Iteratively Saturated Kalman Filtering
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_ | 1866912458898145280 |
|---|---|
| author | Yang, Alan Boyd, Stephen |
| author_facet | Yang, Alan Boyd, Stephen |
| contents | The Kalman filter (KF) provides optimal recursive state estimates for linear-Gaussian systems and underpins applications in control, signal processing, and others. However, it is vulnerable to outliers in the measurements and process noise. We introduce the iteratively saturated Kalman filter (ISKF), which is derived as a scaled gradient method for solving a convex robust estimation problem. It achieves outlier robustness while preserving the KF's low per-step cost and implementation simplicity, since in practice it typically requires only one or two iterations to achieve good performance. The ISKF also admits a steady-state variant that, like the standard steady-state KF, does not require linear system solves in each time step, making it well-suited for real-time systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00272 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Iteratively Saturated Kalman Filtering Yang, Alan Boyd, Stephen Systems and Control The Kalman filter (KF) provides optimal recursive state estimates for linear-Gaussian systems and underpins applications in control, signal processing, and others. However, it is vulnerable to outliers in the measurements and process noise. We introduce the iteratively saturated Kalman filter (ISKF), which is derived as a scaled gradient method for solving a convex robust estimation problem. It achieves outlier robustness while preserving the KF's low per-step cost and implementation simplicity, since in practice it typically requires only one or two iterations to achieve good performance. The ISKF also admits a steady-state variant that, like the standard steady-state KF, does not require linear system solves in each time step, making it well-suited for real-time systems. |
| title | Iteratively Saturated Kalman Filtering |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2507.00272 |