Summary of Physics-informed Calibration Of Aeromagnetic Compensation in Magnetic Navigation Systems Using Liquid Time-constant Networks, by Favour Nerrise (1 and 2) et al.
Physics-Informed Calibration of Aeromagnetic Compensation in Magnetic Navigation Systems using Liquid Time-Constant Networks
by Favour Nerrise, Andrew Sosa Sosanya, Patrick Neary
First submitted to arxiv on: 17 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Systems and Control (eess.SY); Computational Physics (physics.comp-ph); Geophysics (physics.geo-ph)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning-based solution is proposed to improve airborne magnetic navigation systems by compensating for external magnetic field interference. The traditional Global Positioning System (GPS) faces limitations in certain environments and against attacks, making Magnetic Navigation (MagNav) a promising alternative. The approach uses Tolles-Lawson coefficients for compensation and Liquid Time-Constant Networks (LTCs) to remove noisy signals derived from the aircraft’s magnetic sources. Real flight data is used to train the model, resulting in up to 64% reduction in aeromagnetic compensation error (RMSE nT), outperforming conventional models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Airborne Magnetic Navigation (MagNav) could replace GPS, but it has problems too. It uses the Earth’s magnetic field to find its position, but this signal gets messed up by other aircraft electronics and big magnetic fields in the Earth. Scientists are trying to fix this problem using special computer models. They took real flight data and used a new method that combines physics and machine learning to make the signal cleaner and more accurate. This could be very useful for finding your position when GPS isn’t working. |
Keywords
* Artificial intelligence * Machine learning
