Gps-Denied Navigation Using Sar Images And Neural Networks

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.

Sensitivity of back‐projection algorithm (BPA) synthetic aperture radar (SAR) image formation to initial position, velocity, and attitude navigation errors

“…The ambiguity is such that reversing calculations to infer initial navigation errors from image errors is difficult and presents a separate area of ongoing research. White et al [6] explore this reverse problem and work towards SAR-aided GPS-denied navigation by inferring initial navigation errors from SAR image errors using machine learning techniques.…”

“…White et al. [6] explore this reverse problem and work towards SAR‐aided GPS‐denied navigation by inferring initial navigation errors from SAR image errors using machine learning techniques.…”