GrOMP：抓取物体流形投影用于多模态模仿学习的操控
GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation
AI总结：
GrOMP通过抓取物体流形投影技术，提升多模态模仿学习中操控任务的精度和鲁棒性，基于累积误差界理论，利用触觉反馈在多个装配任务中验证其有效性。
摘要：
模仿学习（IL）在学习重复性的操控任务，如工业装配任务中具有巨大潜力。然而，其效果往往受到轨迹精度不足的限制，这通常是由于累积误差所致。在本文中，我们引入了抓取物体流形投影（GrOMP），一种交互式方法，通过将非刚性抓取的物体限制在较低维的流形上来缓解这些误差。GrOMP假设一个精确的任务中，一个执行器持有一个可能在抓取内移动的物体，并以可观察的方式必须与一个接地部分配对。关键的是，所有GrOMP的改进都是从用于训练基础IL策略的相同专家数据集中学习的，并且通过基于n臂老虎机的交互组件进行调整。我们提出了GrOMP在IL文献中著名的累积误差界上的理论基础。我们使用触觉反馈在四个精确装配任务上展示了该框架，并注意到该方法仍然模态无关。数据和视频可在williamvdb.github.io/GrOMPsite上获得。
英文摘要：
Imitation Learning (IL) holds great potential for learning repetitive manipulation tasks, such as those in industrial assembly. However, its effectiveness is often limited by insufficient trajectory precision due to compounding errors. In this paper, we introduce Grasped Object Manifold Projection (GrOMP), an interactive method that mitigates these errors by constraining a non-rigidly grasped object to a lower-dimensional manifold. GrOMP assumes a precise task in which a manipulator holds an object that may shift within the grasp in an observable manner and must be mated with a grounded part. Crucially, all GrOMP enhancements are learned from the same expert dataset used to train the base IL policy, and are adjusted with an n-arm bandit-based interactive component. We propose a theoretical basis for GrOMP's improvement upon the well-known compounding error bound in IL literature. We demonstrate the framework on four precise assembly tasks using tactile feedback, and note that the approach remains modality-agnostic. Data and videos are available at williamvdb.github.io/GrOMPsite.
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。
