Reaching for the unreachable: Integration of locomotion and whole-body movements for extended visually guided reaching

Martim Brandão, Lorenzo Jamone, Przemyslaw Kryczka, Nobotsuna Endo, Kenji Hashimoto, Atsuo Takanishi

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

    3 Citations (Scopus)

    Abstract

    We present a novel control architecture for the integration of visually guided walking and whole-body reaching in a humanoid robot.We propose to use robot gaze as a common reference frame for both locomotion and reaching, as suggested by behavioral neuroscience studies in humans. A gaze controller allows the robot to track and fixate a target object, and motor information related to gaze control is then used to i) estimate the reachability of the target, ii) steer locomotion, iii) control whole-body reaching. The reachability is a measure of how well the object can be reached for, depending on the position and posture of the robot with respect to the target, and it is obtained from the gaze motor information using a mapping that has been learned autonomously by the robot through motor experience: we call this mapping Reachable Space Map. In our approach, both locomotion and whole-body movements are seen as ways to maximize the reachability of a visually detected object, thus i) expanding the robot workspace to the entire visible space and ii) exploiting the robot redundancy to optimize reaching. We implement our method on a full 48-DOF humanoid robot and provide experimental results in the real world.

    Original languageEnglish
    Title of host publicationIEEE-RAS International Conference on Humanoid Robots
    PublisherIEEE Computer Society
    Pages28-33
    Number of pages6
    Volume2015-February
    EditionFebruary
    DOIs
    Publication statusPublished - 2015 Feb 3
    Event2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013 - Atlanta, United States
    Duration: 2013 Oct 152013 Oct 17

    Other

    Other2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013
    CountryUnited States
    CityAtlanta
    Period13/10/1513/10/17

    Fingerprint

    Robots
    Redundancy
    Controllers

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Hardware and Architecture
    • Human-Computer Interaction
    • Electrical and Electronic Engineering

    Cite this

    Brandão, M., Jamone, L., Kryczka, P., Endo, N., Hashimoto, K., & Takanishi, A. (2015). Reaching for the unreachable: Integration of locomotion and whole-body movements for extended visually guided reaching. In IEEE-RAS International Conference on Humanoid Robots (February ed., Vol. 2015-February, pp. 28-33). [7029951] IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2013.7029951

    Reaching for the unreachable : Integration of locomotion and whole-body movements for extended visually guided reaching. / Brandão, Martim; Jamone, Lorenzo; Kryczka, Przemyslaw; Endo, Nobotsuna; Hashimoto, Kenji; Takanishi, Atsuo.

    IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February February. ed. IEEE Computer Society, 2015. p. 28-33 7029951.

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

    Brandão, M, Jamone, L, Kryczka, P, Endo, N, Hashimoto, K & Takanishi, A 2015, Reaching for the unreachable: Integration of locomotion and whole-body movements for extended visually guided reaching. in IEEE-RAS International Conference on Humanoid Robots. February edn, vol. 2015-February, 7029951, IEEE Computer Society, pp. 28-33, 2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013, Atlanta, United States, 13/10/15. https://doi.org/10.1109/HUMANOIDS.2013.7029951
    Brandão M, Jamone L, Kryczka P, Endo N, Hashimoto K, Takanishi A. Reaching for the unreachable: Integration of locomotion and whole-body movements for extended visually guided reaching. In IEEE-RAS International Conference on Humanoid Robots. February ed. Vol. 2015-February. IEEE Computer Society. 2015. p. 28-33. 7029951 https://doi.org/10.1109/HUMANOIDS.2013.7029951
    Brandão, Martim ; Jamone, Lorenzo ; Kryczka, Przemyslaw ; Endo, Nobotsuna ; Hashimoto, Kenji ; Takanishi, Atsuo. / Reaching for the unreachable : Integration of locomotion and whole-body movements for extended visually guided reaching. IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February February. ed. IEEE Computer Society, 2015. pp. 28-33
    @inproceedings{ab1102e11d544164bdb8b48b1043740e,
    title = "Reaching for the unreachable: Integration of locomotion and whole-body movements for extended visually guided reaching",
    abstract = "We present a novel control architecture for the integration of visually guided walking and whole-body reaching in a humanoid robot.We propose to use robot gaze as a common reference frame for both locomotion and reaching, as suggested by behavioral neuroscience studies in humans. A gaze controller allows the robot to track and fixate a target object, and motor information related to gaze control is then used to i) estimate the reachability of the target, ii) steer locomotion, iii) control whole-body reaching. The reachability is a measure of how well the object can be reached for, depending on the position and posture of the robot with respect to the target, and it is obtained from the gaze motor information using a mapping that has been learned autonomously by the robot through motor experience: we call this mapping Reachable Space Map. In our approach, both locomotion and whole-body movements are seen as ways to maximize the reachability of a visually detected object, thus i) expanding the robot workspace to the entire visible space and ii) exploiting the robot redundancy to optimize reaching. We implement our method on a full 48-DOF humanoid robot and provide experimental results in the real world.",
    author = "Martim Brand{\~a}o and Lorenzo Jamone and Przemyslaw Kryczka and Nobotsuna Endo and Kenji Hashimoto and Atsuo Takanishi",
    year = "2015",
    month = "2",
    day = "3",
    doi = "10.1109/HUMANOIDS.2013.7029951",
    language = "English",
    volume = "2015-February",
    pages = "28--33",
    booktitle = "IEEE-RAS International Conference on Humanoid Robots",
    publisher = "IEEE Computer Society",
    edition = "February",

