Optimized Position Estimation in Mobile Multipath Environments Using Machine Learning

Abstract The positioning accuracy of global navigation satellite system receivers is frequently degraded in urban areas due to reflected signals. A moving receiver faces additional challenges because it needs adjust changes the statuses signals received, including line-of-sight (LOS), multipath, non-LOS, or invisible. This paper proposes two new algorithms that can be used enhance a receiver. first algorithm called Optimized Position Estimation (OPE). OPE estimates most likely paths and identifies one with optimal weight. second Intelligent Signal Status (ISE). ISE utilizes self-organizing map machine-learning estimate probability change signal status. are tested using C/A signals, which have over 50 their statuses. results obtained these reveal enhanced by as much 96.3% (i.e., 27-fold improvement) when compared conventional algorithm.