RKO-SLAM

A ROS2 LiDAR-inertial SLAM system that builds maps from sub-maps, closes loops, and aligns multiple recording sessions into one frame.

Made by Photogrammetry & Robotics Bonn, Germany (checked on github.com/PRBonn (opens in a new tab)).

Licenses

Code: MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 4a85cda (opens in a new tab), on 16 Oct 2026.
Commercial use: Yes

Runs on top of rko_lio LiDAR-inertial odometry, or on any locally consistent odometry publishing odom to base_link on TF.
Launches with autodetection of LiDAR and IMU topics and base frame, or through explicit parameters and config files.
Splits the trajectory into sub-maps and detects loop closures between them, with tunable splitting distance and overlap threshold.
Uses an optional IMU for gravity levelling, reducing height drift on long drives.
Dumps sub-maps, trajectory and pose graph to disk for offline use.
Aligns trajectories from several sessions of the same place into a joint frame and pose graph.

Written by Robotheca from the project's README (opens in a new tab) at commit 4a85cda.

Difficulty: Advanced
Hardware it needs, as the project states it: A LiDAR publishing PointCloud2 with per-point timestamps, and optionally an IMU publishing sensor_msgs/Imu, with the frames linked to a base frame on TF.
How to start: The project's website (opens in a new tab)

Checked on GitHub on 16 Oct 2026.

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.