LF-GNSS: Towards More Robust Satellite Positioning with a Hard Example Mining Enhanced Learning-Filtering Deep Fusion Framework

2025-05-26

AI Summary

To address GNSS positioning accuracy degradation in urban environments caused by non-line-of-sight (NLOS) propagation and multipath effects, this paper proposes a learning-filter深度融合 framework: signal-quality-aware adaptive Kalman filtering. Our method jointly optimizes deep neural networks and the extended Kalman filter (EKF) in an end-to-end trainable architecture. Key contributions include: (i) a novel dynamic hard-example mining mechanism to enhance model robustness against NLOS/multipath outliers; and (ii) a DOP-aware satellite feature representation enabling observation weighting optimization and adaptive modeling of measurement noise covariance. Evaluated on both public and proprietary urban GNSS datasets, our approach reduces positioning error by 32.7% compared to conventional GNSS algorithms and state-of-the-art learning-based methods. To foster reproducibility and community advancement, we publicly release both the source code and a dedicated urban satellite dataset.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Global Navigation Satellite System (GNSS) is essential for autonomous driving systems, unmanned vehicles, and various location-based technologies, as it provides the precise geospatial information necessary for navigation and situational awareness. However, its performance is often degraded by Non-Line-Of-Sight (NLOS) and multipath effects, especially in urban environments. Recently, Artificial Intelligence (AI) has been driving innovation across numerous industries, introducing novel solutions to mitigate the challenges in satellite positioning. This paper presents a learning-filtering deep fusion framework for satellite positioning, termed LF-GNSS. The framework utilizes deep learning networks to intelligently analyze the signal characteristics of satellite observations, enabling the adaptive construction of observation noise covariance matrices and compensated innovation vectors for Kalman filter input. A dynamic hard example mining technique is incorporated to enhance model robustness by prioritizing challenging satellite signals during training. Additionally, we introduce a novel feature representation based on Dilution of Precision (DOP) contributions, which helps to more effectively characterize the signal quality of individual satellites and improve measurement weighting. LF-GNSS has been validated on both public and private datasets, demonstrating superior positioning accuracy compared to traditional methods and other learning-based solutions. To encourage further integration of AI and GNSS research, we will open-source the code at https://github.com/GarlanLou/LF-GNSS, and release a collection of satellite positioning datasets for urban scenarios at https://github.com/GarlanLou/LF-GNSS-Dataset.

Problem

• Enhances GNSS robustness against NLOS and multipath effects
• Integrates deep learning with Kalman filtering for improved positioning
• Introduces dynamic hard example mining for model robustness

Innovation

• Deep fusion framework for satellite positioning
• Dynamic hard example mining technique
• Novel DOP-based feature representation