CNNを用いたGNSS相関波形の機械学習による衛星の可視性判別

DOI Web Site

書誌事項

タイトル別名
  • GNSS Satellite Visibility Determination by Machine Learning of GNSS Correlation Waveform using CNN

抄録

<p>Positioning accuracy of global navigation satellite system (GNSS) is deteriorates when non-line-of-sight (NLOS) multipath signals are received in urban environments. Therefore, it is important to determine satellite visibility and reject NLOS satellites from positioning calculation to improve positioning accuracy. In this paper, we focus on a correlation waveform which is affected by multipath signals. To detect NLOS multipath signals, we use convolutional neural networks (CNN) for machine learning to generate the NLOS discriminator. From the evaluations of proposed method, the global positioning system (GPS) accuracy of satellite visibility determination by using the CNN was 98.0 %. In addition, the GPS accuracy of NLOS satellites determination by using the CNN was 97.9 %. Similarly, GLONASS, Galileo and BeiDou accuracy of it were about 90 %. We confirmed the effectiveness of the proposed method with experiments in urban environments by comparing with conventional method.The positioning accuracy without NLOS signals is also improved compared with the conventional positioning method in urban environments.</p>

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