Real-Time Online Learning for Model Predictive Control using a Spatio-Temporal Gaussian Process Approximation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908897433878528 |
|---|---|
| author | Bartels, Lars Lahr, Amon Carron, Andrea Zeilinger, Melanie N. |
| author_facet | Bartels, Lars Lahr, Amon Carron, Andrea Zeilinger, Melanie N. |
| contents | Learning-based model predictive control (MPC) can enhance control performance by correcting for model inaccuracies, enabling more precise state trajectory predictions than traditional MPC. A common approach is to model unknown residual dynamics as a Gaussian process (GP), which leverages data and also provides an estimate of the associated uncertainty. However, the high computational cost of online learning poses a major challenge for real-time GP-MPC applications. This work presents an efficient implementation of an approximate spatio-temporal GP model, offering online learning at constant computational complexity. It is optimized for GP-MPC, where it enables improved control performance by learning more accurate system dynamics online in real-time, even for time-varying systems. The performance of the proposed method is demonstrated by simulations and hardware experiments in the exemplary application of autonomous miniature racing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17632 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Real-Time Online Learning for Model Predictive Control using a Spatio-Temporal Gaussian Process Approximation Bartels, Lars Lahr, Amon Carron, Andrea Zeilinger, Melanie N. Systems and Control Robotics Optimization and Control I.2.9 Learning-based model predictive control (MPC) can enhance control performance by correcting for model inaccuracies, enabling more precise state trajectory predictions than traditional MPC. A common approach is to model unknown residual dynamics as a Gaussian process (GP), which leverages data and also provides an estimate of the associated uncertainty. However, the high computational cost of online learning poses a major challenge for real-time GP-MPC applications. This work presents an efficient implementation of an approximate spatio-temporal GP model, offering online learning at constant computational complexity. It is optimized for GP-MPC, where it enables improved control performance by learning more accurate system dynamics online in real-time, even for time-varying systems. The performance of the proposed method is demonstrated by simulations and hardware experiments in the exemplary application of autonomous miniature racing. |
| title | Real-Time Online Learning for Model Predictive Control using a Spatio-Temporal Gaussian Process Approximation |
| topic | Systems and Control Robotics Optimization and Control I.2.9 |
| url | https://arxiv.org/abs/2603.17632 |