Entanglements can cause robots to pick multiple parts within random bin picking applications. Previous approaches cope with this problem by shaking the gripped workpiece above the bin. However, these methods increase the cycle time and may decrease the robustness of the application. Therefore we propose a new method to separate entangled workpiece situations by using deep supervised learning. To generate annotated training data for a convolutional neural network we set up a simulation scene. In this scene, bins are filled with different amounts of sorted workpieces in several entangled situations. Each workpiece is then moved into different directions to path poses which are evenly distributed along the surface of a hemisphere. The emerging dataset consists of cropped depth images of entangled workpiece situations and several path poses. A serial connection of convolutional neural networks is trained on this dataset and proposes a sequence of poses yielding the general departure path. Finally, the performance of this method is validated on simulated data. To the best of our knowledge, our proposed method is the first systematic approach to find the best extraction strategy to separate entangled workpieces in a pile while decreasing the effective cycle time for gripping entangled workpieces and increasing the robustness significantly.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Using Deep Neural Networks to Separate Entangled Workpieces in Random Bin Picking


    Weitere Titelangaben:

    ARENA2036


    Beteiligte:
    Weißgraeber, Philipp (Herausgeber:in) / Heieck, Frieder (Herausgeber:in) / Ackermann, Clemens (Herausgeber:in) / Moosmann, Marius (Autor:in) / Spenrath, Felix (Autor:in) / Mönnig, Manuel (Autor:in) / Khalid, Muhammad Usman (Autor:in) / Jaumann, Marvin (Autor:in) / Rosport, Johannes (Autor:in) / Bormann, Richard (Autor:in)


    Erscheinungsdatum :

    2021-06-02


    Format / Umfang :

    9 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Using Deep Neural Networks to Separate Entangled Workpieces in Random Bin Picking

    Moosmann, Marius / Spenrath, Felix / Mönnig, Manuel et al. | TIBKAT | 2021


    An Inductive Logic Programming Approach for Entangled Tube Modeling in Bin Picking

    Leão, Gonçalo / Camacho, Rui / Sousa, Armando et al. | Springer Verlag | 2022


    WORKPIECES STACKING APPARATUS

    KANAI YUJI / WATANABE KATSUMI | Europäisches Patentamt | 2015

    Freier Zugriff

    Object Segmentation for Bin Picking Using Deep Learning

    Cordeiro, Artur / Rocha, Luís F. / Costa, Carlos et al. | Springer Verlag | 2022