# Active Neural Localization

arXiv: https://arxiv.org/abs/1801.08214 · HTML: https://mlsanity.com/paper/1801.08214/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2018.

## Built on by (most cited first, 18 of 18)

- [Navigating to Objects in the Real World](https://mlsanity.com/paper/2212.00922/) (2022)
- [Memory-Augmented Reinforcement Learning for Image-Goal Navigation](https://mlsanity.com/paper/2101.05181/) (2021)
- [Retrospectives on the Embodied AI Workshop](https://mlsanity.com/paper/2210.06849/) (2022)
- [Towards Versatile Embodied Navigation](https://mlsanity.com/paper/2210.16822/) (2022)
- [FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation](https://mlsanity.com/paper/2310.07473/) (2023)
- [FrontierNet: Learning Visual Cues to Explore](https://mlsanity.com/paper/2501.04597/) (2025)
- [Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition](https://mlsanity.com/paper/2110.09018/) (2021)
- [Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information](https://mlsanity.com/paper/2407.15593/) (2024)
- [Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations](https://mlsanity.com/paper/2106.11345/) (2021)
- [Active Visual Localization for Multi-Agent Collaboration: A Data-Driven Approach](https://mlsanity.com/paper/2310.02650/) (2023)
- [Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement](https://mlsanity.com/paper/2503.10986/) (2025)
- [Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps](https://mlsanity.com/paper/2204.10497/) (2022)
- [ActLoc: Learning to Localize on the Move via Active Viewpoint Selection](https://mlsanity.com/paper/2508.20981/) (2025)
- [Open-World Distributed Robot Self-Localization with Transferable Visual Vocabulary and Both Absolute and Relative Features](https://mlsanity.com/paper/2109.04569/) (2021)
- [Active Semantic Localization with Graph Neural Embedding](https://mlsanity.com/paper/2305.06141/) (2023)
- [Collision Replay: What Does Bumping Into Things Tell You About Scene Geometry?](https://mlsanity.com/paper/2105.01061/) (2021)
- [FindView: Precise Target View Localization Task for Look Around Agents](https://mlsanity.com/paper/2303.09054/) (2023)
- [Beyond Frontiers: Scene-Anomaly Guided Autonomous Exploration](https://mlsanity.com/paper/2607.15828/) (2026)

## Abstract (arXiv)

Localization is the problem of estimating the location of an autonomous agent from an observation and a map of the environment. Traditional methods of localization, which filter the belief based on the observations, are sub-optimal in the number of steps required, as they do not decide the actions taken by the agent. We propose "Active Neural Localizer", a fully differentiable neural network that learns to localize accurately and efficiently. The proposed model incorporates ideas of traditional filtering-based localization methods, by using a structured belief of the state with multiplicative interactions to propagate belief, and combines it with a policy model to localize accurately while minimizing the number of steps required for localization. Active Neural Localizer is trained end-to-end with reinforcement learning. We use a variety of simulation environments for our experiments which include random 2D mazes, random mazes in the Doom game engine and a photo-realistic environment in the Unreal game engine. The results on the 2D environments show the effectiveness of the learned policy in an idealistic setting while results on the 3D environments demonstrate the model's capability of learning the policy and perceptual model jointly from raw-pixel based RGB observations. We also show that a model trained on random textures in the Doom environment generalizes well to a photo-realistic office space environment in the Unreal engine.