# Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization

arXiv: https://arxiv.org/abs/2211.07635 · HTML: https://mlsanity.com/paper/2211.07635/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 14 Nov 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods](https://mlsanity.com/paper/1905.12853/) (2019)
- [Scene-aware Generative Network for Human Motion Synthesis](https://mlsanity.com/paper/2105.14804/) (2021)
- [Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors](https://mlsanity.com/paper/1805.11122/) (2018)
- [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)
- [IDOL: Inertial Deep Orientation-Estimation and Localization](https://mlsanity.com/paper/2102.04024/) (2021)
- [WhONet: Wheel Odometry Neural Network for Vehicular Localisation in GNSS-Deprived Environments](https://mlsanity.com/paper/2104.02581/) (2021)
- [Map as The Hidden Sensor: Fast Odometry-Based Global Localization](https://mlsanity.com/paper/1910.00572/) (2019)
- [DeepBLE: Generalizing RSSI-based Localization Across Different Devices](https://mlsanity.com/paper/2103.00252/) (2021)

## Built on by (most cited first, 2 of 2)

- [NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT](https://mlsanity.com/paper/2404.08939/) (2024)
- [UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds](https://mlsanity.com/paper/2601.06602/) (2026)

## Abstract (arXiv)

Indoor localization systems often fuse inertial odometry with map information via hand-defined methods to reduce odometry drift, but such methods are sensitive to noise and struggle to generalize across odometry sources. To address the robustness problem in map utilization, we propose a data-driven prior on possible user locations in a map by combining learned spatial map embeddings and temporal odometry embeddings. Our prior learns to encode which map regions are feasible locations for a user more accurately than previous hand-defined methods. This prior leads to a 49% improvement in inertial-only localization accuracy when used in a particle filter. This result is significant, as it shows that our relative positioning method can match the performance of absolute positioning using bluetooth beacons. To show the generalizability of our method, we also show similar improvements using wheel encoder odometry.