Gaussian Processes for Advanced Motion Control

カテゴリ: 論文誌(論文単位)

グループ名: 【D】産業応用部門（英文）

発行日: 2022/05/01

タイトル(英語): Gaussian Processes for Advanced Motion Control

著者名: Maurice Poot (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology), Jim Portegies (CASA, Department of Mathematics and Computer Science, Eindhoven University of Technology), Noud Mooren (Control Sys

著者名(英語): Maurice Poot (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology), Jim Portegies (CASA, Department of Mathematics and Computer Science, Eindhoven University of Technology), Noud Mooren (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology), Max van Haren (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology), Max van Meer (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology), Tom Oomen (Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology/Delft Center for Systems and Control, Delft University of Technology)

キーワード: gaussian processes，feedforward control，learning control

要約(英語): Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.

本誌: IEEJ Journal of Industry Applications Vol.11 No.3 （2022）

本誌掲載ページ: 396-407 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejjia/11/3/11_21011492/_article/-char/ja/