End-to-end visuomotor control is emerging as a compelling solution for robot manipulation tasks. However, imitation learning-based visuomotor control approaches tend to suffer from a common limitation, lacking the ability to recover from an out-of-distribution state caused by compounding errors. In this paper, instead of using tactile feedback or explicitly detecting the failure through vision, we investigate using the uncertainty of a policy neural network. We propose a novel uncertainty-based approach to detect and recover from failure cases. Our hypothesis is that policy uncertainties can implicitly indicate the potential failures in the visuomotor control task and that robot states with minimum uncertainty are more likely to lead to task success. To recover from high uncertainty cases, the robot monitors its uncertainty along a trajectory and explores possible actions in the state-action space to bring itself to a more certain state. Our experiments verify this hypothesis and show a significant improvement on task success rate: 12% in pushing, 15% in pick-and-reach and 22% in pick-and-place.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Introspective visuomotor control: exploiting uncertainty in deep visuomotor control for failure recovery


    Beteiligte:
    Hung, C-M (Autor:in) / Sun, L (Autor:in) / Wu, Y (Autor:in) / Havoutis, I (Autor:in) / Posner, I (Autor:in)

    Erscheinungsdatum :

    10.03.2022



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Virtual Hand Illusion Induced by Visuomotor Correlations.

    M. V. Sanchez / B. Spanlang / M. Slater et al. | BASE | 2010

    Freier Zugriff


    Goal-conditioned end-to-end visuomotor control for versatile skill primitives

    Groth, O / Hung, CM / Vedaldi, A et al. | BASE | 2022

    Freier Zugriff

    Virtual Hand Illusion Induced by Visuomotor Correlations

    Sanchez-Vives, MV / Spanlang, B / Frisoli, A et al. | BASE | 2010

    Freier Zugriff

    Control Order and Visuomotor Strategy Development for Joystick-Steered Underground Shuttle Cars

    Cloete, Steven / Zupanc, Christine / Burgess-Limerick, Robin et al. | Tema Archiv | 2014