Latent-Space Non-Linear Model Predictive Control for Partially-Observable Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908671593676800 |
|---|---|
| author | Marra, Luigi Semeraro, Onofrio Mathelin, Lionel Meilán-Vila, Andrea Discetti, Stefano |
| author_facet | Marra, Luigi Semeraro, Onofrio Mathelin, Lionel Meilán-Vila, Andrea Discetti, Stefano |
| contents | This work presents a scalable control framework based on nonlinear Model Predictive Control for high-dimensional dynamical systems. The proposed approach addresses the key challenges of model scalability and partial observability by integrating data-driven reduced order modelling, control in a latent space, and state estimation within a unified formulation. A predictive model is constructed via Operator Inference on a Proper Orthogonal Decomposition basis, yielding a compact latent representation that captures the dominant system dynamics. State estimation is achieved through an Unscented Kalman Filter, which reconstructs the latent space from sparse and noisy measurements, enabling closed-loop control. The input signals are computed directly in the reduced-order latent space, improving computational efficiency with negligible impact on predictive capability. The methodology is validated on the one- and two-dimensional Kuramoto--Sivashinsky equations, serving as benchmarks for chaotic and spatially-extended systems. Numerical experiments demonstrate that the proposed framework achieves accurate stabilisation. Overall, the framework provides a practical approach for nonlinear control of complex, high-dimensional systems where full-state measurements are often inaccessible or infeasible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19056 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent-Space Non-Linear Model Predictive Control for Partially-Observable Systems Marra, Luigi Semeraro, Onofrio Mathelin, Lionel Meilán-Vila, Andrea Discetti, Stefano Fluid Dynamics This work presents a scalable control framework based on nonlinear Model Predictive Control for high-dimensional dynamical systems. The proposed approach addresses the key challenges of model scalability and partial observability by integrating data-driven reduced order modelling, control in a latent space, and state estimation within a unified formulation. A predictive model is constructed via Operator Inference on a Proper Orthogonal Decomposition basis, yielding a compact latent representation that captures the dominant system dynamics. State estimation is achieved through an Unscented Kalman Filter, which reconstructs the latent space from sparse and noisy measurements, enabling closed-loop control. The input signals are computed directly in the reduced-order latent space, improving computational efficiency with negligible impact on predictive capability. The methodology is validated on the one- and two-dimensional Kuramoto--Sivashinsky equations, serving as benchmarks for chaotic and spatially-extended systems. Numerical experiments demonstrate that the proposed framework achieves accurate stabilisation. Overall, the framework provides a practical approach for nonlinear control of complex, high-dimensional systems where full-state measurements are often inaccessible or infeasible. |
| title | Latent-Space Non-Linear Model Predictive Control for Partially-Observable Systems |
| topic | Fluid Dynamics |
| url | https://arxiv.org/abs/2511.19056 |