Developmental human-robot imitation learning of drawing with a neuro dynamical system

Keita Mochizuki, Shun Nishide, Hiroshi G. Okuno, Tetsuya Ogata

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

    21 Citations (Scopus)

    Abstract

    This paper mainly deals with robot developmental learning on drawing and discusses the influences of physical embodiment to the task. Humans are said to develop their drawing skills through five phases: 1) Scribbling, 2) Fortuitous Realism, 3) Failed Realism, 4) Intellectual Realism, 5) Visual Realism. We implement phases 1) and 3) into the humanoid robot NAO, holding a pen, using a neuro dynamical model, namely Multiple Timescales Recurrent Neural Network (MTRNN). For phase 1), we used random arm motion of the robot as body babbling to associate motor dynamics with pen position dynamics. For phase 3), we developed incremental imitation learning to imitate and develop the robot's drawing skill using basic shapes: circle, triangle, and rectangle. We confirmed two notable features from the experiment. First, the drawing was better performed for shapes requiring arm motions used in babbling. Second, performance of clockwise drawing of circle was good from beginning, which is a similar phenomenon that can be observed in human development. The results imply the capability of the model to create a developmental robot relating to human development.

    Original languageEnglish
    Title of host publicationProceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
    Pages2336-2341
    Number of pages6
    DOIs
    Publication statusPublished - 2013
    Event2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 - Manchester
    Duration: 2013 Oct 132013 Oct 16

    Other

    Other2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
    CityManchester
    Period13/10/1313/10/16

    Fingerprint

    Robot learning
    Dynamical systems
    Robots
    Recurrent neural networks
    Experiments

    Keywords

    • Body babbling
    • Cognitive developmental robotics
    • Imitation learning
    • Neuro dynamical system

    ASJC Scopus subject areas

    • Human-Computer Interaction

    Cite this

    Mochizuki, K., Nishide, S., Okuno, H. G., & Ogata, T. (2013). Developmental human-robot imitation learning of drawing with a neuro dynamical system. In Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 (pp. 2336-2341). [6722152] https://doi.org/10.1109/SMC.2013.399

    Developmental human-robot imitation learning of drawing with a neuro dynamical system. / Mochizuki, Keita; Nishide, Shun; Okuno, Hiroshi G.; Ogata, Tetsuya.

    Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. p. 2336-2341 6722152.

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

    Mochizuki, K, Nishide, S, Okuno, HG & Ogata, T 2013, Developmental human-robot imitation learning of drawing with a neuro dynamical system. in Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013., 6722152, pp. 2336-2341, 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013, Manchester, 13/10/13. https://doi.org/10.1109/SMC.2013.399
    Mochizuki K, Nishide S, Okuno HG, Ogata T. Developmental human-robot imitation learning of drawing with a neuro dynamical system. In Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. p. 2336-2341. 6722152 https://doi.org/10.1109/SMC.2013.399
    Mochizuki, Keita ; Nishide, Shun ; Okuno, Hiroshi G. ; Ogata, Tetsuya. / Developmental human-robot imitation learning of drawing with a neuro dynamical system. Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. pp. 2336-2341
    @inproceedings{1a903c51752745d09a65fe16800a72f9,
    title = "Developmental human-robot imitation learning of drawing with a neuro dynamical system",
    abstract = "This paper mainly deals with robot developmental learning on drawing and discusses the influences of physical embodiment to the task. Humans are said to develop their drawing skills through five phases: 1) Scribbling, 2) Fortuitous Realism, 3) Failed Realism, 4) Intellectual Realism, 5) Visual Realism. We implement phases 1) and 3) into the humanoid robot NAO, holding a pen, using a neuro dynamical model, namely Multiple Timescales Recurrent Neural Network (MTRNN). For phase 1), we used random arm motion of the robot as body babbling to associate motor dynamics with pen position dynamics. For phase 3), we developed incremental imitation learning to imitate and develop the robot's drawing skill using basic shapes: circle, triangle, and rectangle. We confirmed two notable features from the experiment. First, the drawing was better performed for shapes requiring arm motions used in babbling. Second, performance of clockwise drawing of circle was good from beginning, which is a similar phenomenon that can be observed in human development. The results imply the capability of the model to create a developmental robot relating to human development.",
    keywords = "Body babbling, Cognitive developmental robotics, Imitation learning, Neuro dynamical system",
    author = "Keita Mochizuki and Shun Nishide and Okuno, {Hiroshi G.} and Tetsuya Ogata",
    year = "2013",
    doi = "10.1109/SMC.2013.399",
    language = "English",
    isbn = "9780769551548",
    pages = "2336--2341",
    booktitle = "Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013",

    }

    TY - GEN

    T1 - Developmental human-robot imitation learning of drawing with a neuro dynamical system

    AU - Mochizuki, Keita

    AU - Nishide, Shun

    AU - Okuno, Hiroshi G.

    AU - Ogata, Tetsuya

    PY - 2013

    Y1 - 2013

    N2 - This paper mainly deals with robot developmental learning on drawing and discusses the influences of physical embodiment to the task. Humans are said to develop their drawing skills through five phases: 1) Scribbling, 2) Fortuitous Realism, 3) Failed Realism, 4) Intellectual Realism, 5) Visual Realism. We implement phases 1) and 3) into the humanoid robot NAO, holding a pen, using a neuro dynamical model, namely Multiple Timescales Recurrent Neural Network (MTRNN). For phase 1), we used random arm motion of the robot as body babbling to associate motor dynamics with pen position dynamics. For phase 3), we developed incremental imitation learning to imitate and develop the robot's drawing skill using basic shapes: circle, triangle, and rectangle. We confirmed two notable features from the experiment. First, the drawing was better performed for shapes requiring arm motions used in babbling. Second, performance of clockwise drawing of circle was good from beginning, which is a similar phenomenon that can be observed in human development. The results imply the capability of the model to create a developmental robot relating to human development.

    AB - This paper mainly deals with robot developmental learning on drawing and discusses the influences of physical embodiment to the task. Humans are said to develop their drawing skills through five phases: 1) Scribbling, 2) Fortuitous Realism, 3) Failed Realism, 4) Intellectual Realism, 5) Visual Realism. We implement phases 1) and 3) into the humanoid robot NAO, holding a pen, using a neuro dynamical model, namely Multiple Timescales Recurrent Neural Network (MTRNN). For phase 1), we used random arm motion of the robot as body babbling to associate motor dynamics with pen position dynamics. For phase 3), we developed incremental imitation learning to imitate and develop the robot's drawing skill using basic shapes: circle, triangle, and rectangle. We confirmed two notable features from the experiment. First, the drawing was better performed for shapes requiring arm motions used in babbling. Second, performance of clockwise drawing of circle was good from beginning, which is a similar phenomenon that can be observed in human development. The results imply the capability of the model to create a developmental robot relating to human development.

    KW - Body babbling

    KW - Cognitive developmental robotics

    KW - Imitation learning

    KW - Neuro dynamical system

    UR - http://www.scopus.com/inward/record.url?scp=84893548411&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84893548411&partnerID=8YFLogxK

    U2 - 10.1109/SMC.2013.399

    DO - 10.1109/SMC.2013.399

    M3 - Conference contribution

    AN - SCOPUS:84893548411

    SN - 9780769551548

    SP - 2336

    EP - 2341

    BT - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

    ER -