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.


    Access

    Download


    Export, share and cite



    Title :

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


    Contributors:
    Hung, C-M (author) / Sun, L (author) / Wu, Y (author) / Havoutis, I (author) / Posner, I (author)

    Publication date :

    2022-03-10



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629



    Virtual Hand Illusion Induced by Visuomotor Correlations.

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

    Free access


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

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

    Free access

    Virtual Hand Illusion Induced by Visuomotor Correlations

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

    Free access

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

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