LVI-SAM-SAVEMAP

This repository contains code that use LVI-SAM to build map and save the map. The map include visual information and LiDAR information. The map structure is:

your folder
- camera (Visual Map)
  - pose_graph (similar to vins-mono's pose graph)
- lidar (LiDAR Map)
  - Corners (corner point cloud pcd)
  - Surfs (surface point cloud pcd)
  - Scans (deskewed point cloud pcd)
  - SCDs
  - cloudGlobal.pcd
  - cloudCorner.pcd
  - cloudSurfs.pcd
  - trajectory.pcd
  - transformations.pcd

Dependency

The dependency of this repo is same as the official LVI-SAM. So if you occur a compile problem, we recommend you to compile the official LVI-SAM firstly. Right now we have only tested on Ubuntu 18.04 + ROS melodic environment.

Compile

You can use the following commands to download and compile the package.

mkdir -p ~/catkin_ws/src
cd ~/catkin_ws/src
git clone https://github.com/x-Yabao/lvi_sam_savemap
cd ..
catkin_make

Run the package on different datasets

M2DGR dataset

Change the config files, make sure all the paths are right.
Run the launch file:

roslaunch lvi_sam run_m2dgr.launch

Play existing bag files, e.g. gate_01.bag:

rosbag play gate_01.bag

After playing the rosbag, input s and Enter in the terminal to save the Visual Map, then press Ctrl + C to save the LiDAR Map.

KITTI raw dataset

Change the config files, make sure all the paths are right.
Run the launch file:

roslaunch lvi_sam run_kitti_xx_xx.launch

Play existing bag files. Please note that you must use KITTI raw dataset rather than KITTI Odometry dataset, because the latter's IMU frequency is too low. If you want to use KITTI raw dataset for LVI-SAM, you need to get rosbag files firstly. You can get it refer to LIO-SAM/config/doc/kitti2bag.

rosbag play kitti_xxx.bag

After playing the rosbag, input s and Enter in the terminal to save the Visual Map, then press Ctrl + C to save the Lidar Map.

x-Yabao/lvi_sam_savemap

LVI-SAM-SAVEMAP

Dependency

Compile

Run the package on different datasets

Acknowledgement