# NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT

arXiv: https://arxiv.org/abs/2404.08939 · HTML: https://mlsanity.com/paper/2404.08939/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 60 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [Block-Recurrent Transformers](https://mlsanity.com/paper/2203.07852/) (2022)
- [FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter](https://mlsanity.com/paper/2010.08196/) (2020)
- [RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods](https://mlsanity.com/paper/1905.12853/) (2019)
- [IONet: Learning to Cure the Curse of Drift in Inertial Odometry](https://mlsanity.com/paper/1802.02209/) (2018)
- [TLIO: Tight Learned Inertial Odometry](https://mlsanity.com/paper/2007.01867/) (2020)
- [RIDI: Robust IMU Double Integration](https://mlsanity.com/paper/1712.09004/) (2017)
- [Multi-Loss Weighting with Coefficient of Variations](https://mlsanity.com/paper/2009.01717/) (2020)
- [AI-IMU Dead-Reckoning](https://mlsanity.com/paper/1904.06064/) (2019)
- [RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition](https://mlsanity.com/paper/2111.04566/) (2021)
- [STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks](https://mlsanity.com/paper/1902.07849/) (2019)
- [CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction](https://mlsanity.com/paper/1810.01011/) (2018)
- [RIO: Rotation-equivariance supervised learning of robust inertial odometry](https://mlsanity.com/paper/2111.11676/) (2021)
- [Neural Inertial Localization](https://mlsanity.com/paper/2203.15851/) (2022)
- [CTIN: Robust Contextual Transformer Network for Inertial Navigation](https://mlsanity.com/paper/2112.02143/) (2021)
- [MIMC-VINS: A Versatile and Resilient Multi-IMU Multi-Camera Visual-Inertial Navigation System](https://mlsanity.com/paper/2006.15699/) (2020)
- [Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization](https://mlsanity.com/paper/2211.07635/) (2022)
- [Real-Time Robot Localization, Vision, and Speech Recognition on Nvidia Jetson TX1](https://mlsanity.com/paper/1705.10945/) (2017)

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

- [BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices](https://mlsanity.com/paper/2508.03313/) (2025)

## Abstract (arXiv)

Inertial tracking is vital for robotic IoT and has gained popularity thanks to the ubiquity of low-cost inertial measurement units and deep learning-powered tracking algorithms. Existing works, however, have not fully utilized IMU measurements, particularly magnetometers, nor have they maximized the potential of deep learning to achieve the desired accuracy. To address these limitations, we introduce NeurIT, which elevates tracking accuracy to a new level. NeurIT employs a Time-Frequency Block-recurrent Transformer (TF-BRT) at its core, combining both RNN and Transformer to learn representative features in both time and frequency domains. To fully utilize IMU information, we strategically employ body-frame differentiation of magnetometers, considerably reducing the tracking error. We implement NeurIT on a customized robotic platform and conduct evaluation in various indoor environments. Experimental results demonstrate that NeurIT achieves a mere 1-meter tracking error over a 300-meter distance. Notably, it significantly outperforms state-of-the-art baselines by 48.21% on unseen data. Moreover, NeurIT demonstrates robustness in large urban complexes and performs comparably to the visual-inertial approach (Tango Phone) in vision-favored conditions while surpassing it in feature-sparse settings. We believe NeurIT takes an important step forward toward practical neural inertial tracking for ubiquitous and scalable tracking of robotic things. NeurIT is open-sourced here: https://github.com/aiot-lab/NeurIT.