Imitation Learning Framework using Principal Component Analysis for Humanoid Robot Motion Generation

• Material Type: 博士論文
• Title: Imitation Learning Framework using Principal Component Analysis for Humanoid Robot Motion Generation
• Author/Editor: 朴, 江
• Author Heading: 朴, 江
• Publication, Distribution, etc.: Hokkaido University
• Publication Date: 2015-03-25
• Publication Date (W3CDTF): 2015-03-25
• Alternative Title: ヒューマノイドロボット動作生成のための主成分分析を用いた模倣学習フレームワーク
• Contributor: 近野, 敦; 小笠原, 悟司; 五十嵐, 一
• Degree grantor/type: 北海道大学
• Date Granted: 2015-03-25
• Date Granted (W3CDTF): 2015-03-25
• Dissertation Number: 甲第11770号
• Degree Type: 博士(工学)
• Conferring No. (Dissertation): 甲第11770号
• Text Language Code: eng
• Alias of Author: Park, Garam
• Subject Heading: Machine Learning; Imitation Learning; Principal Component Analysis; Evolutionary Process
• NDC: 500
• Target Audience: 一般
• Note (General): This dissertation investigates the efficient imitation learning framework based on principal component analysis to generate desired and abundant motions using few human demonstrations in the workspace. This framework is inspired from human motor learning in upper body. In real life, a robot is expected to autonomously act with varied and abundant motions. Imitation learning might be an efficient approach to enable a robot to generate natural and abundant motions.The framework comprises off-line and on-line processes. In the off-line process, human demonstrations are used to develop a motion database. The database covers the workspace and includes robot properties. The evolved database has a clustered structure for efficiency. In the on-line process, a robot can generate desired motions using a real-time motion reconstruction method based on PCA in real time. However, during the motion reconstruction by few, slight movement, or noisy, it occurs the over-response problem. To prevent that, we uses Regularization method, and curve fitting method to reduce the tolerance. The performance of this method is verified through two case studies. The proposed framework is applied to the generation of reaching motions to an object on a table and a shelf.; (主査) 教授 近野 敦, 教授 小笠原 悟司, 教授 五十嵐 一; 情報科学研究科（システム情報科学専攻）
• DOI: 10.14943/doctoral.k11770; https://doi.org/10.14943/doctoral.k11770
• Persistent ID (NDL): info:ndljp/pid/9374959; https://dl.ndl.go.jp/pid/9374959
• Collection: 障害者向け資料
• Collection (Materials For Handicapped People:1): テキストデータ
• Collection (particular): 国立国会図書館デジタルコレクション > デジタル化資料 > 博士論文; https://dl.ndl.go.jp/collections/A00014
• Acquisition Basis: 博士論文（自動収集）
• Date Accepted (W3CDTF): 2015-06-02T13:06:44+09:00
• Date Created (W3CDTF): 2015-02
• Format (IMT): PDF
• Access Restrictions: 国立国会図書館内限定公開
• Service for the Digitized Contents Transmission Service: 図書館・個人送信対象外
• Availability of remote photoduplication service: 可
• Periodical Title (URI): http://dx.doi.org/10.14943/doctoral.k11770; http://hdl.handle.net/2115/58948
• Is Referenced By (URI): http://hdl.handle.net/2115/58947
• Data Provider (Database): 国立国会図書館 : 国立国会図書館デジタルコレクション; https://dl.ndl.go.jp

• Summary, etc.: This dissertation investigates the efficient imitation learning framework based on principal component analysis to generate desired and abundant motio...