This work presents a probabilistic model for learning robot tasks from human demonstrations using kinesthetic teaching. The difference with respect to previous works is that a complete state of the robot is used to obtain a consistent representation of the dynamics of the task. The learning framework is based on hidden Markov models and Gaussian mixture regression, used for coding and reproducing the skills. Benefits of the proposed approach are shown in the execution of a simple self-crossing trajectory by a 7-DoF manipulator. ; Preprint


    Access

    Download


    Export, share and cite



    DYNAMICALLY RECONFIGURABLE ROBOT

    GROSS WILLIAM TOD | European Patent Office | 2024

    Free access

    Optimal control prediction of dynamically consistent walking motions

    Pallares Lopez, Roger | BASE | 2017

    Free access

    A Consistent Failure Model for Probabilistic Analysis of Shallow Foundations

    Kisse, A. | HENRY – Federal Waterways Engineering and Research Institute (BAW) | 2011

    Free access

    Learning probabilistic structure for human motion detection

    Song, Y. / Goncalves, L. / Perona, P. | IEEE | 2001


    Learning Probabilistic Structure for Human Motion Detection

    Song, Y. / Goncalves, L. / Perona, P. et al. | British Library Conference Proceedings | 2001