Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others

Shingo Murata, Yuichi Yamashita, Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sugano

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

    4 Citations (Scopus)

    Abstract

    This paper investigates the essential difference between two types of behavior generation schemes, namely, sensory reflex behavior generation and intentional proactive behavior generation, by proposing a dynamic neural network model referred to as stochastic multiple-timescale recurrent neural network (S-MTRNN). The proposed model was employed in an experiment involving robots learning to cooperate with others under the condition of potential unpredictability of the others' behaviors. The results of the learning experiment showed that sensory reflex behavior was generated by a self-organizing probabilistic prediction mechanism when the initial sensitivity characteristics in the network dynamics were not utilized in the learning process. In contrast, proactive behavior with a deterministic prediction mechanism was developed when the initial sensitivity was utilized. It was further shown that in situations where unexpected behaviors of others were observed, the behavioral context was re-situated by adaptation of the internal neural dynamics by means of simple sensory reflexes in the former case. In the latter case, the behavioral context was re-situated by error regression of the internal neural activity rather than by sensory reflex. The role of the top-down and bottom-up interactions in dealing with unexpected situations is discussed.

    Original languageEnglish
    Title of host publicationIEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages242-248
    Number of pages7
    ISBN (Print)9781479975402
    DOIs
    Publication statusPublished - 2014 Dec 11
    Event4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014 - Genoa
    Duration: 2014 Oct 132014 Oct 16

    Other

    Other4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014
    CityGenoa
    Period14/10/1314/10/16

    Fingerprint

    Robot learning
    Recurrent neural networks
    Experiments
    Neural networks

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Science Applications
    • Computer Vision and Pattern Recognition

    Cite this

    Murata, S., Yamashita, Y., Arie, H., Ogata, T., Tani, J., & Sugano, S. (2014). Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others. In IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (pp. 242-248). [6982988] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEVLRN.2014.6982988

    Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others. / Murata, Shingo; Yamashita, Yuichi; Arie, Hiroaki; Ogata, Tetsuya; Tani, Jun; Sugano, Shigeki.

    IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc., 2014. p. 242-248 6982988.

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

    Murata, S, Yamashita, Y, Arie, H, Ogata, T, Tani, J & Sugano, S 2014, Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others. in IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics., 6982988, Institute of Electrical and Electronics Engineers Inc., pp. 242-248, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014, Genoa, 14/10/13. https://doi.org/10.1109/DEVLRN.2014.6982988
    Murata S, Yamashita Y, Arie H, Ogata T, Tani J, Sugano S. Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others. In IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc. 2014. p. 242-248. 6982988 https://doi.org/10.1109/DEVLRN.2014.6982988
    Murata, Shingo ; Yamashita, Yuichi ; Arie, Hiroaki ; Ogata, Tetsuya ; Tani, Jun ; Sugano, Shigeki. / Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others. IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 242-248
    @inproceedings{5c9d666bee97419aaf0391ccb620c3e6,
    title = "Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others",
    abstract = "This paper investigates the essential difference between two types of behavior generation schemes, namely, sensory reflex behavior generation and intentional proactive behavior generation, by proposing a dynamic neural network model referred to as stochastic multiple-timescale recurrent neural network (S-MTRNN). The proposed model was employed in an experiment involving robots learning to cooperate with others under the condition of potential unpredictability of the others' behaviors. The results of the learning experiment showed that sensory reflex behavior was generated by a self-organizing probabilistic prediction mechanism when the initial sensitivity characteristics in the network dynamics were not utilized in the learning process. In contrast, proactive behavior with a deterministic prediction mechanism was developed when the initial sensitivity was utilized. It was further shown that in situations where unexpected behaviors of others were observed, the behavioral context was re-situated by adaptation of the internal neural dynamics by means of simple sensory reflexes in the former case. In the latter case, the behavioral context was re-situated by error regression of the internal neural activity rather than by sensory reflex. The role of the top-down and bottom-up interactions in dealing with unexpected situations is discussed.",
    author = "Shingo Murata and Yuichi Yamashita and Hiroaki Arie and Tetsuya Ogata and Jun Tani and Shigeki Sugano",
    year = "2014",
    month = "12",
    day = "11",
    doi = "10.1109/DEVLRN.2014.6982988",
    language = "English",
    isbn = "9781479975402",
    pages = "242--248",
    booktitle = "IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Generation of sensory reflex behavior versus intentional proactive behavior in robot learning of cooperative interactions with others

    AU - Murata, Shingo

    AU - Yamashita, Yuichi

    AU - Arie, Hiroaki

    AU - Ogata, Tetsuya

    AU - Tani, Jun

    AU - Sugano, Shigeki

    PY - 2014/12/11

    Y1 - 2014/12/11

    N2 - This paper investigates the essential difference between two types of behavior generation schemes, namely, sensory reflex behavior generation and intentional proactive behavior generation, by proposing a dynamic neural network model referred to as stochastic multiple-timescale recurrent neural network (S-MTRNN). The proposed model was employed in an experiment involving robots learning to cooperate with others under the condition of potential unpredictability of the others' behaviors. The results of the learning experiment showed that sensory reflex behavior was generated by a self-organizing probabilistic prediction mechanism when the initial sensitivity characteristics in the network dynamics were not utilized in the learning process. In contrast, proactive behavior with a deterministic prediction mechanism was developed when the initial sensitivity was utilized. It was further shown that in situations where unexpected behaviors of others were observed, the behavioral context was re-situated by adaptation of the internal neural dynamics by means of simple sensory reflexes in the former case. In the latter case, the behavioral context was re-situated by error regression of the internal neural activity rather than by sensory reflex. The role of the top-down and bottom-up interactions in dealing with unexpected situations is discussed.

    AB - This paper investigates the essential difference between two types of behavior generation schemes, namely, sensory reflex behavior generation and intentional proactive behavior generation, by proposing a dynamic neural network model referred to as stochastic multiple-timescale recurrent neural network (S-MTRNN). The proposed model was employed in an experiment involving robots learning to cooperate with others under the condition of potential unpredictability of the others' behaviors. The results of the learning experiment showed that sensory reflex behavior was generated by a self-organizing probabilistic prediction mechanism when the initial sensitivity characteristics in the network dynamics were not utilized in the learning process. In contrast, proactive behavior with a deterministic prediction mechanism was developed when the initial sensitivity was utilized. It was further shown that in situations where unexpected behaviors of others were observed, the behavioral context was re-situated by adaptation of the internal neural dynamics by means of simple sensory reflexes in the former case. In the latter case, the behavioral context was re-situated by error regression of the internal neural activity rather than by sensory reflex. The role of the top-down and bottom-up interactions in dealing with unexpected situations is discussed.

    UR - http://www.scopus.com/inward/record.url?scp=84920882110&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84920882110&partnerID=8YFLogxK

    U2 - 10.1109/DEVLRN.2014.6982988

    DO - 10.1109/DEVLRN.2014.6982988

    M3 - Conference contribution

    AN - SCOPUS:84920882110

    SN - 9781479975402

    SP - 242

    EP - 248

    BT - IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -