NeRC: Neural Ranging Correction through Differentiable Moving Horizon Location Estimation

2025-08-19

AI Summary

Low GNSS positioning accuracy for mobile devices in urban environments—caused by multipath effects, signal occlusion, and ranging errors from low-cost hardware—is addressed in this work. We propose NeRC, an end-to-end neural network framework. Its key contributions are: (1) a differentiable moving-window position estimation module that eliminates reliance on ground-truth ranging error labels; (2) a differentiable moving horizontal estimation (MHE) mechanism enabling effective gradient backpropagation; and (3) a cost-map training paradigm based on Euclidean distance fields (EDFs), reducing annotation overhead while supporting joint optimization. Evaluated on both public and custom-built urban datasets, NeRC achieves significant improvements in localization accuracy over state-of-the-art methods. Furthermore, it is successfully deployed on edge devices, demonstrating real-time performance and practical viability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

GNSS localization using everyday mobile devices is challenging in urban environments, as ranging errors caused by the complex propagation of satellite signals and low-quality onboard GNSS hardware are blamed for undermining positioning accuracy. Researchers have pinned their hopes on data-driven methods to regress such ranging errors from raw measurements. However, the grueling annotation of ranging errors impedes their pace. This paper presents a robust end-to-end Neural Ranging Correction (NeRC) framework, where localization-related metrics serve as the task objective for training the neural modules. Instead of seeking impractical ranging error labels, we train the neural network using ground-truth locations that are relatively easy to obtain. This functionality is supported by differentiable moving horizon location estimation (MHE) that handles a horizon of measurements for positioning and backpropagates the gradients for training. Even better, as a blessing of end-to-end learning, we propose a new training paradigm using Euclidean Distance Field (EDF) cost maps, which alleviates the demands on labeled locations. We evaluate the proposed NeRC on public benchmarks and our collected datasets, demonstrating its distinguished improvement in positioning accuracy. We also deploy NeRC on the edge to verify its real-time performance for mobile devices.

Problem

• Corrects GNSS ranging errors in urban environments
• Eliminates need for manual ranging error annotations
• Improves mobile device positioning accuracy end-to-end

Innovation

• Neural network trained with ground-truth locations
• Differentiable moving horizon estimation for backpropagation
• Euclidean Distance Field cost maps reduce labeling needs