# Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal

arXiv: https://arxiv.org/abs/1807.05211 · HTML: https://mlsanity.com/paper/1807.05211/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2018.

## Built on by (most cited first, 11 of 11)

- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints](https://mlsanity.com/paper/2202.11271/) (2022)
- [Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation](https://mlsanity.com/paper/2107.13545/) (2021)
- [Emergence of Maps in the Memories of Blind Navigation Agents](https://mlsanity.com/paper/2301.13261/) (2023)
- [RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation](https://mlsanity.com/paper/2405.05792/) (2024)
- [Visual Representation Learning for Preference-Aware Path Planning](https://mlsanity.com/paper/2109.08968/) (2021)
- [TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals](https://mlsanity.com/paper/2509.08699/) (2025)
- [End-to-End Egospheric Spatial Memory](https://mlsanity.com/paper/2102.07764/) (2021)
- [Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots](https://mlsanity.com/paper/2112.05299/) (2021)
- [DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation](https://mlsanity.com/paper/2509.21930/) (2025)

## Abstract (arXiv)

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be prohibitively costly to obtain on robots in the real world. We present an approach for efficiently learning goal-directed navigation policies on a mobile robot, from only a single coverage traversal of recorded data. The navigation agent learns an effective policy over a diverse action space in a large heterogeneous environment consisting of more than 2km of travel, through buildings and outdoor regions that collectively exhibit large variations in visual appearance, self-similarity, and connectivity. We compare pretrained visual encoders that enable precomputation of visual embeddings to achieve a throughput of tens of thousands of transitions per second at training time on a commodity desktop computer, allowing agents to learn from millions of trajectories of experience in a matter of hours. We propose multiple forms of computationally efficient stochastic augmentation to enable the learned policy to generalise beyond these precomputed embeddings, and demonstrate successful deployment of the learned policy on the real robot without fine tuning, despite environmental appearance differences at test time. The dataset and code required to reproduce these results and apply the technique to other datasets and robots is made publicly available at rl-navigation.github.io/deployable.