Beyond Constant Parameters: Hyper Prediction Models and HyperMPC
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912527482355712 |
|---|---|
| author | Węgrzynowski, Jan Kicki, Piotr Czechmanowski, Grzegorz Krupka, Maciej Walas, Krzysztof |
| author_facet | Węgrzynowski, Jan Kicki, Piotr Czechmanowski, Grzegorz Krupka, Maciej Walas, Krzysztof |
| contents | Model Predictive Control (MPC) is among the most widely adopted and reliable methods for robot control, relying critically on an accurate dynamics model. However, existing dynamics models used in the gradient-based MPC are limited by computational complexity and state representation. To address this limitation, we propose the Hyper Prediction Model (HyperPM) - a novel approach in which we project the unmodeled dynamics onto a time-dependent dynamics model. This time-dependency is captured through time-varying model parameters, whose evolution over the MPC prediction horizon is learned using a neural network. Such formulation preserves the computational efficiency and robustness of the base model while equipping it with the capacity to anticipate previously unmodeled phenomena. We evaluated the proposed approach on several challenging systems, including real-world F1TENTH autonomous racing, and demonstrated that it significantly reduces long-horizon prediction errors. Moreover, when integrated within the MPC framework (HyperMPC), our method consistently outperforms existing state-of-the-art techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Constant Parameters: Hyper Prediction Models and HyperMPC Węgrzynowski, Jan Kicki, Piotr Czechmanowski, Grzegorz Krupka, Maciej Walas, Krzysztof Robotics Model Predictive Control (MPC) is among the most widely adopted and reliable methods for robot control, relying critically on an accurate dynamics model. However, existing dynamics models used in the gradient-based MPC are limited by computational complexity and state representation. To address this limitation, we propose the Hyper Prediction Model (HyperPM) - a novel approach in which we project the unmodeled dynamics onto a time-dependent dynamics model. This time-dependency is captured through time-varying model parameters, whose evolution over the MPC prediction horizon is learned using a neural network. Such formulation preserves the computational efficiency and robustness of the base model while equipping it with the capacity to anticipate previously unmodeled phenomena. We evaluated the proposed approach on several challenging systems, including real-world F1TENTH autonomous racing, and demonstrated that it significantly reduces long-horizon prediction errors. Moreover, when integrated within the MPC framework (HyperMPC), our method consistently outperforms existing state-of-the-art techniques. |
| title | Beyond Constant Parameters: Hyper Prediction Models and HyperMPC |
| topic | Robotics |
| url | https://arxiv.org/abs/2508.06181 |