Calibration-Free Induced Magnetic Field Indoor and Outdoor Positioning via Data-Driven Modeling

TL;DR

The paper tackles indoor localization with induced magnetic fields by replacing analytical inversion and fingerprinting with a data-driven approach that directly maps IMF measurements to spatial coordinates, enabling calibration-free deployment. It introduces a multi-axis transmitter array and tri-axial receiver, uses orientation-invariant magnitude features, and evaluates several learning models, finding Random Forest to offer the best accuracy–robustness trade-off. The method demonstrates sub-20 cm 2D and sub-30 cm 3D localization, with strong cross-environment generalization from indoors to outdoors and a scalable deployment analysis via transmitter spacing. These results indicate a practical, transferable IMF localization framework capable of real-world, calibration-free operation in varied environments.

Abstract

Induced magnetic field (IMF)-based localization offers a robust alternative to wave-based positioning technologies due to its resilience to non-line-of-sight conditions, environmental dynamics, and wireless interference. However, existing magnetic localization systems typically rely on analytical field inversion, manual calibration, or environment-specific fingerprinting, limiting their scalability and transferability. This paper presents a data-driven IMF localization framework that directly maps induced magnetic field measurements to spatial coordinates using supervised learning, eliminating explicit environment-specific calibration. By replacing explicit field modeling with learning-based inference, the proposed approach captures nonlinear field interactions and environmental effects. An orientation-invariant feature representation enables rotation-independent deployment. The system is evaluated across multiple indoor environments and an outdoor deployment. Benchmarking against classical and deep learning baselines shows that a Random Forest regressor achieves sub-20 cm accuracy in 2D and sub-30 cm in 3D localization. Cross-environment validation demonstrates that models trained indoors generalize to outdoor environments without retraining. We further analyze scalability by varying transmitter spacing, showing that coverage and accuracy can be balanced through deployment density. Overall, this work demonstrates that data-driven IMF localization is a scalable and transferable solution for real-world positioning.

Figures (9)

• Figure 1: Transmitter coil prototype for low-frequency magnetic field generation.
• Figure 2: Geometric principle of 3D localization using multiple magnetic field transmitters.
• Figure 3: Prototype of the transmitter (left) and receiver (right).
• Figure 4: Marvelmind ultrasonic localization system: router (left) and stationary beacon (right).
• Figure 5: Experimental scenes for data collection: top-left: Meeting room, top-right: Corridor, bottom-left: Social area, and bottom-right: Outdoor environment.