NavFormer: IGRF Forecasting in Moving Coordinate Frames

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hwang, Yoontae, Lee, Dongwoo, Choi, Minseok, Park, Heechan, Ihn, Yong Sup, Kim, Daham, Lee, Deok-Young
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910002928680960
author Hwang, Yoontae
Lee, Dongwoo
Choi, Minseok
Park, Heechan
Ihn, Yong Sup
Kim, Daham
Lee, Deok-Young
author_facet Hwang, Yoontae
Lee, Dongwoo
Choi, Minseok
Park, Heechan
Ihn, Yong Sup
Kim, Daham
Lee, Deok-Young
contents Triad magnetometer components change with sensor attitude even when the IGRF total intensity target stays invariant. NavFormer forecasts this invariant target with rotation invariant scalar features and a Canonical SPD module that stabilizes the spectrum of window level second moments of the triads without sign discontinuities. The module builds a canonical frame from a Gram matrix per window and applies state dependent spectral scaling in the original coordinates. Experiments across five flights show lower error than strong baselines in standard training, few shot training, and zero shot transfer. The code is available at: https://anonymous.4open.science/r/NavFormer-Robust-IGRF-Forecasting-for-Autonomous-Navigators-0765
format Preprint
id arxiv_https___arxiv_org_abs_2601_18800
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NavFormer: IGRF Forecasting in Moving Coordinate Frames
Hwang, Yoontae
Lee, Dongwoo
Choi, Minseok
Park, Heechan
Ihn, Yong Sup
Kim, Daham
Lee, Deok-Young
Machine Learning
Computer Vision and Pattern Recognition
Triad magnetometer components change with sensor attitude even when the IGRF total intensity target stays invariant. NavFormer forecasts this invariant target with rotation invariant scalar features and a Canonical SPD module that stabilizes the spectrum of window level second moments of the triads without sign discontinuities. The module builds a canonical frame from a Gram matrix per window and applies state dependent spectral scaling in the original coordinates. Experiments across five flights show lower error than strong baselines in standard training, few shot training, and zero shot transfer. The code is available at: https://anonymous.4open.science/r/NavFormer-Robust-IGRF-Forecasting-for-Autonomous-Navigators-0765
title NavFormer: IGRF Forecasting in Moving Coordinate Frames
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18800