Learning to Put On a Knit Cap in a Head-Centric Policy Space

Lukas Twardon; Helge J. Ritter

RA-L 201810 citations

Learning to Put On a Knit Cap in a Head-Centric Policy Space

Abstract

Robotic manipulation of such highly deformable objects as clothes is a challenging problem. Robot-assisted dressing adds even more complexity as the garment motions must be aligned with a human body under conditions of strong and variable occlusion. As a step toward solutions for the general task, we consider the example of a dual-arm robot with attached anthropomorphic hands that learns to put a knit cap on a styrofoam head. Our approach avoids modeling the details of the garment and its deformations. Instead, we demonstrate that a head-centric policy parameterization, combined with a suitable objective function for determining the right amount of contact between the cap and the head, enables a direct policy search algorithm to find successful trajectories for this task. We also show how a toy problem that mirrors some of the task constraints can be used to efficiently structure hyperparameter search. Additionally, we suggest a point cloud based algorithm for modeling the head as an ellipsoid which is required for defining the policy space.

BibTeX

@inproceedings{ral2018_learningtoputona,
  title = {Learning to Put On a Knit Cap in a Head-Centric Policy Space},
  author = {Lukas Twardon and Helge J. Ritter},
  booktitle = {RA-L 2018},
  year = {2018}
}