    }

    TY - GEN

    T1 - Reaching for the unreachable

    T2 - Integration of locomotion and whole-body movements for extended visually guided reaching

    AU - Brandão, Martim

    AU - Jamone, Lorenzo

    AU - Kryczka, Przemyslaw

    AU - Endo, Nobotsuna

    AU - Hashimoto, Kenji

    AU - Takanishi, Atsuo

    PY - 2015/2/3

    Y1 - 2015/2/3

    N2 - We present a novel control architecture for the integration of visually guided walking and whole-body reaching in a humanoid robot.We propose to use robot gaze as a common reference frame for both locomotion and reaching, as suggested by behavioral neuroscience studies in humans. A gaze controller allows the robot to track and fixate a target object, and motor information related to gaze control is then used to i) estimate the reachability of the target, ii) steer locomotion, iii) control whole-body reaching. The reachability is a measure of how well the object can be reached for, depending on the position and posture of the robot with respect to the target, and it is obtained from the gaze motor information using a mapping that has been learned autonomously by the robot through motor experience: we call this mapping Reachable Space Map. In our approach, both locomotion and whole-body movements are seen as ways to maximize the reachability of a visually detected object, thus i) expanding the robot workspace to the entire visible space and ii) exploiting the robot redundancy to optimize reaching. We implement our method on a full 48-DOF humanoid robot and provide experimental results in the real world.

    AB - We present a novel control architecture for the integration of visually guided walking and whole-body reaching in a humanoid robot.We propose to use robot gaze as a common reference frame for both locomotion and reaching, as suggested by behavioral neuroscience studies in humans. A gaze controller allows the robot to track and fixate a target object, and motor information related to gaze control is then used to i) estimate the reachability of the target, ii) steer locomotion, iii) control whole-body reaching. The reachability is a measure of how well the object can be reached for, depending on the position and posture of the robot with respect to the target, and it is obtained from the gaze motor information using a mapping that has been learned autonomously by the robot through motor experience: we call this mapping Reachable Space Map. In our approach, both locomotion and whole-body movements are seen as ways to maximize the reachability of a visually detected object, thus i) expanding the robot workspace to the entire visible space and ii) exploiting the robot redundancy to optimize reaching. We implement our method on a full 48-DOF humanoid robot and provide experimental results in the real world.

    UR - http://www.scopus.com/inward/record.url?scp=84937916114&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84937916114&partnerID=8YFLogxK

    U2 - 10.1109/HUMANOIDS.2013.7029951

    DO - 10.1109/HUMANOIDS.2013.7029951

    M3 - Conference contribution

    AN - SCOPUS:84937916114

    VL - 2015-February

    SP - 28

    EP - 33

    BT - IEEE-RAS International Conference on Humanoid Robots

    PB - IEEE Computer Society

    ER -