initial point of the cycle while generating the appropriate behavior. By self-organizing such an internal structure in its forward dynamics, the model achieves immediate and repeatable response to linguistic directions. Furthermore, the network self-organizes a fixed-point attractor, and so able to wait for directions. It can thus repeat the interaction flexibly without explicit turn-taking signs.

    本文言語English
    ホスト出版物のタイトルIEEE International Conference on Intelligent Robots and Systems
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ4179-4184
    ページ数6
    2015-December
    ISBN(印刷版)9781479999941
    DOI
    出版ステータスPublished - 2015 12 11
    イベントIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015 - Hamburg, Germany
    継続期間: 2015 9 282015 10 2

    Other

    OtherIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015
    CountryGermany
    CityHamburg
    Period15/9/2815/10/2

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Software
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    フィンガープリント 「Attractor representations of language-behavior structure in a recurrent neural network for human-robot interaction」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル