Feedback-based Fabric Strip Folding
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 773-778
Abstract
Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Repeatable Folding Task by Humanoid Robot Worker Using Deep LearningIEEE Robotics and Automation Letters, 2016
- Accuracy of Robotic Elastic Object Manipulation as a Function of Material Properties2016
- Folding Clothes Autonomously: A Complete PipelineIEEE Transactions on Robotics, 2016
- Physics-based model of a rectangular garment for robotic folding2016
- Folding deformable objects using predictive simulation and trajectory optimization2015
- Robotic Garment Folding: Precision Improvement and Workspace Enlargement2015
- MuJoCo: A physics engine for model-based control2012
- A geometric approach to robotic laundry foldingThe International Journal of Robotics Research, 2011
- Gravity-Based Robotic Cloth Folding2010
- Completely Derandomized Self-Adaptation in Evolution StrategiesEvolutionary Computation, 2001