Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas

Abstract

In urban areas, global navigation satellite system (GNSS) signals are often reflected or blocked by buildings, thus resulting in large positioning errors. In this study, we proposed a machine learning approach for global positioning system (GPS) multipath detection that uses dual antennas. A machine learning model that could classify GPS signal reception conditions was trained with several GPS measurements selected as suggested features. We applied five features for machine learning, including a feature obtained from the dual antennas, and evaluated the classification performance of the model, after applying four machine learning algorithms: gradient boosting decision tree (GBDT), random forest, decision tree, and K-nearest neighbor (KNN). It was found that a classification accuracy of 82%-96% was achieved when the test data set was collected at the same locations as those of the training data set. However, when the test data set was collected at locations different from those of the training data, a classification accuracy of 44%-77% was obtained.

Submitted to ASCC 2022

References in corpus (21)

• A GPS spoofing detection and classification correlator-based technique using the LASSO
• Optimal Parameter Inflation to Enhance the Availability of Single-Frequency GBAS for Intelligent Air Transportation
• Enhanced Accuracy Simulator for a Future Korean Nationwide eLoran System
• RSS-based LTE Base Station Localization Using Single Receiver in Environment with Unknown Path-Loss Exponent
• SFOL DME Pulse Shaping Through Digital Predistortion for High-Accuracy DME
• Effect of Outlier Removal from Temporal ASF Corrections on Multichain Loran Positioning Accuracy
• Effects of Initial Attitude Estimation Errors on Loosely Coupled Smartphone GPS/IMU Integration System
• Fast User Adaptation for Human Motion Prediction in Physical Human-Robot Interaction
• Neural Network-Based Ranging with LTE Channel Impulse Response for Localization in Indoor Environments
• Motion Planning by Reinforcement Learning for an Unmanned Aerial Vehicle in Virtual Open Space with Static Obstacles
• Development of Record and Management Software for GPS/Loran Measurements
• Dynamic Difficulty Adjustment via Fast User Adaptation
• Integrity-Based Path Planning Strategy for Urban Autonomous Vehicular Navigation Using GPS and Cellular Signals
• Indoor Path Planning for an Unmanned Aerial Vehicle via Curriculum Learning
• Optimal Action-based or User Prediction-based Haptic Guidance: Can You Do Even Better?
• A Preliminary Study of Machine-Learning-Based Ranging with LTE Channel Impulse Response in Multipath Environment
• Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network
• Development of an R-Mode Simulator Using MF DGNSS Signals
• Single-Antenna-Based GPS Antijamming Method Exploiting Polarization Diversity
• Indoor Navigation Algorithm Based on a Smartphone Inertial Measurement Unit and Map Matching
• First Demonstration of the Korean eLoran Accuracy in a Narrow Waterway Using Improved ASF Maps

Cited by in corpus (2)

• Machine-Learning-Based Classification of GPS Signal Reception Conditions Using a Dual-Polarized Antenna in Urban Areas
• Efficient Quantum Circuit Encoding of Object Information in 2D Ray Casting