GPS-Denied Navigation Using SAR Images and Neural Networks

TL;DR

This paper introduces a neural network-based method for UAV navigation in GPS-denied environments by comparing real-time SAR images with reference images to estimate initial navigation errors.

Contribution

It presents a novel approach combining SAR imaging and neural networks to recover initial navigation errors without GPS, applicable to both simulated and real data.

Findings

Neural network accurately predicts initial errors in simulated SAR data.

Method successfully applied to real SAR images for error estimation.

Approach enhances UAV navigation robustness in GPS-denied scenarios.

Abstract

Unmanned aerial vehicles (UAV) often rely on GPS for navigation. GPS signals, however, are very low in power and easily jammed or otherwise disrupted. This paper presents a method for determining the navigation errors present at the beginning of a GPS-denied period utilizing data from a synthetic aperture radar (SAR) system. This is accomplished by comparing an online-generated SAR image with a reference image obtained a priori. The distortions relative to the reference image are learned and exploited with a convolutional neural network to recover the initial navigational errors, which can be used to recover the true flight trajectory throughout the synthetic aperture. The proposed neural network approach is able to learn to predict the initial errors on both simulated and real SAR image data.