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

arXiv: https://arxiv.org/abs/1902.10194 · HTML: https://mlsanity.com/paper/1902.10194/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition](https://mlsanity.com/paper/2109.08336/) (2021)
- [NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation](https://mlsanity.com/paper/2103.12292/) (2021)
- [Online Pole Segmentation on Range Images for Long-term LiDAR Localization in Urban Environments](https://mlsanity.com/paper/2208.07364/) (2022)
- [ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images](https://mlsanity.com/paper/2503.04475/) (2025)
- [Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition](https://mlsanity.com/paper/2309.00168/) (2023)
- [On the descriptive power of LiDAR intensity images for segment-based loop closing in 3-D SLAM](https://mlsanity.com/paper/2108.01383/) (2021)
- [TreeLoc: 6-DoF LiDAR Global Localization in Forests via Inter-Tree Geometric Matching](https://mlsanity.com/paper/2602.01501/) (2026)

## Abstract (arXiv)

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.