Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
Robert Lee, Daniel Ward, Vibhavari Dasagi, Akansel Cosgun, Juxi Leitner, Peter Corke
Published at CoRL2020
Embedded Files
DemoVideoSmall.mp4
Manipulating deformable objects, such as fabric, is a long standing problem in robotics, with state estimation and control posing a significant challenge for traditional methods. In this paper, we show that it is possible to learn fabric folding skills in only an hour of self-supervised real robot experience, without human supervision or simulation. Our approach relies on fully convolutional networks and the manipulation of visual inputs to exploit learned features, allowing us to create an expressive goal-conditioned pick and place policy that can be trained efficiently with real world robot data only. Folding skills are learned with only a sparse reward function and thus do not require reward function engineering, merely an image of the goal configuration. We demonstrate our method on a set of towel-folding tasks, and show that our approach is able to discover sequential folding strategies, purely from trial-and-error. We achieve state-of-the-art results without the need for demonstrations or simulation, used in prior approaches.
Overview of our approach. We create an expressive fabric folding policy by manipulating the input image. We scale and rotate the image and pick the max value over the output heatmaps.
Examples of successful trajectories for each of the six goals. Robot actions are visualized as red arrows.
Page updated
Google Sites
Report abuse