- SC-LIO-SAM is a real-time lidar-inertial SLAM package.
- LiDAR-inertial SLAM: Scan Context + LIO-SAM
- This repository is an example use-case of Scan Context, which is a fast and robust LiDAR place recognition method.
- For more details for each algorithm please refer to
Scan Context https://github.com/irapkaist/scancontext
LIO-SAM https://github.com/TixiaoShan/LIO-SAM - You can also use the LiDAR-only versions of this project: SC-LeGO-LOAM and SC-A-LOAM.
- Light-weight: a single header and cpp file named "Scancontext.h" and "Scancontext.cpp"
- Our module has KDtree and we used nanoflann. nanoflann is an also single-header-program and that file is in our directory.
- Easy to use: A user just remembers and uses only two API functions;
makeAndSaveScancontextAndKeys
anddetectLoopClosureID
. - Fast: A single loop detection requires under 30 ms (for 20 x 60 size, 3 candidates)
- We provide a tutorial that runs SC-LIO-SAM on MulRan dataset, you can reproduce the above results by following these steps.
- You can download the dataset at the MulRan dataset website
- Place the directory
SC-LIO-SAM
under user catkin work space
For example,cd ~/catkin_ws/src git clone https://github.com/gisbi-kim/SC-LIO-SAM.git cd .. catkin_make source devel/setup.bash roslaunch lio_sam run.launch # or roslaunch lio_sam run_mulran.launch
- By following this guideline, you can easily publish the MulRan dataset's LiDAR and IMU topics via ROS.