https://github.com/ga58lar/mapblend

Consistent Long-Term Point Cloud Mapping with Prior Maps
https://github.com/ga58lar/mapblend

lifelong-static-mapping localization mapping ros2 slam

Last synced: about 1 month ago
JSON representation

Consistent Long-Term Point Cloud Mapping with Prior Maps

• Host: GitHub
• URL: https://github.com/ga58lar/mapblend
• Owner: ga58lar
• Created: 2025-01-31T22:45:34.000Z (3 months ago)
• Default Branch: develop
• Last Pushed: 2025-02-20T23:02:58.000Z (3 months ago)
• Last Synced: 2025-02-20T23:23:00.888Z (3 months ago)
• Topics: lifelong-static-mapping, localization, mapping, ros2, slam
• Language: C++
• Homepage:
• Size: 7.45 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  
MapBlend

  
Consistent Long-Term Point Cloud Mapping with Prior Maps


  


  [![Docker](https://badgen.net/badge/icon/docker?icon=docker&label)](https://www.docker.com/)

  ![Linux](https://img.shields.io/badge/Linux-FCC624?logo=linux&logoColor=black)

  ![License](https://img.shields.io/badge/license-Apache%202.0-blue)

  ![Version](https://img.shields.io/badge/version-0.0.1-blue)

  

  


  



  

## PRELIMINARY version

This is a PRELIMINARY version

## Description

This repository is an extension to [OpenLiDARMap](https://github.com/TUMFTM/OpenLiDARMap), a zero-drift georeferenced LiDAR-only point cloud mapping algorithm.  

We combine the mapping module of OpenLiDARMap with the object detection module of [Autoware](https://autowarefoundation.github.io/autoware.universe/main/perception/autoware_lidar_centerpoint/) to filter movable objects before the mapping.  

Additionally, we enable the update of point cloud maps through a raycasting-based voxel-occlusion update strategy (THIS IS NOT YET AVAILABLE IN THIS REPOSITORY). 

## Install

```bash

git clone --recurse-submodules https://github.com/ga58lar/MapBlend.git

./docker/build_docker.sh

```

## Run

To run this repository, you will need a PC with a NVIDIA GPU.

You also need to download the lidar_centerpoint pre-trained models from [Autoware](https://autowarefoundation.github.io/autoware.universe/main/perception/autoware_lidar_centerpoint/).

```bash

./docker/run_docker.sh            

```

For a detailed instruction the the core module [OpenLiDARMap](https://github.com/TUMFTM/OpenLiDARMap), please refer to the official GitHub repository.

## Missing

- Object tracking module for robust movable object removal

- Life-long mapping module