Neural Ranging Inertial Odometry

2025-12-11

AI Summary

In GPS-denied environments (e.g., long tunnels), UWB-based localization suffers from multipath interference, sensitivity to anchor deployment, and non-Gaussian measurement errors, leading to degraded accuracy. To address this, we propose a calibration-free, multipath-robust neural fusion framework for UWB–IMU integrated localization. Methodologically, we introduce a novel collaborative architecture comprising a graph attention network for UWB ranging and a recurrent neural network for inertial measurement processing, enabling seamless fusion of heterogeneous sensor data. The framework supports arbitrary numbers of anchors and tags, and maintains stability under degenerate configurations—such as single-anchor setups or tag positions outside the anchor convex hull. Geometric consistency is enhanced via nominal coordinate system modeling and least-squares optimization. Extensive real-world experiments across indoor, outdoor, and long-tunnel scenarios demonstrate a 42% reduction in positioning error over state-of-the-art methods, with significantly improved robustness.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Ultra-wideband (UWB) has shown promising potential in GPS-denied localization thanks to its lightweight and drift-free characteristics, while the accuracy is limited in real scenarios due to its sensitivity to sensor arrangement and non-Gaussian pattern induced by multi-path or multi-signal interference, which commonly occurs in many typical applications like long tunnels. We introduce a novel neural fusion framework for ranging inertial odometry which involves a graph attention UWB network and a recurrent neural inertial network. Our graph net learns scene-relevant ranging patterns and adapts to any number of anchors or tags, realizing accurate positioning without calibration. Additionally, the integration of least squares and the incorporation of nominal frame enhance overall performance and scalability. The effectiveness and robustness of our methods are validated through extensive experiments on both public and self-collected datasets, spanning indoor, outdoor, and tunnel environments. The results demonstrate the superiority of our proposed IR-ULSG in handling challenging conditions, including scenarios outside the convex envelope and cases where only a single anchor is available.

Problem

• Improves GPS-denied localization using UWB and inertial data
• Addresses UWB accuracy issues from sensor arrangement and interference
• Enables robust positioning in varied environments without calibration

Innovation

• Graph attention UWB network learns scene-relevant ranging patterns
• Recurrent neural inertial network integrates with least squares and nominal frame
• Framework adapts to any number of anchors or tags without calibration