# Neural SLAM: Learning to Explore with External Memory

arXiv: https://arxiv.org/abs/1706.09520 · HTML: https://mlsanity.com/paper/1706.09520/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 5 of 5)

- [SOON: Scenario Oriented Object Navigation with Graph-based Exploration](https://mlsanity.com/paper/2103.17138/) (2021)
- [Collaborative Visual Navigation](https://mlsanity.com/paper/2107.01151/) (2021)
- [SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation](https://mlsanity.com/paper/2110.07171/) (2021)
- [A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings](https://mlsanity.com/paper/2104.08492/) (2021)
- [SegVisRL: Visuomotor Development for a Lunar Rover for Hazard Avoidance using Camera Images](https://mlsanity.com/paper/2103.14422/) (2021)

## Abstract (arXiv)

We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment. This structure encourages the evolution of SLAM-like behaviors inside a completely differentiable deep neural network. We show that this approach can help reinforcement learning agents to successfully explore new environments where long-term memory is essential. We validate our approach in both challenging grid-world environments and preliminary Gazebo experiments. A video of our experiments can be found at: https://goo.gl/G2Vu5y.