In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which often are the kinematic and dynamic constraints of the system, are then only restored when synthesizing the motion, which introduces possibly heavy distortions. In this work, we propose to use those approximate trajectory distributions as close-to-optimal discriminators in the popular generative adversarial framework to stabilize and accelerate the learning procedure. The two problems of adaptability and robustness are addressed with our method. In order to adapt the motions to varying contexts, we propose to use a product of Gaussian policies defined in several parametrized task spaces. Robustness to perturbations and varying dynamics is ensured with the use of stochastic gradient descent and ensemble methods to learn the stochastic dynamics. Two experiments are performed on a 7-DoF manipulator to validate the approach.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Generative adversarial training of product of policies for robust and adaptive movement primitives


    Beteiligte:
    Pignat, Emmanuel (Autor:in) / Girgin, Hakan (Autor:in) / Calinon, Sylvain (Autor:in)

    Erscheinungsdatum :

    2020-10-10



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629




    Conditional Neural Movement Primitives

    M. Yunus Seker / Mert Imre / Justus Piater et al. | BASE | 2019

    Freier Zugriff

    Using probabilistic movement primitives in robotics

    Paraschos, A. | British Library Online Contents | 2018


    Dimensionality reduction for probabilistic movement primitives

    Colomé Figueras, Adrià / Neumann, Gerhard / Peters, Jan et al. | BASE | 2014

    Freier Zugriff

    Dimensionality reduction for probabilistic movement primitives

    Colomé, Adrià / Neumann, Gerhard / Peters, Jan et al. | BASE | 2014

    Freier Zugriff

    Automated Derivation of Primitives for Movement Classification

    Fod, A. / Mataric, M. J. / Jenkins, O. C. | British Library Online Contents | 2002