Corpus ID: 214714285

Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images

  title={Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images},
  author={Aditya Ganapathi and Priya Sundaresan and Brijen Thananjeyan and A. Balakrishna and Daniel Seita and J. Grannen and Minho Hwang and Ryan Hoque and J. Gonzalez and N. Jamali and K. Yamane and Soshi Iba and Ken Goldberg},
  • Aditya Ganapathi, Priya Sundaresan, +10 authors Ken Goldberg
  • Published 2020
  • Computer Science
  • ArXiv
  • Robotic fabric manipulation is challenging due to the infinite dimensional configuration space and complex dynamics. In this paper, we learn visual representations of deformable fabric by training dense object descriptors that capture correspondences across images of fabric in various configurations. The learned descriptors capture higher level geometric structure, facilitating design of explainable policies. We demonstrate that the learned representation facilitates multistep fabric smoothing… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper.

    Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
    • 2
    • Highly Influenced
    • PDF
    Untangling Dense Knots by Learning Task-Relevant Keypoints
    Learning Robot Policies for Untangling Dense Knots in Linear Deformable Structures
    • 1
    • PDF


    Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data
    • 6
    • PDF
    Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary
    • 13
    • PDF
    VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
    • 6
    • PDF
    Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor
    • 9
    Learning Predictive Representations for Deformable Objects Using Contrastive Estimation
    • 12
    • PDF
    Cloth Manipulation Using Random-Forest-Based Imitation Learning
    • 5
    • PDF
    Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making.
    • 16
    • PDF
    Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
    • 76
    • Highly Influential
    • PDF
    Learning to Manipulate Deformable Objects without Demonstrations
    • 16
    • PDF
    Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
    • 16
    • PDF