arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.02201cs.ROcs.LG
收藏

基于微分仿真的接触丰富操作任务的工具形态学习

Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulation

Stanford University(斯坦福大学);FANUC(发那科)

Mengxi Li, Rika Antonova, Dorsa Sadigh, Jeannette Bohg

摘要:

当人类执行接触丰富的操作任务时,通常需要定制工具来简化任务。例如,我们使用各种各样的餐具来处理食物,比如刀、叉和勺子。类似地,机器人可以受益于使它们能够更容易地完成各种任务的专用工具。我们提出了一个端到端的框架,自动学习工具形态接触丰富的操作任务,利用微分物理模拟器。以前的工作依赖于手动构建的先验,需要详细说明的3D对象模型,把握姿势和任务描述,以方便搜索或优化过程。我们的方法只需要定义目标的任务性能,并使学习一个强大的形态,通过随机变化的任务。我们通过将其作为一个持续学习问题来进行优化。我们证明了我们的方法的有效性,设计新的工具,在几个场景中,如缠绕绳索,翻转一个盒子,并推动豌豆到一个勺子在模拟。此外,真实机器人的实验表明,我们的方法发现的工具形状有助于他们在这些场景中取得成功。

英文摘要:

When humans perform contact-rich manipulation tasks, customized tools are often necessary to simplify the task. For instance, we use various utensils for handling food, such as knives, forks and spoons. Similarly, robots may benefit from specialized tools that enable them to more easily complete a variety of tasks. We present an end-to-end framework to automatically learn tool morphology for contact-rich manipulation tasks by leveraging differentiable physics simulators. Previous work relied on manually constructed priors requiring detailed specification of a 3D object model, grasp pose and task description to facilitate the search or optimization process. Our approach only requires defining the objective with respect to task performance and enables learning a robust morphology through randomizing variations of the task. We make this optimization tractable by casting it as a continual learning problem. We demonstrate the effectiveness of our method for designing new tools in several scenarios, such as winding ropes, flipping a box and pushing peas onto a scoop in simulation. Additionally, experiments with real robots show that the tool shapes discovered by our method help them succeed in these scenarios.

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。

↑