Skip to content
Conference Open access

Calibration-Free Online Indoor Localization via 5G Channel Impulse Response SLAM

Oct 2026 · International Conference on Indoor Positioning and Indoor Navigation · pp. 1-6 · 0 citations · 24 references

Abstract

Today’s smartphone indoor-localization methods require extensive prior knowledge of the environment, such as precise maps, known base station positions, or large labeled datasets. These requirements often result in long initial calibration and maintenance efforts, making deployment in new or changing environments difficult. To address this problem, we present a SLAM-based approach to smartphone indoor localization that uses 5G Channel Impulse Response (CIR) and Inertial Measurement Unit (IMU) data. This approach relies on a robust factor-graph formulation that is based on detected loop closures, which are identified using a similarity metric on CIR data. Unlike many existing methods, our approach does not require any prior knowledge of the environment and enables instant, real-time localization relative to the starting position. In experimental evaluations, we show competitive performance to a fingerprinting solution consisting of a neural network that was trained using position-labeled data and fused with a map of the environment and IMU measurements. The results show that our approach achieves a mean localization accuracy of approximately 1.2 m, which is comparable to the fingerprinting solution.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.