Head stabilization based on a feedback error learning in a humanoid robot

Egidio Falotico, Nino Cauli, Kenji Hashimoto, Przemyslaw Kryczka, Atsuo Takanishi, Paolo Dario, Alain Berthoz, Cecilia Laschi

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

    8 Citations (Scopus)

    Abstract

    In this work we propose an adaptive model for the head stabilization based on a feedback error learning (FEL). This model is capable to overcome the delays caused by the head motor system and adapts itself to the dynamics of the head motion. It has been designed to track an arbitrary reference orientation for the head in space and reject the disturbance caused by trunk motion. For efficient error learning we use the recursive least square algorithm (RLS), a Newton-like method which guarantees very fast convergence. Moreover, we implement a neural network to compute the rotational part of the head inverse kinematics. Verification of the proposed control is conducted through experiments with Matlab SIMULINK and a humanoid robot SABIAN.

    Original languageEnglish
    Title of host publicationProceedings - IEEE International Workshop on Robot and Human Interactive Communication
    Pages449-454
    Number of pages6
    DOIs
    Publication statusPublished - 2012
    Event2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012 - Paris
    Duration: 2012 Sep 92012 Sep 13

    Other

    Other2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012
    CityParis
    Period12/9/912/9/13

    Fingerprint

    Stabilization
    Robots
    Feedback
    Inverse kinematics
    Neural networks
    Experiments

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence
    • Human-Computer Interaction

    Cite this

    Falotico, E., Cauli, N., Hashimoto, K., Kryczka, P., Takanishi, A., Dario, P., ... Laschi, C. (2012). Head stabilization based on a feedback error learning in a humanoid robot. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication (pp. 449-454). [6343793] https://doi.org/10.1109/ROMAN.2012.6343793

    Head stabilization based on a feedback error learning in a humanoid robot. / Falotico, Egidio; Cauli, Nino; Hashimoto, Kenji; Kryczka, Przemyslaw; Takanishi, Atsuo; Dario, Paolo; Berthoz, Alain; Laschi, Cecilia.

    Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. p. 449-454 6343793.

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

    Falotico, E, Cauli, N, Hashimoto, K, Kryczka, P, Takanishi, A, Dario, P, Berthoz, A & Laschi, C 2012, Head stabilization based on a feedback error learning in a humanoid robot. in Proceedings - IEEE International Workshop on Robot and Human Interactive Communication., 6343793, pp. 449-454, 2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012, Paris, 12/9/9. https://doi.org/10.1109/ROMAN.2012.6343793
    Falotico E, Cauli N, Hashimoto K, Kryczka P, Takanishi A, Dario P et al. Head stabilization based on a feedback error learning in a humanoid robot. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. p. 449-454. 6343793 https://doi.org/10.1109/ROMAN.2012.6343793
    Falotico, Egidio ; Cauli, Nino ; Hashimoto, Kenji ; Kryczka, Przemyslaw ; Takanishi, Atsuo ; Dario, Paolo ; Berthoz, Alain ; Laschi, Cecilia. / Head stabilization based on a feedback error learning in a humanoid robot. Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2012. pp. 449-454
    @inproceedings{1069d84dad234f6398d78dc64cf183e4,
    title = "Head stabilization based on a feedback error learning in a humanoid robot",
    abstract = "In this work we propose an adaptive model for the head stabilization based on a feedback error learning (FEL). This model is capable to overcome the delays caused by the head motor system and adapts itself to the dynamics of the head motion. It has been designed to track an arbitrary reference orientation for the head in space and reject the disturbance caused by trunk motion. For efficient error learning we use the recursive least square algorithm (RLS), a Newton-like method which guarantees very fast convergence. Moreover, we implement a neural network to compute the rotational part of the head inverse kinematics. Verification of the proposed control is conducted through experiments with Matlab SIMULINK and a humanoid robot SABIAN.",
    author = "Egidio Falotico and Nino Cauli and Kenji Hashimoto and Przemyslaw Kryczka and Atsuo Takanishi and Paolo Dario and Alain Berthoz and Cecilia Laschi",
    year = "2012",
    doi = "10.1109/ROMAN.2012.6343793",
    language = "English",
    isbn = "9781467346054",
    pages = "449--454",
    booktitle = "Proceedings - IEEE International Workshop on Robot and Human Interactive Communication",

    }

    TY - GEN

    T1 - Head stabilization based on a feedback error learning in a humanoid robot

    AU - Falotico, Egidio

    AU - Cauli, Nino

    AU - Hashimoto, Kenji

    AU - Kryczka, Przemyslaw

    AU - Takanishi, Atsuo

    AU - Dario, Paolo

    AU - Berthoz, Alain

    AU - Laschi, Cecilia

    PY - 2012

    Y1 - 2012

    N2 - In this work we propose an adaptive model for the head stabilization based on a feedback error learning (FEL). This model is capable to overcome the delays caused by the head motor system and adapts itself to the dynamics of the head motion. It has been designed to track an arbitrary reference orientation for the head in space and reject the disturbance caused by trunk motion. For efficient error learning we use the recursive least square algorithm (RLS), a Newton-like method which guarantees very fast convergence. Moreover, we implement a neural network to compute the rotational part of the head inverse kinematics. Verification of the proposed control is conducted through experiments with Matlab SIMULINK and a humanoid robot SABIAN.

    AB - In this work we propose an adaptive model for the head stabilization based on a feedback error learning (FEL). This model is capable to overcome the delays caused by the head motor system and adapts itself to the dynamics of the head motion. It has been designed to track an arbitrary reference orientation for the head in space and reject the disturbance caused by trunk motion. For efficient error learning we use the recursive least square algorithm (RLS), a Newton-like method which guarantees very fast convergence. Moreover, we implement a neural network to compute the rotational part of the head inverse kinematics. Verification of the proposed control is conducted through experiments with Matlab SIMULINK and a humanoid robot SABIAN.

    UR - http://www.scopus.com/inward/record.url?scp=84870851268&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84870851268&partnerID=8YFLogxK

    U2 - 10.1109/ROMAN.2012.6343793

    DO - 10.1109/ROMAN.2012.6343793

    M3 - Conference contribution

    AN - SCOPUS:84870851268

    SN - 9781467346054

    SP - 449

    EP - 454

    BT - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

    ER -