# Deep Active Localization

## TL;DR

This paper presents a fully trainable, end-to-end deep learning approach for active robot localization that outperforms traditional methods and is transferable from simulation to real-world hardware.

## Contribution

It introduces a novel differentiable system combining perception and planning modules, trained entirely in simulation for effective real-world application.

## Key findings

- Outperforms traditional information-theoretic approaches
- Robust to different map configurations and nuisance parameters
- Compatible with OpenAI gym and Gazebo simulators

## Abstract

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models. In this work we propose an end-to-end differentiable method for learning to take informative actions that is trainable entirely in simulation and then transferable to real robot hardware with zero refinement. The system is composed of two modules: a convolutional neural network for perception, and a deep reinforcement learned planning module. We introduce a multi-scale approach to the learned perceptual model since the accuracy needed to perform action selection with reinforcement learning is much less than the accuracy needed for robot control. We demonstrate that the resulting system outperforms using the traditional approach for either perception or planning. We also demonstrate our approaches robustness to different map configurations and other nuisance parameters through the use of domain randomization in training. The code is also compatible with the OpenAI gym framework, as well as the Gazebo simulator.