Corpus ID: 214714285

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

@article{Ganapathi2020LearningTS,
  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},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.12698}
}
  • Aditya Ganapathi, Priya Sundaresan, +10 authors Ken Goldberg
  • Published 2020
  • Computer Science, Engineering
  • 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

    Figures, Tables, and Topics from this paper.

    Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
    • 1
    • Highly Influenced
    • PDF
    Learning Robot Policies for Untangling Dense Knots in Linear Deformable Structures
    • Jennifer Grannen, Priya Sundaresan, +6 authors Ken Goldberg
    • 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 53 REFERENCES
    Microsoft COCO: Common Objects in Context
    • 10,292
    • PDF
    Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection
    • 963
    • PDF
    Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours
    • 619
    • PDF
    (CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
    • 349
    • PDF
    QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
    • 283
    • PDF
    Self-Supervised Visual Descriptor Learning for Dense Correspondence
    • 91
    • PDF