Possibilities of AI Algorithm Execution in GNSS

A large number of studies were obtained to validate the opportunity of using Artificial Intelligence (AI) algorithms in the field of the Global Navigation Satellite System (GNSS). There are two ways to achieve intelligence: one is through Machine Learning (ML) and another is through Deep Learning (DL). Most commonly, Support Vector Machine (SVM) and Convolutional Neural Network (CNN) are the important algorithms of AI which is used in the literature to enhance the position accuracy of GNSS system. Here, the literature review has been done by considering the different stages of GNSS receivers at the Radio Frequency (RF) Front End level, at the pre-correlation level, at the post-correlation level, and at the Navigation level which will provide a better understanding of the implementation of AI in this domain. The major research work is done at the post-correlation stage where different data formats like correlation outputs, National Marine Electronics Association (NMEA) data, and Receiver Independent Exchange Format (RINEX) data have been utilized. Along with that, threats and risk factors associated with the application of AI algorithms have been discussed in this paper.