Recent work has shown that 2-arm “fling” motions can be effective for garment smoothing. We consider single-arm fling motions. Unlike 2-arm fling motions, which require little robot trajectory parameter tuning, single-arm fling motions are very sensitive to trajectory parameters. We consider a single 6-DOF robot arm that learns fling trajectories to achieve high garment coverage. Given a garment grasp point, the robot explores different parameterized fling trajectories in physical experiments. To improve learning efficiency, we propose a coarse-to-fine learning method that first uses a multi-armed bandit (MAB) framework to efficiently find a candidate fling action, which it then refines via a continuous optimization method. Further, we propose novel training and execution-time stopping criteria based on fling outcome uncertainty; the training-time stopping criterion increases data efficiency while the execution-time stopping criteria leverage repeated fling actions to increase performance. Compared to baselines, the proposed method significantly accelerates learning. Moreover, with prior experience on similar garments collected through self-supervision, the MAB learning time for a new garment is reduced by up to 87%. We evaluate on 36 real garments: towels, T-shirts, long-sleeve shirts, dresses, sweat pants, and jeans. Results suggest that using prior experience, a robot requires under 30 min to learn a fling action for a novel garment that achieves 60–94% coverage. Supplementary material can be found at https://sites.google.com/view/single-arm-fling.
Efficiently Learning Single-Arm Fling Motions to Smooth Garments
Springer Proceedings in Advanced Robotics
The International Symposium of Robotics Research ; 2022 ; Geneva, Switzerland September 25, 2022 - September 30, 2022
2023-03-08
16 pages
Article/Chapter (Book)
Electronic Resource
English
Online Contents | 2006