GPS-Denied Navigation Using SAR Images and Neural Networks
This addresses navigation reliability for UAVs in GPS-disrupted environments, representing an incremental improvement over existing methods.
The paper tackles GPS-denied navigation for UAVs by using SAR images and a convolutional neural network to estimate initial navigation errors, enabling recovery of the true flight trajectory, with validation on simulated and real data.
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.