Effective motion learning for a flexible-joint robot using motor babbling

Kuniyuki Takahashi, Tetsuya Ogata, Hiroki Yamada, Hadi Tjandra, Shigeki Sugano

    研究成果: Conference contribution

    3 引用 (Scopus)

    抄録

    We propose a method for realizing effective dynamic motion learning in a flexible-joint robot using motor babbling. Flexible-joint robots have recently attracted attention because of their adaptiveness, safety, and, in particular, dynamic motions. It is difficult to control robots that require dynamic motion. In past studies, attractors and oscillators were designed as motion primitives of an assumed task in advance. However, it is difficult to adapt to unintended environmental changes using such methods. To overcome this problem, we use a recurrent neural network (RNN) that does not require predetermined parameters. In this research, we propose a method for facilitating effective learning. First, a robot learns simple motions via motor babbling, acquiring body dynamics using a recurrent neural network (RNN). Motor babbling is the process of movement that infants use to acquire their own body dynamics during their early days. Next, the robot learns additional motions required for a target task using the acquired body dynamics. For acquiring these body dynamics, the robot uses motor babbling with its redundant flexible joints to learn motion primitives. This redundancy implies that there are numerous possible motion patterns. In comparison to a basic learning task, the motion primitives are simply modified to adjust to the task. Next, we focus on the types of motions used in motor babbling. We classify the motions into two motion types, passive motion and active motion. Passive motion involves inertia without any torque input, whereas active motion involves a torque input. The robot acquires body dynamics from the passive motion and a means of torque generation from the active motion. As a result, we demonstrate the importance of performing prior learning via motor babbling before learning a task. In addition, task learning is made more efficient by dividing the motion into two types of motor babbling patterns.

    元の言語English
    ホスト出版物のタイトルIEEE International Conference on Intelligent Robots and Systems
    出版者Institute of Electrical and Electronics Engineers Inc.
    ページ2723-2728
    ページ数6
    2015-December
    ISBN(印刷物)9781479999941
    DOI
    出版物ステータス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
    Germany
    Hamburg
    期間15/9/2815/10/2

    Fingerprint

    Robots
    Torque
    Recurrent neural networks
    Redundancy

    ASJC Scopus subject areas

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

    これを引用

    Takahashi, K., Ogata, T., Yamada, H., Tjandra, H., & Sugano, S. (2015). Effective motion learning for a flexible-joint robot using motor babbling. : IEEE International Conference on Intelligent Robots and Systems (巻 2015-December, pp. 2723-2728). [7353750] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2015.7353750

    Effective motion learning for a flexible-joint robot using motor babbling. / Takahashi, Kuniyuki; Ogata, Tetsuya; Yamada, Hiroki; Tjandra, Hadi; Sugano, Shigeki.

    IEEE International Conference on Intelligent Robots and Systems. 巻 2015-December Institute of Electrical and Electronics Engineers Inc., 2015. p. 2723-2728 7353750.

    研究成果: Conference contribution

    Takahashi, K, Ogata, T, Yamada, H, Tjandra, H & Sugano, S 2015, Effective motion learning for a flexible-joint robot using motor babbling. : IEEE International Conference on Intelligent Robots and Systems. 巻. 2015-December, 7353750, Institute of Electrical and Electronics Engineers Inc., pp. 2723-2728, IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015, Hamburg, Germany, 15/9/28. https://doi.org/10.1109/IROS.2015.7353750
    Takahashi K, Ogata T, Yamada H, Tjandra H, Sugano S. Effective motion learning for a flexible-joint robot using motor babbling. : IEEE International Conference on Intelligent Robots and Systems. 巻 2015-December. Institute of Electrical and Electronics Engineers Inc. 2015. p. 2723-2728. 7353750 https://doi.org/10.1109/IROS.2015.7353750
    Takahashi, Kuniyuki ; Ogata, Tetsuya ; Yamada, Hiroki ; Tjandra, Hadi ; Sugano, Shigeki. / Effective motion learning for a flexible-joint robot using motor babbling. IEEE International Conference on Intelligent Robots and Systems. 巻 2015-December Institute of Electrical and Electronics Engineers Inc., 2015. pp. 2723-2728
    @inproceedings{97e3c6d6ff6743e181c28cf60214e548,
    title = "Effective motion learning for a flexible-joint robot using motor babbling",
    abstract = "We propose a method for realizing effective dynamic motion learning in a flexible-joint robot using motor babbling. Flexible-joint robots have recently attracted attention because of their adaptiveness, safety, and, in particular, dynamic motions. It is difficult to control robots that require dynamic motion. In past studies, attractors and oscillators were designed as motion primitives of an assumed task in advance. However, it is difficult to adapt to unintended environmental changes using such methods. To overcome this problem, we use a recurrent neural network (RNN) that does not require predetermined parameters. In this research, we propose a method for facilitating effective learning. First, a robot learns simple motions via motor babbling, acquiring body dynamics using a recurrent neural network (RNN). Motor babbling is the process of movement that infants use to acquire their own body dynamics during their early days. Next, the robot learns additional motions required for a target task using the acquired body dynamics. For acquiring these body dynamics, the robot uses motor babbling with its redundant flexible joints to learn motion primitives. This redundancy implies that there are numerous possible motion patterns. In comparison to a basic learning task, the motion primitives are simply modified to adjust to the task. Next, we focus on the types of motions used in motor babbling. We classify the motions into two motion types, passive motion and active motion. Passive motion involves inertia without any torque input, whereas active motion involves a torque input. The robot acquires body dynamics from the passive motion and a means of torque generation from the active motion. As a result, we demonstrate the importance of performing prior learning via motor babbling before learning a task. In addition, task learning is made more efficient by dividing the motion into two types of motor babbling patterns.",
    keywords = "Dynamics, Neurons, Oscillators, Recurrent neural networks, Robot sensing systems, Torque",
    author = "Kuniyuki Takahashi and Tetsuya Ogata and Hiroki Yamada and Hadi Tjandra and Shigeki Sugano",
    year = "2015",
    month = "12",
    day = "11",
    doi = "10.1109/IROS.2015.7353750",
    language = "English",
    isbn = "9781479999941",
    volume = "2015-December",
    pages = "2723--2728",
    booktitle = "IEEE International Conference on Intelligent Robots and Systems",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Effective motion learning for a flexible-joint robot using motor babbling

