Active Learning of Probabilistic Movement Primitives
Active Learning of Probabilistic Movement Primitives
复制标题
概率运动原语的主动学习
DOI：
10.1109/humanoids43949.2019.9035026
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Tucker Hermans
中科院分区：
文献类型：
--
作者：
Adam Conkey;Tucker Hermans
概率运动基元（ProMP）定义了具有相关联的反馈策略的轨迹上的分布。ProMP通常从人类演示中初始化，并通过概率操作实现任务泛化。然而，目前文献中没有原则性指导来确定教师应该提供多少次演示以及什么构成促进概括的“良好”演示。在本文中，我们提出了一种主动学习的方法来学习一个图书馆的ProMP能够在给定的空间任务泛化。我们利用不确定性抽样技术来生成一个任务实例，教师应该提供一个示范。如果可能，将所提供的演示合并到现有的ProMP中，或者如果确定新的ProMP与现有的演示太不相似，则从演示创建新的ProMP。我们提供了一个常见的主动学习指标之间的定性比较，这种比较的动机，我们提出了一种新的不确定性采样方法命名为“最大马氏距离”。我们在一个真实的KUKA机器人上进行抓取实验，并表明我们新的主动学习方法比空间上的随机采样方法具有更少的演示，从而实现了更好的任务泛化。
A Probabilistic Movement Primitive (ProMP) defines a distribution over trajectories with an associated feedback policy. ProMPs are typically initialized from human demonstrations and achieve task generalization through probabilistic operations. However, there is currently no principled guidance in the literature to determine how many demonstrations a teacher should provide and what constitutes a “good” demonstration for promoting generalization. In this paper, we present an active learning approach to learning a library of ProMPs capable of task generalization over a given space. We utilize uncertainty sampling techniques to generate a task instance for which a teacher should provide a demonstration. The provided demonstration is incorporated into an existing ProMP if possible, or a new ProMP is created from the demonstration if it is determined that it is too dissimilar from existing demonstrations. We provide a qualitative comparison between common active learning metrics; motivated by this comparison we present a novel uncertainty sampling approach named “Greatest Mahalanobis Distance.” We perform grasping experiments on a real KUKA robot and show our novel active learning measure achieves better task generalization with fewer demonstrations than a random sampling over the space.
影响因子：
3.5
作者：
Sundaralingam, Balakumar;Hermans, Tucker
通讯作者：
Hermans, Tucker
影响因子：
7.8
作者：
Gomez-Gonzalez, Sebastian;Neumann, Gerhard;Peters, Jan
通讯作者：
Peters, Jan