Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.10945 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913950547836928 |
|---|---|
| author | Delcaro, Giacomo Poli, Riccardo Dettù, Federico Formentin, Simone Savaresi, Sergio Matteo |
| author_facet | Delcaro, Giacomo Poli, Riccardo Dettù, Federico Formentin, Simone Savaresi, Sergio Matteo |
| contents | Conventional vehicle dynamics estimation methods suffer from the drawback of employing independent, separately calibrated filtering modules for each variable. To address this limitation, a recent proposal introduces a unified Twin-in-the-Loop (TiL) Observer architecture. This architecture replaces the simplified control-oriented vehicle model with a full-fledged vehicle simulator (digital twin), and employs a real-time correction mechanism using a linear time-invariant output error law. Bayesian Optimization is utilized to tune the observer due to the simulator's black-box nature, leading to a high-dimensional optimization problem. This paper focuses on developing a procedure to reduce the observer's complexity by exploring both supervised and unsupervised learning approaches. The effectiveness of these strategies is validated for longitudinal and lateral vehicle dynamics using real-world data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10945 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic dimensionality reduction of Twin-in-the-Loop Observers Delcaro, Giacomo Poli, Riccardo Dettù, Federico Formentin, Simone Savaresi, Sergio Matteo Systems and Control Machine Learning Conventional vehicle dynamics estimation methods suffer from the drawback of employing independent, separately calibrated filtering modules for each variable. To address this limitation, a recent proposal introduces a unified Twin-in-the-Loop (TiL) Observer architecture. This architecture replaces the simplified control-oriented vehicle model with a full-fledged vehicle simulator (digital twin), and employs a real-time correction mechanism using a linear time-invariant output error law. Bayesian Optimization is utilized to tune the observer due to the simulator's black-box nature, leading to a high-dimensional optimization problem. This paper focuses on developing a procedure to reduce the observer's complexity by exploring both supervised and unsupervised learning approaches. The effectiveness of these strategies is validated for longitudinal and lateral vehicle dynamics using real-world data. |
| title | Automatic dimensionality reduction of Twin-in-the-Loop Observers |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2401.10945 |