Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching

Lorenzo Jamone, Martim Brandao, Lorenzo Natale, Kenji Hashimoto, Giulio Sandini, Atsuo Takanishi

    Research output: Contribution to journalArticle

    14 Citations (Scopus)

    Abstract

    We describe a learning strategy that allows a humanoid robot to autonomously build a representation of its workspace: we call this representation Reachable Space Map. Interestingly, the robot can use this map to: (i) estimate the Reachability of a visually detected object (i.e. judge whether the object can be reached for, and how well, according to some performance metric) and (ii) modify its body posture or its position with respect to the object to achieve better reaching. The robot learns this map incrementally during the execution of goal-directed reaching movements; reaching control employs kinematic models that are updated online as well. Our solution is innovative with respect to previous works in three aspects: the robot workspace is described using a gaze-centered motor representation, the map is built incrementally during the execution of goal-directed actions, learning is autonomous and online. We implement our strategy on the 48-DOFs humanoid robot Kobian and we show how the Reachable Space Map can support intelligent reaching behavior with the whole-body (i.e. head, eyes, arm, waist, legs).

    Original languageEnglish
    Pages (from-to)556-567
    Number of pages12
    JournalRobotics and Autonomous Systems
    Volume62
    Issue number4
    DOIs
    Publication statusPublished - 2014 Apr

    Fingerprint

    Workspace
    Robots
    Humanoid Robot
    Robot
    Kinematic Model
    Learning Strategies
    Performance Metrics
    Reachability
    Kinematics
    Estimate
    Object

    Keywords

    • Bio-inspired robotics
    • Humanoid robots
    • Kinematic workspace
    • Online sensorimotor learning
    • Whole-body reaching

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Computer Science Applications
    • Software
    • Mathematics(all)

    Cite this

    Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching. / Jamone, Lorenzo; Brandao, Martim; Natale, Lorenzo; Hashimoto, Kenji; Sandini, Giulio; Takanishi, Atsuo.

    In: Robotics and Autonomous Systems, Vol. 62, No. 4, 04.2014, p. 556-567.

    Research output: Contribution to journalArticle

    Jamone, Lorenzo ; Brandao, Martim ; Natale, Lorenzo ; Hashimoto, Kenji ; Sandini, Giulio ; Takanishi, Atsuo. / Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching. In: Robotics and Autonomous Systems. 2014 ; Vol. 62, No. 4. pp. 556-567.
    @article{6eb2cd5619b84c2c9f98d8c2df6a6b91,
    title = "Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching",
    abstract = "We describe a learning strategy that allows a humanoid robot to autonomously build a representation of its workspace: we call this representation Reachable Space Map. Interestingly, the robot can use this map to: (i) estimate the Reachability of a visually detected object (i.e. judge whether the object can be reached for, and how well, according to some performance metric) and (ii) modify its body posture or its position with respect to the object to achieve better reaching. The robot learns this map incrementally during the execution of goal-directed reaching movements; reaching control employs kinematic models that are updated online as well. Our solution is innovative with respect to previous works in three aspects: the robot workspace is described using a gaze-centered motor representation, the map is built incrementally during the execution of goal-directed actions, learning is autonomous and online. We implement our strategy on the 48-DOFs humanoid robot Kobian and we show how the Reachable Space Map can support intelligent reaching behavior with the whole-body (i.e. head, eyes, arm, waist, legs).",
    keywords = "Bio-inspired robotics, Humanoid robots, Kinematic workspace, Online sensorimotor learning, Whole-body reaching",
    author = "Lorenzo Jamone and Martim Brandao and Lorenzo Natale and Kenji Hashimoto and Giulio Sandini and Atsuo Takanishi",
    year = "2014",
    month = "4",
    doi = "10.1016/j.robot.2013.12.011",
    language = "English",
    volume = "62",
    pages = "556--567",
    journal = "Robotics and Autonomous Systems",
    issn = "0921-8890",
    publisher = "Elsevier",
    number = "4",

    }

    TY - JOUR

    T1 - Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching

    AU - Jamone, Lorenzo

    AU - Brandao, Martim

    AU - Natale, Lorenzo

    AU - Hashimoto, Kenji

    AU - Sandini, Giulio

    AU - Takanishi, Atsuo

    PY - 2014/4

    Y1 - 2014/4

    N2 - We describe a learning strategy that allows a humanoid robot to autonomously build a representation of its workspace: we call this representation Reachable Space Map. Interestingly, the robot can use this map to: (i) estimate the Reachability of a visually detected object (i.e. judge whether the object can be reached for, and how well, according to some performance metric) and (ii) modify its body posture or its position with respect to the object to achieve better reaching. The robot learns this map incrementally during the execution of goal-directed reaching movements; reaching control employs kinematic models that are updated online as well. Our solution is innovative with respect to previous works in three aspects: the robot workspace is described using a gaze-centered motor representation, the map is built incrementally during the execution of goal-directed actions, learning is autonomous and online. We implement our strategy on the 48-DOFs humanoid robot Kobian and we show how the Reachable Space Map can support intelligent reaching behavior with the whole-body (i.e. head, eyes, arm, waist, legs).

    AB - We describe a learning strategy that allows a humanoid robot to autonomously build a representation of its workspace: we call this representation Reachable Space Map. Interestingly, the robot can use this map to: (i) estimate the Reachability of a visually detected object (i.e. judge whether the object can be reached for, and how well, according to some performance metric) and (ii) modify its body posture or its position with respect to the object to achieve better reaching. The robot learns this map incrementally during the execution of goal-directed reaching movements; reaching control employs kinematic models that are updated online as well. Our solution is innovative with respect to previous works in three aspects: the robot workspace is described using a gaze-centered motor representation, the map is built incrementally during the execution of goal-directed actions, learning is autonomous and online. We implement our strategy on the 48-DOFs humanoid robot Kobian and we show how the Reachable Space Map can support intelligent reaching behavior with the whole-body (i.e. head, eyes, arm, waist, legs).

    KW - Bio-inspired robotics

    KW - Humanoid robots

    KW - Kinematic workspace

    KW - Online sensorimotor learning

    KW - Whole-body reaching

    UR - http://www.scopus.com/inward/record.url?scp=84897640150&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84897640150&partnerID=8YFLogxK

    U2 - 10.1016/j.robot.2013.12.011

    DO - 10.1016/j.robot.2013.12.011

    M3 - Article

    AN - SCOPUS:84897640150

    VL - 62

    SP - 556

    EP - 567

    JO - Robotics and Autonomous Systems

    JF - Robotics and Autonomous Systems

    SN - 0921-8890

    IS - 4

    ER -