Paper Info
Title
Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics
Abstract
Robotic fabric manipulation is challenging due to the infinite dimensional configuration space, self-occlusion, and complex dynamics of fabrics. There has been significant prior work on learning policies for specific fabric manipulation tasks, but comparatively less focus on algorithms which can perform many different tasks. We take a step towards this goal by learning point-pair correspondences across different fabric configurations in simulation. Then, given a single demonstration of a new task from an initial fabric configuration, these correspondences can be used to compute geometrically equivalent actions in a new fabric configuration. This makes it possible to define policies to robustly imitate a broad set of multi-step fabric smoothing and folding tasks. The resulting policies achieve 80.3% average task success rate across 10 fabric manipulation tasks on two different physical robotic systems. Results also suggest robustness to fabrics of various colors, sizes, and shapes. See https : / /tinyurl . com/ fabric-descriptors for supplementary material and videos.
Year
DOI
Venue
2021
10.1109/ICRA48506.2021.9561980
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
Keywords
DocType
Volume
Robustness (computer science),Smoothing,Configuration space,Complex dynamics,Computer vision,Computer science,Artificial intelligence,Robotic systems,Surgical robot
Conference
2021
Issue
ISSN
Citations 
1
1050-4729
0
PageRank 
References 
Authors
0.34
7
13
Name
Order
Citations
PageRank
Aditya Ganapathi110.68
Priya Sundaresan212.37
Brijen Thananjeyan3133.93
Ashwin Balakrishna446.80
Daniel Seita512.03
Grannen Jennifer601.69
Minho Hwang774.18
Ryan Hoque812.03
Joseph E. Gonzalez92219102.68
Nawid Jamali1072.55
Katsu Yamane1142.12
Soshi Iba12707.27
Ken Goldberg1303.38