PC-DeepNet: A GNSS Positioning Error Minimization Framework Using Permutation-Invariant Deep Neural Network

2025-04-18

IEEE Sensors Journal

AI Summary

GNSS positioning in urban and suburban environments suffers from severe nonlinear and non-Gaussian measurement errors due to non-line-of-sight (NLOS) propagation, multipath effects, and weak signals, leading to significant degradation in accuracy for conventional model-driven approaches. To address this, we propose the first permutation-invariant deep neural network (PI-DNN) framework specifically designed for GNSS position correction. Its architecture inherently accommodates dynamic numbers of visible satellites and arbitrary ordering of pseudorange observations, while explicitly incorporating NLOS/multipath indicator features to enhance robustness and generalization. The model jointly optimizes error modeling and position correction via end-to-end learning. Evaluated on two public datasets, our method achieves up to a 42% improvement in positioning accuracy over state-of-the-art model-driven and learning-based baselines, while maintaining lower computational complexity.

Technology Category

Intelligent Robots: State EstimationSearch and Optimization: Learning to SearchPlanning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingUser Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Global navigation satellite systems (GNSS) face significant challenges in urban and sub-urban areas due to non-line-of-sight (NLOS) propagation, multipath effects, and low received power levels, resulting in highly non-linear and non-Gaussian measurement error distributions. In light of this, conventional model-based positioning approaches, which rely on Gaussian error approximations, struggle to achieve precise localization under these conditions. To overcome these challenges, we put forth a novel learning-based framework, PC-DeepNet, that employs a permutation-invariant (PI) deep neural network (DNN) to estimate position corrections (PC). This approach is designed to ensure robustness against changes in the number and/or order of visible satellite measurements, a common issue in GNSS systems, while leveraging NLOS and multipath indicators as features to enhance positioning accuracy in challenging urban and sub-urban environments. To validate the performance of the proposed framework, we compare the positioning error with state-of-the-art model-based and learning-based positioning methods using two publicly available datasets. The results confirm that proposed PC-DeepNet achieves superior accuracy than existing model-based and learning-based methods while exhibiting lower computational complexity compared to previous learning-based approaches.

Problem

• Minimizes GNSS positioning errors in urban areas
• Addresses NLOS and multipath effects in satellite signals
• Ensures robustness against variable satellite measurements

Innovation

• Uses permutation-invariant deep neural network
• Leverages NLOS and multipath indicators
• Ensures robustness against satellite measurement changes