Grasp stability prediction of unknown objects is crucial to enable autonomous robotic manipulation in an unstructured environment. Even if prior information about the object is available, real-time local exploration might be necessary to mitigate object modelling inaccuracies. This paper presents an approach to predict safe grasps of unknown objects using depth vision and a dexterous robot hand equipped with tactile feedback. Our approach does not assume any prior knowledge about the objects. First, an object pose estimation is obtained from RGB-D sensing; then, the object is explored haptically to maximise a given grasp metric. We compare two probabilistic methods (i.e. standard and unscented Bayesian Optimisation) against random exploration (i.e. uniform grid search). Our experimental results demonstrate that these probabilistic methods can provide confident predictions after a limited number of exploratory observations, and that unscented Bayesian Optimisation can find safer grasps, taking into account the uncertainty in robot sensing and grasp execution.


    Access

    Download


    Export, share and cite



    Title :

    Grasp Stability Prediction for a Dexterous Robotic Hand Combining Depth Vision and Haptic Bayesian Exploration.


    Contributors:
    Siddiqui, MS (author) / Coppola, C (author) / Solak, G (author) / Jamone, L (author)

    Publication date :

    2021-01-01


    Remarks:

    doi:10.3389/frobt.2021.703869



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629




    Vision-based perception for dexterous hand-arm teleoperation

    Li, Shuang / Universität Hamburg / Universität Hamburg, Fakultät für Mathematik, Informatik und Naturwissenschaften et al. | TIBKAT | 2021

    Free access

    A three-finger multisensory hand for dexterous space robotic tasks

    Murase, Yuichi / Komada, Satoru / Uchiyama, Takashi et al. | NTRS | 1994



    Motion mapping in master-slave grasp for dexterous hands

    Jiting, L. / Yuru, Z. | British Library Online Contents | 2005