A chaotic neural network as motor path generator for mobile robotics

Michele Folgheraiter, Giuseppina Gini

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

    4 Citations (Scopus)

    Abstract

    This work aims at developing a motor path generator for applications in mobile robotics based on a chaotic neural network. The computational paradigm inspired by the neural structure of microcircuits located in the human prefrontal cortex is adapted to work in real-time and used to generate the joints trajectories of a lightweight quadruped robot. The recurrent neural network was implemented in Matlab and a software framework was developed to test the performances of the system with the robot dynamic model. Preliminary results demonstrate the capability of the neural controller to learn period signals in a short period of time allowing adaptation during the robot operation.

    Original languageEnglish
    Title of host publication2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages64-69
    Number of pages6
    ISBN (Print)9781479973965
    DOIs
    Publication statusPublished - Apr 20 2014
    Event2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014 - Bali, Indonesia
    Duration: Dec 5 2014Dec 10 2014

    Other

    Other2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014
    CountryIndonesia
    CityBali
    Period12/5/1412/10/14

    Fingerprint

    Robotics
    Mobile Applications
    Robots
    Neural networks
    Prefrontal Cortex
    Software
    Joints
    Recurrent neural networks
    Dynamic models
    Trajectories
    Controllers

    Keywords

    • Control Path Generator
    • Dynamic Neural Network
    • Lightweight Quadruped Robot
    • Neurodynamics
    • Recurrent Neural Network RNN

    ASJC Scopus subject areas

    • Biotechnology
    • Artificial Intelligence
    • Human-Computer Interaction

    Cite this

    Folgheraiter, M., & Gini, G. (2014). A chaotic neural network as motor path generator for mobile robotics. In 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014 (pp. 64-69). [7090308] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBIO.2014.7090308

    A chaotic neural network as motor path generator for mobile robotics. / Folgheraiter, Michele; Gini, Giuseppina.

    2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 64-69 7090308.

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

    Folgheraiter, M & Gini, G 2014, A chaotic neural network as motor path generator for mobile robotics. in 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014., 7090308, Institute of Electrical and Electronics Engineers Inc., pp. 64-69, 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014, Bali, Indonesia, 12/5/14. https://doi.org/10.1109/ROBIO.2014.7090308
    Folgheraiter M, Gini G. A chaotic neural network as motor path generator for mobile robotics. In 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 64-69. 7090308 https://doi.org/10.1109/ROBIO.2014.7090308
    Folgheraiter, Michele ; Gini, Giuseppina. / A chaotic neural network as motor path generator for mobile robotics. 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 64-69
    @inproceedings{41e1c4932e814ac38f896dbb85bcc91a,
    title = "A chaotic neural network as motor path generator for mobile robotics",
    abstract = "This work aims at developing a motor path generator for applications in mobile robotics based on a chaotic neural network. The computational paradigm inspired by the neural structure of microcircuits located in the human prefrontal cortex is adapted to work in real-time and used to generate the joints trajectories of a lightweight quadruped robot. The recurrent neural network was implemented in Matlab and a software framework was developed to test the performances of the system with the robot dynamic model. Preliminary results demonstrate the capability of the neural controller to learn period signals in a short period of time allowing adaptation during the robot operation.",
    keywords = "Control Path Generator, Dynamic Neural Network, Lightweight Quadruped Robot, Neurodynamics, Recurrent Neural Network RNN",
    author = "Michele Folgheraiter and Giuseppina Gini",
    year = "2014",
    month = "4",
    day = "20",
    doi = "10.1109/ROBIO.2014.7090308",
    language = "English",
    isbn = "9781479973965",
    pages = "64--69",
    booktitle = "2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - A chaotic neural network as motor path generator for mobile robotics

    AU - Folgheraiter, Michele

    AU - Gini, Giuseppina

    PY - 2014/4/20

    Y1 - 2014/4/20

    N2 - This work aims at developing a motor path generator for applications in mobile robotics based on a chaotic neural network. The computational paradigm inspired by the neural structure of microcircuits located in the human prefrontal cortex is adapted to work in real-time and used to generate the joints trajectories of a lightweight quadruped robot. The recurrent neural network was implemented in Matlab and a software framework was developed to test the performances of the system with the robot dynamic model. Preliminary results demonstrate the capability of the neural controller to learn period signals in a short period of time allowing adaptation during the robot operation.

    AB - This work aims at developing a motor path generator for applications in mobile robotics based on a chaotic neural network. The computational paradigm inspired by the neural structure of microcircuits located in the human prefrontal cortex is adapted to work in real-time and used to generate the joints trajectories of a lightweight quadruped robot. The recurrent neural network was implemented in Matlab and a software framework was developed to test the performances of the system with the robot dynamic model. Preliminary results demonstrate the capability of the neural controller to learn period signals in a short period of time allowing adaptation during the robot operation.

    KW - Control Path Generator

    KW - Dynamic Neural Network

    KW - Lightweight Quadruped Robot

    KW - Neurodynamics

    KW - Recurrent Neural Network RNN

    UR - http://www.scopus.com/inward/record.url?scp=84949926786&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84949926786&partnerID=8YFLogxK

    U2 - 10.1109/ROBIO.2014.7090308

    DO - 10.1109/ROBIO.2014.7090308

    M3 - Conference contribution

    SN - 9781479973965

    SP - 64

    EP - 69

    BT - 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -