# Multi-Modal Recurrent Fusion for Indoor Localization

arXiv: https://arxiv.org/abs/2203.00510 · HTML: https://mlsanity.com/paper/2203.00510/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 19 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [A Survey of Indoor Localization Systems and Technologies](https://mlsanity.com/paper/1709.01015/) (2017)
- [Recurrent Neural Networks For Accurate RSSI Indoor Localization](https://mlsanity.com/paper/1903.11703/) (2019)
- [Indoor positioning systems: Smart fusion of a variety of sensor readings](https://mlsanity.com/paper/2105.05438/) (2021)
- [Multi-Band Wi-Fi Sensing with Matched Feature Granularity](https://mlsanity.com/paper/2112.14006/) (2021)
- [Calibration-Free Positioning Technique Using Wi-Fi Ranging and Built-in Sensors of Mobile Devices](https://mlsanity.com/paper/2003.06013/) (2020)

## Built on by (most cited first, 3 of 3)

- [MetaGraphLoc: A Graph-based Meta-learning Scheme for Indoor Localization via Sensor Fusion](https://mlsanity.com/paper/2411.17781/) (2024)
- [Neural 5G Indoor Localization with IMU Supervision](https://mlsanity.com/paper/2402.09948/) (2024)
- [Hybrid Indoor Localization via Reinforcement Learning-based Information Fusion](https://mlsanity.com/paper/2210.15132/) (2022)

## Abstract (arXiv)

This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localization as a multi-modal sequence regression problem, a multi-stream recurrent fusion method is proposed to combine the current hidden state of each modality in the context of recurrent neural networks while accounting for the modality uncertainty which is directly learned from its own immediate past states. The proposed method was evaluated on the large-scale SPAWC2021 multi-modal localization dataset and compared with a wide range of baseline methods including the trilateration method, traditional fingerprinting methods, and convolution network-based methods.