# Pre-Trained Masked Image Model for Mobile Robot Navigation

arXiv: https://arxiv.org/abs/2310.07021 · HTML: https://mlsanity.com/paper/2310.07021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Adversarial Masking for Self-Supervised Learning](https://mlsanity.com/paper/2201.13100/) (2022)
- [Learning to Map for Active Semantic Goal Navigation](https://mlsanity.com/paper/2106.15648/) (2021)
- [Simple and Effective Synthesis of Indoor 3D Scenes](https://mlsanity.com/paper/2204.02960/) (2022)
- [Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation](https://mlsanity.com/paper/1803.02007/) (2018)
- [ProxMaP: Proximal Occupancy Map Prediction for Efficient Indoor Robot Navigation](https://mlsanity.com/paper/2203.04177/) (2022)

## Abstract (arXiv)

2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have shown that predicting the structural patterns in the environment through learning-based approaches can greatly enhance task efficiency. While many such works build task-specific networks using limited datasets, we show that the existing foundational vision networks can accomplish the same without any fine-tuning. Specifically, we use Masked Autoencoders, pre-trained on street images, to present novel applications for field-of-view expansion, single-agent topological exploration, and multi-agent exploration for indoor mapping, across different input modalities. Our work motivates the use of foundational vision models for generalized structure prediction-driven applications, especially in the dearth of training data. For more qualitative results see https://raaslab.org/projects/MIM4Robots.