让机器人学会通用挂衣，能自动把各种衣服挂上衣架。
RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments
- 拆解挂衣任务为子步骤，用低维动作参数化提升学习效率。
- 在仿真中训练，真实世界对8种未见衣服成功率达75%。
- 仅需单视角深度图和物体掩码，适应性强适合实际应用。
挂衣任务中，将衣架插入衣物是关键但鲜有研究的环节。本文针对初始平铺在桌面上的多种未见衣物，实现衣架插入。由于任务时长较长、衣物自由度高且数据稀缺，我们首先将任务分解为多个子任务，并将每个子任务建模为策略学习问题，提出低维动作参数化方法。为解决数据不足问题，构建专属仿真环境并生成144个合成服装资产，高效获取高质量训练数据。方法仅使用单视角深度图像和物体掩码作为输入，有效缓解了仿真到现实的视觉差异，具备强泛化能力。仿真与真实世界中的大量实验验证了有效性：在仿真中训练后，对8种真实世界未见衣物的成功率达到75%。
原文摘要 · Abstract (English)
For the task of hanging clothes, learning how to insert a hanger into a garment is a crucial step, but has rarely been explored in robotics. In this work, we address the problem of inserting a hanger into various unseen garments that are initially laid flat on a table. This task is challenging due to its long-horizon nature, the high degrees of freedom of the garments and the lack of data. To simplify the learning process, we first propose breaking the task into several subtasks. Then, we formulate each subtask as a policy learning problem and propose a low-dimensional action parameterization. To overcome the challenge of limited data, we build our own simulator and create 144 synthetic clothing assets to effectively collect high-quality training data. Our approach uses single-view depth images and object masks as input, which mitigates the Sim2Real appearance gap and achieves high generalization capabilities for new garments. Extensive experiments in both simulation and reality validate our proposed method. By training on various garments in the simulator, our method achieves a 75\% success rate with 8 different unseen garments in the real world.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。