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


    Access

    Download


    Export, share and cite



    Title :

    Optimized Position Estimation in Mobile Multipath Environments Using Machine Learning


    Contributors:


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Spatio-temporal equalization for multipath environments in mobile radio applications

    Lindskog,E. / Ahlen,A. / Sternad,M. et al. | Automotive engineering | 1995


    Evaluation of GNSS Direct Position Estimation in Realistic Multipath Channels

    Closas, P. / Fernández-Prades, C. / Fernández, A. et al. | British Library Conference Proceedings | 2015




    Multipath Characterization of Micro and Macrocellular Environments for Mobile Radio Systems

    Aguilar, Jesús G. / Fregoso, Cesar J. / Garcia, José D. Cortez et al. | IEEE | 2009