Information-Theoretic Geometry Optimization and Physics-Aware Learning for Calibration-Free Magnetic Localization

2026-04-24

AI Summary

This work addresses the challenges of permanent magnet–based wireless localization in medical interventions, which are hindered by poor observability of sensor arrays and the simulation-to-reality (Sim-to-Real) modeling gap. The authors propose a calibration-free, high-precision magnetic localization system that first optimizes an interleaved split sensor array design using the Fisher Information Matrix (FIM) to enhance observability. They further introduce Phy-GAANet, a novel neural network integrating Physics-Informed Features (PIF) with a Geometry-Aware Attention (GAA) mechanism, trained on hardware-aware synthetic data to effectively bridge the Sim-to-Real gap. Experimental results demonstrate a localization error as low as 1.84 mm, an orientation error of 3.18°, and a refresh rate exceeding 270 Hz, with strong robustness in near-field boundary regions, significantly outperforming conventional approaches and generic convolutional models.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Hardware-aware ML
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Wireless localization of permanent magnets enables occlusion-free guidance for medical interventions, yet its practical accuracy is fundamentally limited by two coupled challenges: the poor observability of conventional planar sensor arrays and the simulation-to-reality (Sim-to-Real) gap of learning-based estimators. To address these issues, this article presents a unified framework that combines information-theoretic sensor geometry optimization with physics-aware deep learning. First, a rigorous Fisher Information Matrix (FIM)-based evaluation framework is established to quantify geometry-induced observability limitations. The results show that a staggered split-array topology provides a substantially stronger observability foundation for localization while remaining compatible with practical external deployment. Second, building on this optimized sensing configuration, we propose Phy-GAANet, a calibration-free estimator trained entirely on hardware-aware synthetic data. By incorporating Physics-Informed Features (PIF) for saturation modeling and Geometry-Aware Attention (GAA) for preserving cross-layer vector structure, the network effectively bridges the Sim-to-Real gap. Extensive real-world experiments demonstrate state-of-the-art performance, achieving a position error of 1.84 mm and an orientation error of 3.18 degrees at a refresh rate exceeding 270 Hz. The proposed method consistently outperforms classical Levenberg--Marquardt solvers and generic convolutional baselines, particularly in suppressing catastrophic outliers and maintaining robustness in challenging near-field boundary regions. Beyond the proposed network, the FIM-guided analysis also provides a framework for sensor geometry design in magnetic localization systems under practical deployment constraints.

Problem

• magnetic localization
• sensor geometry
• observability
• simulation-to-reality gap
• calibration-free

Innovation

• Fisher Information Matrix
• Sensor Geometry Optimization
• Physics-Informed Features
• Geometry-Aware Attention
• Calibration-Free Localization