# Spatio-Temporal Graph Localization Networks for Image-based Navigation

arXiv: https://arxiv.org/abs/2204.13237 · HTML: https://mlsanity.com/paper/2204.13237/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2022.

## Built on by (most cited first, 10 of 10)

- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [SACSoN: Scalable Autonomous Control for Social Navigation](https://mlsanity.com/paper/2306.01874/) (2023)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation](https://mlsanity.com/paper/2210.07450/) (2022)
- [Learning to Drive Anywhere with Model-Based Reannotation](https://mlsanity.com/paper/2505.05592/) (2025)
- [Supercharging Floorplan Localization with Semantic Rays](https://mlsanity.com/paper/2507.09291/) (2025)
- [AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge](https://mlsanity.com/paper/2602.13476/) (2026)
- [SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation](https://mlsanity.com/paper/2403.00991/) (2024)
- [Online Embedding Multi-Scale CLIP Features into 3D Maps](https://mlsanity.com/paper/2403.18178/) (2024)

## Abstract (arXiv)

Localization in topological maps is essential for image-based navigation using an RGB camera. Localization using only one camera can be challenging in medium-to-large-sized environments because similar-looking images are often observed repeatedly, especially in indoor environments. To overcome this issue, we propose a learning-based localization method that simultaneously utilizes the spatial consistency from topological maps and the temporal consistency from time-series images captured by the robot. Our method combines a convolutional neural network (CNN) to embed image features and a recurrent-type graph neural network to perform accurate localization. When training our model, it is difficult to obtain the ground truth pose of the robot when capturing images in real-world environments. Hence, we propose a sim2real transfer approach with semi-supervised learning that leverages simulator images with the ground truth pose in addition to real images. We evaluated our method quantitatively and qualitatively and compared it with several state-of-the-art baselines. The proposed method outperformed the baselines in environments where the map contained similar images. Moreover, we evaluated an image-based navigation system incorporating our localization method and confirmed that navigation accuracy significantly improved in the simulator and real environments when compared with the other baseline methods.