Nagano Masatoshi, Nakamura Tomoaki, Nagai Takayuki, Mochihashi Daichi, Kobayashi Ichiro, Takano Wataru
Department of Mechanical Engineering and Intelligent Systems, The University of Electro-Communications, Tokyo, Japan.
Graduate School of Engineering Science, Osaka University, Osaka, Japan.
Front Robot AI. 2019 Nov 20;6:115. doi: 10.3389/frobt.2019.00115. eCollection 2019.
Humans perceive continuous high-dimensional information by dividing it into meaningful segments, such as words and units of motion. We believe that such unsupervised segmentation is also important for robots to learn topics such as language and motion. To this end, we previously proposed a hierarchical Dirichlet process-Gaussian process-hidden semi-Markov model (HDP-GP-HSMM). However, an important drawback of this model is that it cannot divide high-dimensional time-series data. Furthermore, low-dimensional features must be extracted in advance. Segmentation largely depends on the design of features, and it is difficult to design effective features, especially in the case of high-dimensional data. To overcome this problem, this study proposes a hierarchical Dirichlet process-variational autoencoder-Gaussian process-hidden semi-Markov model (HVGH). The parameters of the proposed HVGH are estimated through a mutual learning loop of the variational autoencoder and our previously proposed HDP-GP-HSMM. Hence, HVGH can extract features from high-dimensional time-series data while simultaneously dividing it into segments in an unsupervised manner. In an experiment, we used various motion-capture data to demonstrate that our proposed model estimates the correct number of classes and more accurate segments than baseline methods. Moreover, we show that the proposed method can learn latent space suitable for segmentation.
人类通过将连续的高维信息划分为有意义的片段（如单词和运动单元）来感知它。我们认为，这种无监督分割对于机器人学习语言和运动等主题也很重要。为此，我们之前提出了一种分层狄利克雷过程 - 高斯过程 - 隐藏半马尔可夫模型（HDP - GP - HSMM）。然而，该模型的一个重要缺点是它不能分割高维时间序列数据。此外，必须预先提取低维特征。分割在很大程度上取决于特征的设计，并且很难设计有效的特征，尤其是在高维数据的情况下。为了克服这个问题，本研究提出了一种分层狄利克雷过程 - 变分自编码器 - 高斯过程 - 隐藏半马尔可夫模型（HVGH）。所提出的HVGH的参数通过变分自编码器和我们之前提出的HDP - GP - HSMM的相互学习循环来估计。因此，HVGH可以从高维时间序列数据中提取特征，同时以无监督的方式将其分割成片段。在一项实验中，我们使用了各种运动捕捉数据来证明我们提出的模型比基线方法估计出正确的类别数量和更准确的片段。此外，我们表明所提出的方法可以学习适合分割的潜在空间。
