arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.13675cs.ROcs.CVcs.LG
收藏

Form2Fit:从模板中学习可泛化装配的形状先验

Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly

Stanford University(斯坦福大学);Google(谷歌);Columbia University(哥伦比亚大学)

Kevin Zakka, Andy Zeng, Johnny Lee, Shuran Song

摘要:

有没有可能学习机器人装配的策略,从而推广到新的对象?我们在套件组装任务的背景下探索这个想法。由于经典方法严重依赖于对象姿态估计,因此在没有3D CAD模型或特定于任务的训练数据的情况下,它们通常难以推广到新对象。在这项工作中,我们建议制定的工具包组装任务作为一个形状匹配问题,其目标是学习一个形状描述符,建立对象表面和它们的目标放置位置之间的几何对应关系,从视觉输入。这种公式使模型能够更广泛地了解形状和表面如何组合在一起进行组装--使其能够推广到新的对象和套件。为了获得我们的模型的训练数据,我们提出了一个自我监督的数据收集管道,通过拆卸完整的工具包来获得地面实况对象到位置的对应关系。我们由此产生的真实世界的系统,Form 2Fit,学习有效的拾取和放置策略,用于将对象组装成各种工具包-在不同的初始条件下(例如,不同的对象和工具包姿势)实现$90\%$平均成功率,在多个工具包的新配置下成功$94\%$,以及在全新的对象和工具包上成功超过$86\%$。

英文摘要:

Is it possible to learn policies for robotic assembly that can generalize to new objects? We explore this idea in the context of the kit assembly task. Since classic methods rely heavily on object pose estimation, they often struggle to generalize to new objects without 3D CAD models or task-specific training data. In this work, we propose to formulate the kit assembly task as a shape matching problem, where the goal is to learn a shape descriptor that establishes geometric correspondences between object surfaces and their target placement locations from visual input. This formulation enables the model to acquire a broader understanding of how shapes and surfaces fit together for assembly -- allowing it to generalize to new objects and kits. To obtain training data for our model, we present a self-supervised data-collection pipeline that obtains ground truth object-to-placement correspondences by disassembling complete kits. Our resulting real-world system, Form2Fit, learns effective pick and place strategies for assembling objects into a variety of kits -- achieving $90\%$ average success rates under different initial conditions (e.g. varying object and kit poses), $94\%$ success under new configurations of multiple kits, and over $86\%$ success with completely new objects and kits.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