Effective input order of dynamics learning tree

Chyon Hae Kim, Shohei Hama, Ryo Hirai, Kuniyuki Takahashi, Hiroki Yamada, Tetsuya Ogata, Shigeki Sugano

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    In this paper, we discuss about the learning performance of dynamics learning tree (DLT) while mainly focusing on the implementation on robot arms. We propose an input-order-designing method for DLT. DLT has been applied to the modeling of boat, vehicle, and humanoid robot. However, the relationship between the input order and the performance of DLT has not been investigated. In the proposed method, a developer is able to design an effective input order intuitively. The proposed method was validated in the model learning tasks on a simulated robot manipulator, a real robot manipulator, and a simulated vehicle. The first/second manipulator was equipped with flexible arm/finger joints that made uncertainty around the trajectories of manipulated objects. In all of the cases, the proposed method improved the performance of DLT.

    Original languageEnglish
    Pages (from-to)122-136
    Number of pages15
    JournalAdvanced Robotics
    Volume32
    Issue number3
    DOIs
    Publication statusPublished - 2018 Feb 1

    Fingerprint

    Robots
    Manipulators
    Boats
    Trajectories
    Uncertainty

    Keywords

    • drawing
    • humanoid robot
    • Learning
    • manipulation
    • modeling

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Software
    • Human-Computer Interaction
    • Hardware and Architecture
    • Computer Science Applications

    Cite this

    Effective input order of dynamics learning tree. / Kim, Chyon Hae; Hama, Shohei; Hirai, Ryo; Takahashi, Kuniyuki; Yamada, Hiroki; Ogata, Tetsuya; Sugano, Shigeki.

    In: Advanced Robotics, Vol. 32, No. 3, 01.02.2018, p. 122-136.

    Research output: Contribution to journalArticle

    Kim, CH, Hama, S, Hirai, R, Takahashi, K, Yamada, H, Ogata, T & Sugano, S 2018, 'Effective input order of dynamics learning tree', Advanced Robotics, vol. 32, no. 3, pp. 122-136. https://doi.org/10.1080/01691864.2018.1427146
    Kim CH, Hama S, Hirai R, Takahashi K, Yamada H, Ogata T et al. Effective input order of dynamics learning tree. Advanced Robotics. 2018 Feb 1;32(3):122-136. https://doi.org/10.1080/01691864.2018.1427146
    Kim, Chyon Hae ; Hama, Shohei ; Hirai, Ryo ; Takahashi, Kuniyuki ; Yamada, Hiroki ; Ogata, Tetsuya ; Sugano, Shigeki. / Effective input order of dynamics learning tree. In: Advanced Robotics. 2018 ; Vol. 32, No. 3. pp. 122-136.
    @article{cb0b2221e00d42088a9ce7fef5cfa156,
    title = "Effective input order of dynamics learning tree",
    abstract = "In this paper, we discuss about the learning performance of dynamics learning tree (DLT) while mainly focusing on the implementation on robot arms. We propose an input-order-designing method for DLT. DLT has been applied to the modeling of boat, vehicle, and humanoid robot. However, the relationship between the input order and the performance of DLT has not been investigated. In the proposed method, a developer is able to design an effective input order intuitively. The proposed method was validated in the model learning tasks on a simulated robot manipulator, a real robot manipulator, and a simulated vehicle. The first/second manipulator was equipped with flexible arm/finger joints that made uncertainty around the trajectories of manipulated objects. In all of the cases, the proposed method improved the performance of DLT.",
    keywords = "drawing, humanoid robot, Learning, manipulation, modeling",
    author = "Kim, {Chyon Hae} and Shohei Hama and Ryo Hirai and Kuniyuki Takahashi and Hiroki Yamada and Tetsuya Ogata and Shigeki Sugano",
    year = "2018",
    month = "2",
    day = "1",
    doi = "10.1080/01691864.2018.1427146",
    language = "English",
    volume = "32",
    pages = "122--136",
    journal = "Advanced Robotics",
    issn = "0169-1864",
    publisher = "Taylor and Francis Ltd.",
    number = "3",

    }

    TY - JOUR

    T1 - Effective input order of dynamics learning tree

    AU - Kim, Chyon Hae

    AU - Hama, Shohei

    AU - Hirai, Ryo

    AU - Takahashi, Kuniyuki

    AU - Yamada, Hiroki

    AU - Ogata, Tetsuya

    AU - Sugano, Shigeki

    PY - 2018/2/1

    Y1 - 2018/2/1

    N2 - In this paper, we discuss about the learning performance of dynamics learning tree (DLT) while mainly focusing on the implementation on robot arms. We propose an input-order-designing method for DLT. DLT has been applied to the modeling of boat, vehicle, and humanoid robot. However, the relationship between the input order and the performance of DLT has not been investigated. In the proposed method, a developer is able to design an effective input order intuitively. The proposed method was validated in the model learning tasks on a simulated robot manipulator, a real robot manipulator, and a simulated vehicle. The first/second manipulator was equipped with flexible arm/finger joints that made uncertainty around the trajectories of manipulated objects. In all of the cases, the proposed method improved the performance of DLT.

    AB - In this paper, we discuss about the learning performance of dynamics learning tree (DLT) while mainly focusing on the implementation on robot arms. We propose an input-order-designing method for DLT. DLT has been applied to the modeling of boat, vehicle, and humanoid robot. However, the relationship between the input order and the performance of DLT has not been investigated. In the proposed method, a developer is able to design an effective input order intuitively. The proposed method was validated in the model learning tasks on a simulated robot manipulator, a real robot manipulator, and a simulated vehicle. The first/second manipulator was equipped with flexible arm/finger joints that made uncertainty around the trajectories of manipulated objects. In all of the cases, the proposed method improved the performance of DLT.

    KW - drawing

    KW - humanoid robot

    KW - Learning

    KW - manipulation

    KW - modeling

    UR - http://www.scopus.com/inward/record.url?scp=85041546749&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85041546749&partnerID=8YFLogxK

    U2 - 10.1080/01691864.2018.1427146

    DO - 10.1080/01691864.2018.1427146

    M3 - Article

    VL - 32

    SP - 122

    EP - 136

    JO - Advanced Robotics

    JF - Advanced Robotics

    SN - 0169-1864

    IS - 3

    ER -