    AU - Takahashi, Kuniyuki

    AU - Ogata, Tetsuya

    AU - Yamada, Hiroki

    AU - Tjandra, Hadi

    AU - Sugano, Shigeki

    PY - 2015/12/11

    Y1 - 2015/12/11

    N2 - We propose a method for realizing effective dynamic motion learning in a flexible-joint robot using motor babbling. Flexible-joint robots have recently attracted attention because of their adaptiveness, safety, and, in particular, dynamic motions. It is difficult to control robots that require dynamic motion. In past studies, attractors and oscillators were designed as motion primitives of an assumed task in advance. However, it is difficult to adapt to unintended environmental changes using such methods. To overcome this problem, we use a recurrent neural network (RNN) that does not require predetermined parameters. In this research, we propose a method for facilitating effective learning. First, a robot learns simple motions via motor babbling, acquiring body dynamics using a recurrent neural network (RNN). Motor babbling is the process of movement that infants use to acquire their own body dynamics during their early days. Next, the robot learns additional motions required for a target task using the acquired body dynamics. For acquiring these body dynamics, the robot uses motor babbling with its redundant flexible joints to learn motion primitives. This redundancy implies that there are numerous possible motion patterns. In comparison to a basic learning task, the motion primitives are simply modified to adjust to the task. Next, we focus on the types of motions used in motor babbling. We classify the motions into two motion types, passive motion and active motion. Passive motion involves inertia without any torque input, whereas active motion involves a torque input. The robot acquires body dynamics from the passive motion and a means of torque generation from the active motion. As a result, we demonstrate the importance of performing prior learning via motor babbling before learning a task. In addition, task learning is made more efficient by dividing the motion into two types of motor babbling patterns.

    AB - We propose a method for realizing effective dynamic motion learning in a flexible-joint robot using motor babbling. Flexible-joint robots have recently attracted attention because of their adaptiveness, safety, and, in particular, dynamic motions. It is difficult to control robots that require dynamic motion. In past studies, attractors and oscillators were designed as motion primitives of an assumed task in advance. However, it is difficult to adapt to unintended environmental changes using such methods. To overcome this problem, we use a recurrent neural network (RNN) that does not require predetermined parameters. In this research, we propose a method for facilitating effective learning. First, a robot learns simple motions via motor babbling, acquiring body dynamics using a recurrent neural network (RNN). Motor babbling is the process of movement that infants use to acquire their own body dynamics during their early days. Next, the robot learns additional motions required for a target task using the acquired body dynamics. For acquiring these body dynamics, the robot uses motor babbling with its redundant flexible joints to learn motion primitives. This redundancy implies that there are numerous possible motion patterns. In comparison to a basic learning task, the motion primitives are simply modified to adjust to the task. Next, we focus on the types of motions used in motor babbling. We classify the motions into two motion types, passive motion and active motion. Passive motion involves inertia without any torque input, whereas active motion involves a torque input. The robot acquires body dynamics from the passive motion and a means of torque generation from the active motion. As a result, we demonstrate the importance of performing prior learning via motor babbling before learning a task. In addition, task learning is made more efficient by dividing the motion into two types of motor babbling patterns.

    KW - Dynamics

    KW - Neurons

    KW - Oscillators

    KW - Recurrent neural networks

    KW - Robot sensing systems

    KW - Torque

    UR - http://www.scopus.com/inward/record.url?scp=84958185076&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84958185076&partnerID=8YFLogxK

    U2 - 10.1109/IROS.2015.7353750

    DO - 10.1109/IROS.2015.7353750

    M3 - Conference contribution

    AN - SCOPUS:84958185076

    SN - 9781479999941

    VL - 2015-December

    SP - 2723

    EP - 2728

    BT - IEEE International Conference on Intelligent Robots and Systems

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -