# Neural 5G Indoor Localization with IMU Supervision

arXiv: https://arxiv.org/abs/2402.09948 · HTML: https://mlsanity.com/paper/2402.09948/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 11 of 11)

- [Channel Charting: Locating Users within the Radio Environment using Channel State Information](https://mlsanity.com/paper/1807.05247/) (2018)
- [Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning](https://mlsanity.com/paper/1708.06235/) (2017)
- [Novel Massive MIMO Channel Sounding Data Applied to Deep Learning-based Indoor Positioning](https://mlsanity.com/paper/1810.04126/) (2018)
- [Modern WLAN Fingerprinting Indoor Positioning Methods and Deployment Challenges](https://mlsanity.com/paper/1610.05424/) (2016)
- [CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network](https://mlsanity.com/paper/2205.05775/) (2022)
- [Fingerprinting-Based Positioning in Distributed Massive MIMO Systems](https://mlsanity.com/paper/1509.00202/) (2015)
- [WiCluster: Passive Indoor 2D/3D Positioning using WiFi without Precise Labels](https://mlsanity.com/paper/2107.01002/) (2021)
- [Multi-Modal Recurrent Fusion for Indoor Localization](https://mlsanity.com/paper/2203.00510/) (2022)
- [Neural RF SLAM for unsupervised positioning and mapping with channel state information](https://mlsanity.com/paper/2203.08264/) (2022)
- [Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization](https://mlsanity.com/paper/2111.12175/) (2021)
- [Benchmarking Learnt Radio Localisation under Distribution Shift](https://mlsanity.com/paper/2210.01930/) (2022)

## Built on by (most cited first, 1 of 1)

- [5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization](https://mlsanity.com/paper/2505.17684/) (2025)

## Abstract (arXiv)

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.