Write a comment
Urban environments pose unique challenges for Global Navigation Satellite Systems (GNSS), with tall buildings, vehicles, and other obstacles often disrupting signals and causing Non-Line-of-Sight (NLOS) errors. To address this, researchers have developed an Artificial Intelligence (AI)-driven solution using the Light Gradient Boosting Machine (LightGBM), offering a new level of precision in iden 
by Simon Mansfield
Sydney, Australia (SPX) Dec 03, 2024
Urban environments pose unique challenges for Global Navigation Satellite Systems (GNSS), with tall buildings, vehicles, and other obstacles often disrupting signals and causing Non-Line-of-Sight (NLOS) errors. To address this, researchers have developed an Artificial Intelligence (AI)-driven solution using the Light Gradient Boosting Machine (LightGBM), offering a new level of precision in identifying and mitigating these errors.
The study, published in Satellite Navigation on November 22, 2024, showcases a machine learning approach that significantly improves GNSS accuracy by identifying and excluding NLOS signals. Researchers from Wuhan University, Southeast University, and Baidu conducted real-world experiments in Wuhan, China, validating the efficacy of the LightGBM model in complex urban settings.
The LightGBM method employs a fisheye camera to classify GNSS signals as Line-of-Sight (LOS) or NLOS based on satellite visibility. By analyzing multiple signal features - such as signal-to-noise ratio, elevation angle, and pseudorange consistency - the model achieved a remarkable 92% accuracy rate in distinguishing between LOS and NLOS signals. Compared to traditional methods like XGBoost, LightGBM delivered superior performance, enhancing computational efficiency and accuracy. Excluding NLOS signals from GNSS calculations resulted in notable improvements in positioning precision, particularly in dense urban areas.
"This method represents a major leap forward in enhancing GNSS positioning in urban environments," said Dr. Xiaohong Zhang, the lead researcher. "By using machine learning to analyze multiple signal features, we've shown that excluding NLOS signals can significantly boost the accuracy and reliability of satellite-based navigation systems. This has profound implications for applications such as autonomous driving and smart city infrastructure."
The findings have critical implications for industries reliant on GNSS, including autonomous vehicles, drones, and urban planning. Enhanced detection and mitigation of NLOS errors can improve the safety and efficiency of navigation in crowded urban landscapes. As cities adopt smarter and more connected systems, this advancement is set to play a vital role in shaping future transportation and infrastructure technologies.
Research Report:A reliable NLOS error identification method based on LightGBM driven by multiple features of GNSS signals
Related Links
Aerospace Information Research Institute
GPS Applications, Technology and Suppliers