Corpus ID: 210920445

Multi-Fingered Grasp Planning via Inference in Deep Neural Networks

  title={Multi-Fingered Grasp Planning via Inference in Deep Neural Networks},
  author={Qingkai Lu and Mark Van der Merwe and Balakumar Sundaralingam and Tucker Hermans},
  • Qingkai Lu, Mark Van der Merwe, +1 author Tucker Hermans
  • Published 2020
  • Computer Science
  • ArXiv
  • We propose a novel approach to multi-fingered grasp planning leveraging learned deep neural network models. We train a voxel-based 3D convolutional neural network to predict grasp success probability as a function of both visual information of an object and grasp configuration. We can then formulate grasp planning as inferring the grasp configuration which maximizes the probability of grasp success. In addition, we learn a prior over grasp configurations as a mixture density network conditioned… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper

    Multi-Fingered Active Grasp Learning
    • 4
    • PDF
    Learning Continuous 3D Reconstructions for Geometrically Aware Grasping
    • 14
    • PDF
    Robotic Grasp Control using Tactile Feedback
    • Highly Influenced
    • PDF
    In-Hand Object-Dynamics Inference using Tactile Fingertips
    • 2
    • PDF


    Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network
    • 39
    • PDF
    Grasp Planning by Optimizing a Deep Learning Scoring Function
    • 13
    • PDF
    Modeling Grasp Type Improves Learning-Based Grasp Planning
    • 14
    • PDF
    Generating Grasp Poses for a High-DOF Gripper Using Neural Networks
    • 16
    • PDF
    Generating multi-fingered robotic grasps via deep learning
    • 67
    • PDF
    Deep learning a grasp function for grasping under gripper pose uncertainty
    • 158
    • PDF
    High precision grasp pose detection in dense clutter
    • 176
    • PDF
    6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
    • 58
    • PDF
    Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
    • 8
    • PDF
    Real-time grasp detection using convolutional neural networks
    • 364
    • PDF