High-precision positioning with low-cost global navigation satellite systems (GNSS) in urban environments remains a significant challenge due to the significant multipath effects, non-line-of-sight (NLOS) errors, as well as poor satellite visibility and geometry. A GNSS system is typically implemented with a least-square (LS) or a Kalman-filter (KF) estimator, and a proper weight scheme is vital for achieving reliable navigation solutions. The traditional weight schemes are based on the signal-in-space ranging errors (SISRE), elevation and C/N0 values, which would be less effective in urban environments since the observation quality cannot be fully manifested by those values. In this paper, we propose a new multi-feature support vector machine (SVM) signal classifier-based weight scheme for GNSS measurements to improve the kinematic GNSS positioning accuracy in urban environments. The proposed new weight scheme is based on the identification of important features in GNSS data in urban environments and intelligent classification of line-of-sight (LOS) and NLOS signals. To validate the performance of the newly proposed weight scheme, we have implemented it into a real-time single-frequency precise point positioning (SFPPP) system. The dynamic vehicle-based tests with a low-cost single-frequency u-blox M8T GNSS receiver demonstrate that the positioning accuracy using the new weight scheme outperforms the traditional C/N0 based weight model by 65.4% and 85.0% in the horizontal and up direction, and most position error spikes at overcrossing and short tunnels can be eliminated by the new weight scheme compared to the traditional method. It also surpasses the built-in satellite-based augmentation systems (SBAS) solutions of the u-blox M8T and is even better than the built-in real-time-kinematic (RTK) solutions of multi-frequency receivers like the u-blox F9P and Trimble BD982.

The classification of the line-of-sight (LOS) and non-line-of-sight (NLOS) signals is one of the major problems for robust GNSS positioning and the shadow matching in urban environments. The existing techniques include the multi-sensor integration, 3D map aid, using a dual-polarized antenna, an omnidirectional camera aid are proposed to solve the classification problem. However, they all require external hardware or up-to-date map, which is expensive or impractical for mass-market applications. Consistency checking with the receiver autonomous integrity monitoring (RAIM) is widely used for the detection of NLOS signals, but it is efficient only when the majority of the received signals are LOS signals. Machine learning methods, including the decision tree, the support vector machine (SVM) have been explored to classify LOS and NLOS with good accuracy. However, all current machine learning based method only utilize information within one epoch, all the inter-epoch information and data features in time series are lost, and the information of signal propagation in the complex urban environments is not fully manifested in the Rinex level observation and NMEA level observations in one single epoch. In this paper, a multivariate Long Short Term Memory Fully Convolutional Network (MLSTM-FCN) based signal classification method is proposed. With the aid of the convolution layer and long short term memory block, this method handles the data features in both time domain and value domain. Six time series features of GNSS signal, including differenced C/N0, time differenced ambiguity, double difference phase and pseudorange, phase and pseudorange consistency are analyzed and used as the input of the MLSTM-FCN. Datasets from two locations in the urban Calgary are collected, each of which is used for training and testing purposes respectively. The results reveal that, compared to the SVM classification method, the overall testing accuracy of the newly proposed classifier is improved from 93.00% to 95.97% for the Rinex level observation, and from 92.99% to 93.83 for the NMEA level observation. This improved classification accuracy brought by the proposed classifier is encouraging since it will enhance the robustness of the conventional GNSS positioning and the shadow matching based navigation system by reducing unbounded NLOS signal errors in urban environments and result in significant improvement in positioning accuracy. Compared to the SVM classifier aided single point positioning (SPP) test, the accuracy in the form of RMS of the MLSTM-FCN aided SPP test can be improved by 24.3%, 17.8% and 24.4% in the East, North and Up directions respectively, and the rate of the valid solution can be increased from 99.02% to 99.94%. The new method has the potential to be widely applied by various receiver types with the output of the raw observation or only with the NMEA observations output.