# Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU

## TL;DR

This paper introduces a deep learning-based laser localization method that learns meaningful descriptors from 3D point clouds, enabling efficient loop closure detection suitable for CPU deployment in challenging urban and natural environments.

## Contribution

A novel deep learning approach for laser-based localization that learns descriptors directly from 3D point clouds, optimized for CPU-based real-time applications in diverse environments.

## Key findings

- Effective loop closure detection in natural and urban environments
- Small model size suitable for CPU deployment
- Applicable to robots with limited computational resources

## Abstract

Localization in challenging, natural environments such as forests or woodlands is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this work we explore laser-based localization in both urban and natural environments, which is suitable for online applications. We propose a deep learning approach capable of learning meaningful descriptors directly from 3D point clouds by comparing triplets (anchor, positive and negative examples). The approach learns a feature space representation for a set of segmented point clouds that are matched between a current and previous observations. Our learning method is tailored towards loop closure detection resulting in a small model which can be deployed using only a CPU. The proposed learning method would allow the full pipeline to run on robots with limited computational payload such as drones, quadrupeds or UGVs.