<aside> 💡 In the following, we assume that the installation directory of Exwayz 3D Mapping is in the $PATH, and all executables are accessible from anywhere on the computer.

</aside>

exwayz_slam.exe takes in input

A LiDAR dataset : Exwayz SLAM can process the raw data of various LiDAR sensors from various manufacturers. Learn how to input your dataset by refereing to Supported dataset inputs
A configuration file, this is what we call a profile. Learn more about the profile mechanism and internal SLAM parameters in Profile mechanism

To run the SLAM on the sample dataset, execute the following commands

exwayz_slam --bag <path/to/sample/bag> --bag-hesai /hesai/pandar_packets --hesai-model PandarXT-32 --d-write 0.1 -o ./slam_session_tutorial --no-date

A 3D viewer will pop-up, showing the SLAM computed as fast as possible on the dataset.

The output will be the slam_session directory (check 2. SLAM session structure if not already done).

Once the SLAM is over, the SLAM session should be structured as follow :

📂 slam_session_<hour>_<date>

📂 frames
📂 log

traj_odometry.ply ****# Odometry trajectory computed by the SLAM

<aside> 💡 If you’re interested in using the traj_odometry.ply, don’t hesitate check Exwayz PLY trajectory format!

</aside>

Optional parameters

`--d-write`	Allow to write frames only after a minimum motion of `--d-write` . This is useful for saving disk space and not writing redundant data, when the sensor is stationnary for instance.
`-o`	Specify the output directory path. The date in format yyyy-MM-dd-hh-mm-ss is appended to the directory name.
`--no-date`	Disable the appending of the date at the end of the SLAM session name

Well done!

Once you’ve completed the first SLAM step, go the next tutorial : 4. Close the loops

FAQ

How do I run the SLAM on my dataset, which was not recorded as in the sample dataset?