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

Tatsuro Yamada, Shingo Murata, Hiroaki Arie, Tetsuya Ogata

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

    4 Citations (Scopus)

    Abstract

    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.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Intelligent Robots and Systems
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages4179-4184
    Number of pages6
    Volume2015-December
    ISBN (Print)9781479999941
    DOIs
    Publication statusPublished - 2015 Dec 11
    EventIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015 - Hamburg, Germany
    Duration: 2015 Sep 282015 Oct 2

    Other

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

    Keywords

    • Hidden Markov models
    • Neurons
    • Pragmatics
    • Robots
    • Semantics
    • Training
    • Training data

    ASJC Scopus subject areas

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

    Fingerprint Dive into the research topics of 'Attractor representations of language-behavior structure in a recurrent neural network for human-robot interaction'. Together they form a unique fingerprint.

    Cite this