Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911544520998912 |
|---|---|
| author | Clement, Mihaela-Larisa Farsang, Mónika Poks, Agnes Edelmann, Johannes Plöchl, Manfred Grosu, Radu Bartocci, Ezio |
| author_facet | Clement, Mihaela-Larisa Farsang, Mónika Poks, Agnes Edelmann, Johannes Plöchl, Manfred Grosu, Radu Bartocci, Ezio |
| contents | The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap the policy in a safety-augmented online evaluation and fallback mechanism, yielding Safe Sequential-AMPC. Compared to a naive feedforward policy baseline across several benchmarks, Sequential-AMPC requires substantially fewer expert MPC rollouts and yields candidate sequences with higher feasibility rates and improved closed-loop safety. On high-dimensional systems, it also exhibits better learning dynamics and performance in fewer epochs while maintaining stable validation improvement where the feedforward baseline can stagnate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling Clement, Mihaela-Larisa Farsang, Mónika Poks, Agnes Edelmann, Johannes Plöchl, Manfred Grosu, Radu Bartocci, Ezio Machine Learning Robotics Systems and Control The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap the policy in a safety-augmented online evaluation and fallback mechanism, yielding Safe Sequential-AMPC. Compared to a naive feedforward policy baseline across several benchmarks, Sequential-AMPC requires substantially fewer expert MPC rollouts and yields candidate sequences with higher feasibility rates and improved closed-loop safety. On high-dimensional systems, it also exhibits better learning dynamics and performance in fewer epochs while maintaining stable validation improvement where the feedforward baseline can stagnate. |
| title | Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling |
| topic | Machine Learning Robotics Systems and Control |
| url | https://arxiv.org/abs/2603.24503 |