Real-time Unsupervised Segmentation of human whole-body motion and its application to humanoid robot acquisition of motion symbols
Real-time Unsupervised Segmentation of human whole-body motion and its application to humanoid robot acquisition of motion symbols
复制标题
DOI：
10.1016/j.robot.2015.09.021
复制
发表时间：
2016-01-01
影响因子：
4.3
通讯作者：
Nakamura, Yoshihiko
中科院分区：
文献类型：
--
作者：
Takano, Wataru;Nakamura, Yoshihiko
运动识别和运动生成之间的交互循环是人类和仿人机器人的基本机制。我们一直在开发一个智能框架的运动识别和生成的基础上象征运动原语。运动基元被编码到隐马尔可夫模型（HMRM）中，我们称之为“运动符号”。然而，要确定运动原语用作训练数据的障碍，这个框架需要一个手动分割的人类运动。从本质上讲，人形机器人被期望参与日常生活，必须学习许多运动符号以适应各种情况。对于这种用途，手动分割对于人形机器人来说是繁琐且不切实际的。在本研究中，我们提出了一种新的分割方法，即实时无监督分割（罗斯）方法，该方法包括三个阶段。在第一阶段中，短的人体运动被编码到特征中。无缝的人体运动可以被转换为这些特征的序列HALTH。在第二阶段，提取特征之间的因果关系。因果关系数据使得有可能从观察中预测运动。在第三阶段中，具有大的预测不确定性的运动被指定为运动基元的边界。通过这种方式，可以将人体全身运动分割成一系列运动基元。本文还描述了罗斯在运动基元的AUDUSSymbolization（AUS）中的应用。每个派生的运动基元被分类到一个运动符号的隐马尔可夫模型，并通过使用运动基元作为竞争学习中的训练数据来优化隐马尔可夫模型的参数。以这样一种方式逐步优化Hessions，使得Hessions可以抽象相似的运动基元。我们测试了罗斯和AUS框架上捕获的人体全身运动，并证明了所提出的框架的有效性。(C)2015作者由爱思唯尔公司出版。这是一篇开放获取的文章，使用CC BY许可证（http：//creativecommons.org/licenses/by/4.0/）。
An interactive loop between motion recognition and motion generation is a fundamental mechanism for humans and humanoid robots. We have been developing an intelligent framework for motion recognition and generation based on symbolizing motion primitives. The motion primitives are encoded into Hidden Markov Models (HMMs), which we call "motion symbols". However, to determine the motion primitives to use as training data for the HMMs, this framework requires a manual segmentation of human motions. Essentially, a humanoid robot is expected to participate in daily life and must learn many motion symbols to adapt to various situations. For this use, manual segmentation is cumbersome and impractical for humanoid robots. In this study, we propose a novel approach to segmentation, the Real-time Unsupervised Segmentation (RUS) method, which comprises three phases. In the first phase, short human movements are encoded into feature HMMs. Seamless human motion can be converted to a sequence of these feature HMMs. In the second phase, the causality between the feature HMMs is extracted. The causality data make it possible to predict movement from observation. In the third phase, movements having a large prediction uncertainty are designated as the boundaries of motion primitives. In this way, human whole-body motion can be segmented into a sequence of motion primitives. This paper also describes an application of RUS to AUtonomous Symbolization of motion primitives (AUS). Each derived motion primitive is classified into an HMM for a motion symbol, and parameters of the HMMs are optimized by using the motion primitives as training data in competitive learning. The HMMs are gradually optimized in such a way that the HMMs can abstract similar motion primitives. We tested the RUS and AUS frameworks on captured human whole-body motions and demonstrated the validity of the proposed framework. (C) 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).