Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Holtmann, Tobin, Stenger, David, Posada-Moreno, Andres, Solowjow, Friedrich, Trimpe, Sebastian
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