# Efficiently Learning Single-Arm Fling Motions to Smooth Garments

arXiv: https://arxiv.org/abs/2206.08921 · HTML: https://mlsanity.com/paper/2206.08921/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2022.

## Built on by (most cited first, 8 of 8)

- [SpeedFolding: Learning Efficient Bimanual Folding of Garments](https://mlsanity.com/paper/2208.10552/) (2022)
- [That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulation](https://mlsanity.com/paper/2210.01116/) (2022)
- [SGTM 2.0: Autonomously Untangling Long Cables using Interactive Perception](https://mlsanity.com/paper/2209.13706/) (2022)
- [One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes](https://mlsanity.com/paper/2503.01092/) (2025)
- [Automating Deformable Gasket Assembly](https://mlsanity.com/paper/2408.12593/) (2024)
- [DexKnot: Generalizable Visuomotor Policy Learning for Dexterous Bag-Knotting Manipulation](https://mlsanity.com/paper/2603.07136/) (2026)
- [Periodic Steady-State Control of a Handkerchief-Spinning Task Using a Parallel Anti-Parallelogram Tendon-driven Wrist](https://mlsanity.com/paper/2604.17863/) (2026)
- [Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation](https://mlsanity.com/paper/2604.22102/) (2026)

## Abstract (arXiv)

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 minutes to learn a fling action for a novel garment that achieves 60-94% coverage.