Robotic grasping has been a prevailing problem ever since humans began creating robots to execute human-like tasks. The problems are usually due to the involvement of moving parts and sensors. Inaccuracy in sensor data usually leads to unexpected results. Researchers have used a variety of sensors for improving manipulation tasks in robots. We focus specifically on grasping unknown objects using mobile service robots. An approach using convolutional neural networks to generate grasp points in a scene using RGBD sensor data is proposed. Two convolutional neural networks that perform grasp detection in a top down scenario are evaluated, enhanced and compared in a more general scenario. Experiments are performed in a simulated environment as well as the real world. The results are used to understand how the difference in sensor data can affect grasping and enhancements are made to overcome these effects and to optimize the solution.


    Access

    Download


    Export, share and cite



    Title :

    Grasping Unknown Objects Using Convolutional Neural Networks



    Publication date :

    2020-08-25


    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    Grasping Unknown Objects Using Convolutional Neural Networks

    Krishna Prasad, Pranav (M.Sc.) | BASE | 2020

    Free access

    Task Understanding for Grasping Unknown Objects

    Kaneko, M. | British Library Online Contents | 1993


    Framework for Autonomous Underwater Grasping of Unknown Objects

    Peñalver Monfort, Antonio | BASE | 2019

    Free access

    Grasping unknown objects in clutter by superquadric representation

    Makhal, Abhijit / Thomas, Federico / Pérez Gracia, Alba | BASE | 2018

    Free access

    Discovery, segmentation and reactive grasping of unknown objects

    Schiebener, David / Schill, Julian / Asfour, Tamim | IEEE | 2012