arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.14078cs.RO
收藏

从人类演示中学习周期性任务

Learning Periodic Tasks from Human Demonstrations

Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学);Meta AI

Jingyun Yang, Junwu Zhang, Connor Settle, Akshara Rai, Rika Antonova, Jeannette Bohg

摘要:

我们开发了一种从视觉演示中学习周期性任务的方法。其核心思想是利用策略结构中的周期性来对任务的周期性方面进行建模。我们使用主动学习来优化节奏动态运动基元(rDMP)的参数,并提出了一个目标,以最大化机器人操纵的对象运动与人类视频演示中所需运动之间的相似性。我们考虑的任务与可变形的物体和颗粒物质的状态是具有挑战性的表示和跟踪:擦拭表面的布,缠绕电缆/电线,和搅拌颗粒物质用勺子。我们的方法不需要跟踪标记或手动注释。初始训练数据由机器人和人类与物体的随机不成对交互的10分钟视频组成。我们使用这些对关键点模型进行无监督学习,以获得与任务无关的视觉对应。然后,我们使用贝叶斯优化优化rDMPs从一个单一的人类视频演示在几个机器人试验。我们目前的仿真和硬件实验来验证我们的方法。

英文摘要:

We develop a method for learning periodic tasks from visual demonstrations. The core idea is to leverage periodicity in the policy structure to model periodic aspects of the tasks. We use active learning to optimize parameters of rhythmic dynamic movement primitives (rDMPs) and propose an objective to maximize the similarity between the motion of objects manipulated by the robot and the desired motion in human video demonstrations. We consider tasks with deformable objects and granular matter whose states are challenging to represent and track: wiping surfaces with a cloth, winding cables/wires, and stirring granular matter with a spoon. Our method does not require tracking markers or manual annotations. The initial training data consists of 10-minute videos of random unpaired interactions with objects by the robot and human. We use these for unsupervised learning of a keypoint model to get task-agnostic visual correspondences. Then, we use Bayesian optimization to optimize rDMPs from a single human video demonstration within few robot trials. We present simulation and hardware experiments to validate our approach.

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。

↑