Since there isn't an official package manager for C/C++, its always time-consuming and annoying to benchmark and develop various SLAM algorithm. Since the algorithms have various third parties with different version. This repo aims to provide reusable installer scripts for commonly used SLAM third-party libraries and merge them all together into various base Docker containers. Based on this repo, you may customize your environment to quickly run different SLAM algorithms for comparison, maintain a consitent SLAM development environment, or distribute your own SLAM algorithm with the container for rapid spread. Only the run-time environments are provided, the SLAM source codes and datasets are mounted into the container. In this way, you can modify the codes and datasets at any time while keeping the docker image consistent.

A bunch of popular SLAM algorithms are well tested and listed as follows:

CI Status	Dockerfile	SLAM algorithm (commit link)
	Dockerfile.orb-slam	ORB_SLAM2, ORB_SLAM3
	Dockerfile.r3live	r3live, FAST-LIO(2.0), LIO-Livox
	Dockerfile.faster-lio	Faster-LIO, DLIO
	BAD-SLAM	BAD SLAM

Docker installed. Install Docker Engine

1. Build the Docker image:

   ./build.sh Dockerfile.image-name
   

   This will build a Docker image named image-name:latest. Change Dockerfile.image-name to yours.

2. Run the Docker image:

   ./run.sh image-name
   

   This will run Docker image image-name as a container. The container will mount the host source directory. The HOST_SOURCE_DIR in run.sh specifies the directory.

3. Enjoy!

1. Create a third_party lib installer script, e.g., installers/3rdparties_slam/slam.sh , (like orb_slam.sh) to customize your third_party libs.

2. Create a Docker file, e.g., Dockerfile.slam which will run above script.

3. Build your container:

   ./build.sh Dockerfile.slam
   

   which will create a container named slam.

4. Run the container:

   ./run.sh slam
   

1. The SLAM source code directory is mounted into the Docker container. Set HOST_SOURCE_DIR="slam/source/dir" in run.sh , this will mount your host directory slam/source/dir into Docker directory /home/slam/src . You can mount your datasets by modifing HOST_DATASET_DIR.

2. Some source mirrors such as apt and python mirrors are modified to China mirrors to improve download speed for China mainland users.

3. You can manually pre-download third-party lib source code tarball files into archive dir for offline Docker building.

4. Recommend to develop your SLAM algorithm using VS Code inside the containers, just modify the the attributes of ./devcontainer/devcontainer.json in VSCode:

   "build": {
        "dockerfile": "pathto/Dockerfile.ubuntu18-opengl",
   },

   See more details in Developing inside a Container.

5. Welcome to contribute new installers needed for SLAM development and create new branches to host the State-of-the-Art SLAM algorithm development environments.

Some part of source code are adapted from Baidu Apollo, which is licensed under the Apache-2.0 license.