- 著者
- Maarten Steinbuch Tom Oomen Hans Vermeulen
- 出版者
- The Institute of Electrical Engineers of Japan
- 雑誌
- IEEJ Journal of Industry Applications (ISSN:21871094)
- 巻号頁・発行日
- pp.21006010, (Released:2021-08-06)
- 被引用文献数
- 12
Technology in a broad sense is driven by developments in semiconductor technology, particularly with respect to the computational power of devices and systems, as well as sensor technology. The progress of semiconductor technology has demonstrated an exponential curve since the middle of the previous century, representing Moore's Law. Consequently, it is of utmost importance to bridge the gaps between disciplines in the fields of control, automation, and robotics. Moreover, data-driven approaches need to be combined with model-based design. This will lead to new digital twinning and automated design approaches that provide major opportunities. Furthermore, this necessitates the redefinition of our university system.
- 著者
- Maurice Poot Jim Portegies Noud Mooren Max van Haren Max van Meer Tom Oomen
- 出版者
- The Institute of Electrical Engineers of Japan
- 雑誌
- IEEJ Journal of Industry Applications (ISSN:21871094)
- 巻号頁・発行日
- vol.11, no.3, pp.396-407, 2022-05-01 (Released:2022-05-01)
- 参考文献数
- 74
- 被引用文献数
- 8
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.