CNPE-KalmanNet: Learning-Aided Kalman Filter With Complex Number Position Encoding
IEEE Signal Processing Letters · 2026 · 33 · 1556-1560
DOI: 10.1109/lsp.2026.3674044 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Yucheng Long und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben.
Abstract (Originalsprache)
KalmanNet demonstrates potential for nonlinear state estimation, but it directly concatenates heterogeneous components with disparate semantics into a composite vector. This approach ignores capturing semantic component correlations, limiting the network’s ability to utilize this information when computing the Kalman gain. To address this, we propose CNPE-KalmanNet, a novel learning-aided Kalman filter that models semantic component correlations by integrating element-wise rotary encoding with multilayer perceptrons in the complex domain. CNPE serves as a plug-and-play module compatible with two baseline KalmanNet architectures. Experiments on the Michigan NCLT dataset demonstrate that CNPE-KalmanNet significantly improves estimation accuracy. Compared to the existing KalmanNet, our method reduces the RMSE by 20%-25% in state estimation tasks and by 15%-20% in sensor fusion tasks.
Zitieren
APA
Long, Y., Mei, W., Song, J., Xu, Y., Fu, Q., & Bu, L. (2026). CNPE-KalmanNet: Learning-Aided Kalman Filter With Complex Number Position Encoding. IEEE Signal Processing Letters, 33, 1556-1560. https://doi.org/10.1109/lsp.2026.3674044
Vancouver
Long Y, Mei W, Song J, Xu Y, Fu Q, Bu L. CNPE-KalmanNet: Learning-Aided Kalman Filter With Complex Number Position Encoding. IEEE Signal Processing Letters. 2026;33:1556-1560. doi:10.1109/lsp.2026.3674044
BibTeX
@article{Long2026,
author = {Long, Yucheng and Mei, Wei and Song, Jian and Xu, Yunfeng and Fu, Qiang and Bu, Lina},
title = {CNPE-KalmanNet: Learning-Aided Kalman Filter With Complex Number Position Encoding},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {1556--1560},
doi = {10.1109/lsp.2026.3674044}
}
EUVIMED