Safe Data-Driven Predictive Control
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916685525549056 |
|---|---|
| author | Vahidi-Moghaddam, Amin Chen, Kaian Zhang, Kaixiang Li, Zhaojian Wang, Yan Wu, Kai |
| author_facet | Vahidi-Moghaddam, Amin Chen, Kaian Zhang, Kaixiang Li, Zhaojian Wang, Yan Wu, Kai |
| contents | In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential; however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within real-time nonlinear systems. This study presents an innovative control framework to enhance the practical viability of the MPC. The developed safe data-driven predictive control aims to eliminate the requirement for precise models and alleviate computational burdens in the nonlinear MPC (NMPC). This is achieved by learning both the system dynamics and the control policy, enabling efficient data-driven predictive control while ensuring system safety. The methodology involves a spatial temporal filter (STF)-based concurrent learning for system identification, a robust control barrier function (RCBF) to ensure the system safety amid model uncertainties, and a RCBF-based NMPC policy approximation. An online policy correction mechanism is also introduced to counteract performance degradation caused by the existing model uncertainties. Demonstrated through simulations on two applications, the proposed approach offers comparable performance to existing benchmarks with significantly reduced computational costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Safe Data-Driven Predictive Control Vahidi-Moghaddam, Amin Chen, Kaian Zhang, Kaixiang Li, Zhaojian Wang, Yan Wu, Kai Systems and Control In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential; however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within real-time nonlinear systems. This study presents an innovative control framework to enhance the practical viability of the MPC. The developed safe data-driven predictive control aims to eliminate the requirement for precise models and alleviate computational burdens in the nonlinear MPC (NMPC). This is achieved by learning both the system dynamics and the control policy, enabling efficient data-driven predictive control while ensuring system safety. The methodology involves a spatial temporal filter (STF)-based concurrent learning for system identification, a robust control barrier function (RCBF) to ensure the system safety amid model uncertainties, and a RCBF-based NMPC policy approximation. An online policy correction mechanism is also introduced to counteract performance degradation caused by the existing model uncertainties. Demonstrated through simulations on two applications, the proposed approach offers comparable performance to existing benchmarks with significantly reduced computational costs. |
| title | Safe Data-Driven Predictive Control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2504.08188 |