Abstract
As the necessity of location information closely related to everyday life has increased, the use of global navigation satellite systems (GNSS) has gradually increased in populated urban areas. Contrary to the high necessity and expectation of GNSS in urban areas, GNSS performance is easily degraded by multipath errors due to high-rise buildings and is very difficult to guarantee. Errors in the signals reflected by the buildings, i.e., multipath and non-line-of-sight (NLOS) errors, are the major cause of the poor accuracy in urban areas. Unlike other GNSS major error sources, the reflected signal error, which is a user-dependent error, is difficult to differentiate or model. This paper suggests training a multipath prediction model based on support vector regression to obtain a function of the elevation and azimuth angle of each satellite. To extract an unbiased multipath from the GNSS measurements, the clock error of high-elevation QZSS was estimated, and the clock offset with other constellations was also calculated. A nonlinear multipath map was generated, as a result of training with the extracted multipaths, by a Support Vector Machine, which appropriately reflected the geometry of the building near the user. The model was effective at improving the urban area positioning accuracy by 58.4% horizontally and 77.7% vertically, allowing us to achieve a 20 m accuracy level in a deep urban area, Teheran-ro, Seoul, Korea.
Highlights
Global navigation satellite systems (GNSS) have been used as the main navigation source in various location-based services (LBS), such as vehicle navigation [1,2] and smart phone location services, for the past 30 years, and are expected to be used for autonomous cars [3,4] and unmanned aerial mobility (UAM) vehicles [5,6]
Contrary to the high demand and expectations for GNSS in urban areas, GNSS performance is degraded by multipath errors due to high-rise buildings, and robust and reliable navigation is a primary challenge for urban navigation [6]
The change in the shape of the correlation values of NLOS signals can be trained by convolutional neural networks, and its reflected signal discrimination probability was 98%, with the positional accuracy improved by 30 m [33]
Summary
Global navigation satellite systems (GNSS) have been used as the main navigation source in various location-based services (LBS), such as vehicle navigation [1,2] and smart phone location services, for the past 30 years, and are expected to be used for autonomous cars [3,4] and unmanned aerial mobility (UAM) vehicles [5,6]. The change in the shape of the correlation values of NLOS signals can be trained by convolutional neural networks, and its reflected signal discrimination probability was 98%, with the positional accuracy improved by 30 m [33] This method does not eliminate the reflected signal errors, but rather unweights them, so it could not be a solution to the extremely large multipath errors of hundreds of meters. We introduce an SVM-based nonlinear NLOS/multipath prediction model using only the relative position information of the user and the satellite. It belongs to the third category of the machine learning-based multipath error research. Reference station-free PRC corrections are effective and convenient considering the wide mobility of vehicles, and corrections from SBAS (prcSBAS) were used in this study
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
