Physics-Informed Calibration of Aeromagnetic Compensation in Magnetic Navigation Systems using Liquid Time-Constant Networks

TL;DR

The paper tackles calibrating aeromagnetic compensation in MagNav by fusing physics-inspired Tolles-Lawson coefficients with Liquid Time-Constant networks to extract weak Earth magnetic anomalies amid strong aircraft-induced interference. It introduces a two-step framework where LTC/CfC models capture nonlinear dynamics and learn coefficients to update Tolles-Lawson terms, enabling improved real-time calibration. On real flight data, the approach achieves up to $64\%$ RMSE reduction relative to Tolles-Lawson calibration and outperforms traditional baselines, validating the effectiveness of physics-informed learning for MagNav signal extraction. This work promises more robust, navigation-grade magnetic localization by enhancing the separation of weak anomaly signals from noise in airborne magnetometer measurements.

Abstract

Magnetic navigation (MagNav) is a rising alternative to the Global Positioning System (GPS) and has proven useful for aircraft navigation. Traditional aircraft navigation systems, while effective, face limitations in precision and reliability in certain environments and against attacks. Airborne MagNav leverages the Earth's magnetic field to provide accurate positional information. However, external magnetic fields induced by aircraft electronics and Earth's large-scale magnetic fields disrupt the weaker signal of interest. We introduce a physics-informed approach using Tolles-Lawson coefficients for compensation and Liquid Time-Constant Networks (LTCs) to remove complex, noisy signals derived from the aircraft's magnetic sources. Using real flight data with magnetometer measurements and aircraft measurements, we observe up to a 64% reduction in aeromagnetic compensation error (RMSE nT), outperforming conventional models. This significant improvement underscores the potential of a physics-informed, machine learning approach for extracting clean, reliable, and accurate magnetic signals for MagNav positional estimation.

Figures (4)

• Figure 1: The architecture for the Liquid Time-Constant Network comprises the input, perception layer, a liquid layer (i.e., a time-continuous gating mechanism), and an output layer. Here, $I(t)$ is the real input signal, and $y(t)$ is the predicted, filtered signal.
• Figure 2: a) Flight trajectory on the magnetic anomaly of Renfrew, Canada, and Ontario, Canada, at 300m above the WGS84 ellipsoid (flight 1007). b) Locations of magnetometers positioned around the MagNav Challenge aircraft.
• Figure 3: Model comparison of aerocompensation calibration error (RMSE nT) for flights 1003 and 1007.
• Figure 4: Truth signal (IGRF-corrected Mag 1) vs. predicted signal [nT] for a portion of flight 1007.