Interactive online learning of the kinematic workspace of a humanoid robot

Lorenzo Jamone, Lorenzo Natale, Giulio Sandini, Atsuo Takanishi

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

    9 Citations (Scopus)

    Abstract

    We describe an interactive learning strategy that enables a humanoid robot to build a representation of its workspace: we call it a Reachable Space Map. The robot learns this map autonomously and online during the execution of goal-directed reaching movements; reaching control is based on kinematic models that are learned online as well. The map can be used to estimate the reachability of a fixated object and to plan preparatory movements (e.g. bending or rotating the waist) that improve the effectiveness of the subsequent reaching action. Three main concepts make our solution innovative with respect to previous works: the use of a gaze-centered motor representation to describe the robot workspace, the primary role of action in building and representing knowledge (i.e. interactive learning), the realization of autonomous online learning. We evaluate our strategy by learning the workspace of a simulated humanoid robot and we show how this knowledge can be exploited to plan and execute complex actions, like whole-body bimanual reaching.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Intelligent Robots and Systems
    Pages2606-2612
    Number of pages7
    DOIs
    Publication statusPublished - 2012
    Event25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012 - Vilamoura, Algarve
    Duration: 2012 Oct 72012 Oct 12

    Other

    Other25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012
    CityVilamoura, Algarve
    Period12/10/712/10/12

    Fingerprint

    Kinematics
    Robots

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Software
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    Cite this

    Jamone, L., Natale, L., Sandini, G., & Takanishi, A. (2012). Interactive online learning of the kinematic workspace of a humanoid robot. In IEEE International Conference on Intelligent Robots and Systems (pp. 2606-2612). [6385595] https://doi.org/10.1109/IROS.2012.6385595

    Interactive online learning of the kinematic workspace of a humanoid robot. / Jamone, Lorenzo; Natale, Lorenzo; Sandini, Giulio; Takanishi, Atsuo.

    IEEE International Conference on Intelligent Robots and Systems. 2012. p. 2606-2612 6385595.

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

    Jamone, L, Natale, L, Sandini, G & Takanishi, A 2012, Interactive online learning of the kinematic workspace of a humanoid robot. in IEEE International Conference on Intelligent Robots and Systems., 6385595, pp. 2606-2612, 25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012, Vilamoura, Algarve, 12/10/7. https://doi.org/10.1109/IROS.2012.6385595
    Jamone L, Natale L, Sandini G, Takanishi A. Interactive online learning of the kinematic workspace of a humanoid robot. In IEEE International Conference on Intelligent Robots and Systems. 2012. p. 2606-2612. 6385595 https://doi.org/10.1109/IROS.2012.6385595
    Jamone, Lorenzo ; Natale, Lorenzo ; Sandini, Giulio ; Takanishi, Atsuo. / Interactive online learning of the kinematic workspace of a humanoid robot. IEEE International Conference on Intelligent Robots and Systems. 2012. pp. 2606-2612
    @inproceedings{f006da9455b14d41874dcdc70cbce541,
    title = "Interactive online learning of the kinematic workspace of a humanoid robot",
    abstract = "We describe an interactive learning strategy that enables a humanoid robot to build a representation of its workspace: we call it a Reachable Space Map. The robot learns this map autonomously and online during the execution of goal-directed reaching movements; reaching control is based on kinematic models that are learned online as well. The map can be used to estimate the reachability of a fixated object and to plan preparatory movements (e.g. bending or rotating the waist) that improve the effectiveness of the subsequent reaching action. Three main concepts make our solution innovative with respect to previous works: the use of a gaze-centered motor representation to describe the robot workspace, the primary role of action in building and representing knowledge (i.e. interactive learning), the realization of autonomous online learning. We evaluate our strategy by learning the workspace of a simulated humanoid robot and we show how this knowledge can be exploited to plan and execute complex actions, like whole-body bimanual reaching.",
    author = "Lorenzo Jamone and Lorenzo Natale and Giulio Sandini and Atsuo Takanishi",
    year = "2012",
    doi = "10.1109/IROS.2012.6385595",
    language = "English",
    isbn = "9781467317375",
    pages = "2606--2612",
    booktitle = "IEEE International Conference on Intelligent Robots and Systems",

    }

    TY - GEN

    T1 - Interactive online learning of the kinematic workspace of a humanoid robot

    AU - Jamone, Lorenzo

    AU - Natale, Lorenzo

    AU - Sandini, Giulio

    AU - Takanishi, Atsuo

    PY - 2012

    Y1 - 2012

    N2 - We describe an interactive learning strategy that enables a humanoid robot to build a representation of its workspace: we call it a Reachable Space Map. The robot learns this map autonomously and online during the execution of goal-directed reaching movements; reaching control is based on kinematic models that are learned online as well. The map can be used to estimate the reachability of a fixated object and to plan preparatory movements (e.g. bending or rotating the waist) that improve the effectiveness of the subsequent reaching action. Three main concepts make our solution innovative with respect to previous works: the use of a gaze-centered motor representation to describe the robot workspace, the primary role of action in building and representing knowledge (i.e. interactive learning), the realization of autonomous online learning. We evaluate our strategy by learning the workspace of a simulated humanoid robot and we show how this knowledge can be exploited to plan and execute complex actions, like whole-body bimanual reaching.

    AB - We describe an interactive learning strategy that enables a humanoid robot to build a representation of its workspace: we call it a Reachable Space Map. The robot learns this map autonomously and online during the execution of goal-directed reaching movements; reaching control is based on kinematic models that are learned online as well. The map can be used to estimate the reachability of a fixated object and to plan preparatory movements (e.g. bending or rotating the waist) that improve the effectiveness of the subsequent reaching action. Three main concepts make our solution innovative with respect to previous works: the use of a gaze-centered motor representation to describe the robot workspace, the primary role of action in building and representing knowledge (i.e. interactive learning), the realization of autonomous online learning. We evaluate our strategy by learning the workspace of a simulated humanoid robot and we show how this knowledge can be exploited to plan and execute complex actions, like whole-body bimanual reaching.

    UR - http://www.scopus.com/inward/record.url?scp=84872311687&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84872311687&partnerID=8YFLogxK

    U2 - 10.1109/IROS.2012.6385595

    DO - 10.1109/IROS.2012.6385595

    M3 - Conference contribution

    SN - 9781467317375

    SP - 2606

    EP - 2612

    BT - IEEE International Conference on Intelligent Robots and Systems

    ER -