Extracting a known target object from a pile of other objects in a cluttered environment is a challenging robotic manipulation task encountered in many robotic applications. In such conditions, the target object touches or is covered by adjacent obstacle objects, thus rendering traditional grasping techniques ineffective. In this paper, we propose a pushing policy aiming at singulating the target object from its surrounding clutter, by means of lateral pushing movements of both the neighboring objects and the target object until sufficient 'grasping room' has been achieved. To achieve the above goal we employ reinforcement learning and particularly Deep Q-learning (DQN) to learn optimal push policies by trial and error. A novel Split DQN is proposed to improve the learning rate and increase the modularity of the algorithm. Experiments show that although learning is performed in a simulated environment the transfer of learned policies to a real environment is effective thanks to robust feature selection. Finally we demonstrate that the modularity of the algorithm allows the addition of extra primitives without retraining the model from scratch.


    Access

    Download


    Export, share and cite



    Title :

    Split Deep Q-Learning for Robust Object Singulation


    Contributors:

    Publication date :

    2020-05-31



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    SplitAMC: Split Learning for Robust Automatic Modulation Classification

    Park, Jihoon / Oh, Seungeun / Kim, Seong-Lyun | IEEE | 2023


    Automated Stack Singulation for Technical Textiles Using Sensor Supervised Low Pressure Suction Grippers

    Wirth, Benjamin / Schwind, Tizian / Friedmann, Marco et al. | Springer Verlag | 2023

    Free access


    Deep Learning for Robust Vehicle Identification

    Ramajo Ballester, Álvaro / González Cepeda, Jacobo / Armingol Moreno, José María | Springer Verlag | 2022


    Deep cross-domain flying object classification for robust UAV detection

    Schumann, A. / Sommer, L. / Klatte, J. et al. | Fraunhofer Publica | 2017

    Free access