arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.06695cs.ROcs.LG
收藏

一种用于操作嵌入的运动分类法

A Motion Taxonomy for Manipulation Embedding

University of South Florida(南佛罗里达大学)

David Paulius, Nicholas Eales, Yu Sun

摘要:

为了从机械的角度来表示运动,本文探讨了使用运动分类的运动嵌入。使用这种分类法,操作可以被描述和表示为称为运动代码的二进制字符串。运动代码捕获机械属性,如接触类型和轨迹,这些属性应用于定义运动之间的合适距离度量或深度学习和强化学习的损失函数。运动代码还可用于合并别名或群集共享相似特性的运动类型。使用现有的数据集作为参考,我们讨论了如何创建运动代码,并根据直觉和真实数据将其分配给日常生活活动中常见的动作。运动代码进行比较,从预先训练的Word2Vec模型的矢量,我们表明,运动代码保持的距离,密切匹配的现实操纵。

英文摘要:

To represent motions from a mechanical point of view, this paper explores motion embedding using the motion taxonomy. With this taxonomy, manipulations can be described and represented as binary strings called motion codes. Motion codes capture mechanical properties, such as contact type and trajectory, that should be used to define suitable distance metrics between motions or loss functions for deep learning and reinforcement learning. Motion codes can also be used to consolidate aliases or cluster motion types that share similar properties. Using existing data sets as a reference, we discuss how motion codes can be created and assigned to actions that are commonly seen in activities of daily living based on intuition as well as real data. Motion codes are compared to vectors from pre-trained Word2Vec models, and we show that motion codes maintain distances that closely match the reality of manipulation.

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。

↑