NavFormer: IGRF Forecasting in Moving Coordinate Frames

2026-01-14

AI Summary

This work addresses the challenge that triaxial magnetometer readings are sensitive to sensor orientation, whereas the total intensity of the International Geomagnetic Reference Field (IGRF) is a rotation-invariant scalar, complicating robust modeling. To resolve this, the authors propose the Canonical SPD module, which constructs a canonical coordinate frame via the Gram matrix and introduces state-dependent spectral scaling in the original coordinates to stabilize the spectral structure of moving-window second-order moments. This approach enables robust prediction of IGRF total intensity by integrating rotation-invariant scalar features, spectral decomposition, and deep learning architecture, effectively avoiding sign discontinuities. Evaluated across five flight experiments, the model consistently outperforms strong baselines under standard training, few-shot learning, and zero-shot transfer settings.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Matrix & Tensor Methods
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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

Problem

• IGRF forecasting
• moving coordinate frames
• triad magnetometer
• rotation invariance
• attitude variation

Innovation

• rotation-invariant features
• Canonical SPD module
• IGRF forecasting
• moving coordinate frames
• spectral scaling