Learning exactly linearizable deep dynamics models
Research on control using models based on machine-learning methods has now shifted to the practical engineering stage. Achieving high performance and theoretically guaranteeing the safety of the system is critical for such applications. In this paper, we propose a learning method for exactly lineari...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | SICE Journal of Control, Measurement, and System Integration |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/18824889.2025.2459429 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823858041352617984 |
|---|---|
| author | Ryuta Moriyasu Masayuki Kusunoki Kenji Kashima |
| author_facet | Ryuta Moriyasu Masayuki Kusunoki Kenji Kashima |
| author_sort | Ryuta Moriyasu |
| collection | DOAJ |
| description | Research on control using models based on machine-learning methods has now shifted to the practical engineering stage. Achieving high performance and theoretically guaranteeing the safety of the system is critical for such applications. In this paper, we propose a learning method for exactly linearizable dynamical models that can easily apply various control theories to ensure stability, reliability, etc., and to provide a high degree of freedom of expression. As an example, we present a design that combines simple linear control and control barrier functions. The proposed model is employed for the real-time control of an automotive engine, and the results demonstrate good predictive performance and stable control under constraints. |
| format | Article |
| id | doaj-art-4ff336ddd0ca4bd9bf695bc0cec88163 |
| institution | Kabale University |
| issn | 1884-9970 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | SICE Journal of Control, Measurement, and System Integration |
| spelling | doaj-art-4ff336ddd0ca4bd9bf695bc0cec881632025-02-11T15:10:11ZengTaylor & Francis GroupSICE Journal of Control, Measurement, and System Integration1884-99702025-12-0118110.1080/18824889.2025.24594292459429Learning exactly linearizable deep dynamics modelsRyuta Moriyasu0Masayuki Kusunoki1Kenji Kashima2Toyota Central R&D Labs., Inc.Toyota Industries CorporationKyoto UniversityResearch on control using models based on machine-learning methods has now shifted to the practical engineering stage. Achieving high performance and theoretically guaranteeing the safety of the system is critical for such applications. In this paper, we propose a learning method for exactly linearizable dynamical models that can easily apply various control theories to ensure stability, reliability, etc., and to provide a high degree of freedom of expression. As an example, we present a design that combines simple linear control and control barrier functions. The proposed model is employed for the real-time control of an automotive engine, and the results demonstrate good predictive performance and stable control under constraints.http://dx.doi.org/10.1080/18824889.2025.2459429model predictive controlmachine learningcontrol applicationnonlinear controlhammerstein–wiener model |
| spellingShingle | Ryuta Moriyasu Masayuki Kusunoki Kenji Kashima Learning exactly linearizable deep dynamics models SICE Journal of Control, Measurement, and System Integration model predictive control machine learning control application nonlinear control hammerstein–wiener model |
| title | Learning exactly linearizable deep dynamics models |
| title_full | Learning exactly linearizable deep dynamics models |
| title_fullStr | Learning exactly linearizable deep dynamics models |
| title_full_unstemmed | Learning exactly linearizable deep dynamics models |
| title_short | Learning exactly linearizable deep dynamics models |
| title_sort | learning exactly linearizable deep dynamics models |
| topic | model predictive control machine learning control application nonlinear control hammerstein–wiener model |
| url | http://dx.doi.org/10.1080/18824889.2025.2459429 |
| work_keys_str_mv | AT ryutamoriyasu learningexactlylinearizabledeepdynamicsmodels AT masayukikusunoki learningexactlylinearizabledeepdynamicsmodels AT kenjikashima learningexactlylinearizabledeepdynamicsmodels |