Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916933773819904 |
|---|---|
| author | Holtmann, Tobin Stenger, David Posada-Moreno, Andres Solowjow, Friedrich Trimpe, Sebastian |
| author_facet | Holtmann, Tobin Stenger, David Posada-Moreno, Andres Solowjow, Friedrich Trimpe, Sebastian |
| contents | State estimation in control and systems engineering traditionally requires extensive manual system identification or data-collection effort. However, transformer-based foundation models in other domains have reduced data requirements by leveraging pre-trained generalist models. Ultimately, developing zero-shot foundation models of system dynamics could drastically reduce manual deployment effort. While recent work shows that transformer-based end-to-end approaches can achieve zero-shot performance on unseen systems, they are limited to sensor models seen during training. We introduce the foundation model unscented Kalman filter (FM-UKF), which combines a transformer-based model of system dynamics with analytically known sensor models via an UKF, enabling generalization across varying dynamics without retraining for new sensor configurations. We evaluate FM-UKF on a new benchmark of container ship models with complex dynamics, demonstrating a competitive accuracy, effort, and robustness trade-off compared to classical methods with approximate system knowledge and to an end-to-end approach. The benchmark and dataset are open sourced to further support future research in zero-shot state estimation via foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF Holtmann, Tobin Stenger, David Posada-Moreno, Andres Solowjow, Friedrich Trimpe, Sebastian Systems and Control Machine Learning State estimation in control and systems engineering traditionally requires extensive manual system identification or data-collection effort. However, transformer-based foundation models in other domains have reduced data requirements by leveraging pre-trained generalist models. Ultimately, developing zero-shot foundation models of system dynamics could drastically reduce manual deployment effort. While recent work shows that transformer-based end-to-end approaches can achieve zero-shot performance on unseen systems, they are limited to sensor models seen during training. We introduce the foundation model unscented Kalman filter (FM-UKF), which combines a transformer-based model of system dynamics with analytically known sensor models via an UKF, enabling generalization across varying dynamics without retraining for new sensor configurations. We evaluate FM-UKF on a new benchmark of container ship models with complex dynamics, demonstrating a competitive accuracy, effort, and robustness trade-off compared to classical methods with approximate system knowledge and to an end-to-end approach. The benchmark and dataset are open sourced to further support future research in zero-shot state estimation via foundation models. |
| title | Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2509.04213 |