Abstract
Global Positioning System (GPS) has been used in many aerial and terrestrial high precision positioning applications. Multipath affects positioning and navigation performance. This paper proposes a convolutional neural network based carrier-phase multipath detection method. The method is based on the fact that the features of multipath characteristics in multipath contaminated data can be learned and identified by a convolutional neural network. The proposed method is validated with simulated and real GPS data and compared with existing multipath mitigation methods in position domain. The results show the proposed method can detect about 80% multipath errors (i.e., recall) in both simulated and real data. The impact of the proposed method on positioning accuracy improvement is demonstrated with two datasets, 18–30% improvement is obtained by down-weighting the detected multipath measurements. The focus of this paper is on the development and test of the proposed convolutional neural network based multipath detection algorithm.
Highlights
Global Positioning System (GPS) has been intensively used in high precision positioning applications such as attitude determination of unmanned aerial vehicles e.g., [1] and other autonomous vehicles e.g., [2]
The proposed methods can be used in carrier phase based kinematic positioning, including Real-Time Kinematic (RTK) applications for improving kinematic positioning performance in difficult environments
The real data have higher rates of false detection. This is because a real multipath signal may have small magnitudes of multipath errors labelled as direct-signal only; they are sometimes comparable to the carrier phase measurement noise
Summary
Global Positioning System (GPS) has been intensively used in high precision positioning applications such as attitude determination of unmanned aerial vehicles e.g., [1] and other autonomous vehicles e.g., [2]. With a temporary or permanent reference station and a rover station, carrier phase based relative GPS biases and errors such as satellite clock and orbit offsets, ionospheric and tropospheric biases can be eliminated or greatly mitigated with differencing techniques at a short baseline between the rover and reference stations. Convolutional Neural Networks (CNN) are being widely deployed in many applications, like image recognition, video analysis, and for time series processing like music, speech recognition [19,20]. A convolutional filter (kernel) within convolutional layers can provide a compressed representation of input data, and it can be computed using methods such as Sparse Auto-Encoder (SAE) and Principle Component Analysis (PCA). An SAE neural network is an unsupervised learning algorithm that applies backpropagation and sparsity constraint [21,22,23].
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
