Enhancing GNSS Positioning in Urban Environments: A Transformer-Based NLOS Detection and Adaptive Weighting Approach

Global navigation satellite system (GNSS) positioning is widely used in various applications, but its positioning accuracy is often compromised by nonline-of-sight (NLOS) signals, particularly in urban environments. To address this challenge, we conduct a physical analysis to construct features that reflect NLOS signals. Based on this, we propose a hybrid architecture that integrates Transformer-based self-attention mechanisms with a Mixture-of-Experts (MoEs) framework, referred to as TransMoE, for NLOS signal detection. Additionally, to enhance the interpretability of TransMoE, we assign each feature with learnable parameters that dynamically update their weights. Furthermore, we propose an adaptive NLOS weighting algorithm that prioritizes satellites with favorable geometric distributions while mitigating NLOS-contaminated measurements in positioning solutions. Experimental validation on Hong Kong UrbanNav datasets demonstrates that TransMoE achieves consistent detection accuracy exceeding 90% across varying urban canyon scenarios. When integrated into positioning workflows, the adaptive correction algorithm reduces 2-D positioning errors by 42.73%, 27.43%, and 40.68% compared to the conventional weighted least squares method.