Radio signals are well suited for user localization because they are ubiquitous, can operate in the dark and maintain privacy. Many prior works learn mappings between channel state information (CSI) and position fully-supervised. However, that approach relies on position labels which are very expensive to acquire. In this work, this requirement is relaxed by using pseudo-labels during deployment, which are calculated from an inertial measurement unit (IMU). We propose practical algorithms for IMU double integration and training of the localization system. We show decimeter-level accuracy on simulated and challenging real data of 5G measurements. Our IMU-supervised method performs similarly to fully-supervised, but requires much less effort to deploy.
@article{arxiv.2402.09948,
title = {Neural 5G Indoor Localization with IMU Supervision},
author = {Aleksandr Ermolov and Shreya Kadambi and Maximilian Arnold and Mohammed Hirzallah and Roohollah Amiri and Deepak Singh Mahendar Singh and Srinivas Yerramalli and Daniel Dijkman and Fatih Porikli and Taesang Yoo and Bence Major},
journal= {arXiv preprint arXiv:2402.09948},
year = {2024}
}