lidar_localization_ros2

A ROS 2 package that localizes a robot in a prior 3D point-cloud map using LiDAR scan matching, and can serve as the localization source for Nav2.

Licenses

Code: BSD-2-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-2-Clause) at commit fe2b7d9 (opens in a new tab), on 22 Oct 2026.
Commercial use: Yes

Takes a .pcd or .ply point-cloud map and a LiDAR stream, and publishes the robot pose in the map.
Finds the starting pose by itself via a global search, or uses a pose saved for the same map or a manually given pose.
Matches each scan to the map with NDT (default) or GICP, seeded by the last pose and optional odometry or IMU.
Uses optional external odometry to predict motion between scans and carry the pose where matching fails.
Runs standalone, publishing map to base_link, or in Nav2 mode, publishing map to odom.
Includes a quickstart script that prints tracking status and can start RViz.

Written by Robotheca from the project's README (opens in a new tab) at commit fe2b7d9.

Difficulty: Advanced
Hardware it needs, as the project states it: Livox MID-360 or another LiDAR driver with a point cloud stream, optionally an IMU and wheel or leg odometry; ROS 2 Jazzy (Humble supported); builds in about 30 minutes on an 8-core machine. A Docker image is also provided. No GPU requirement is stated.
How to start: The project's README (opens in a new tab)

Status: Active: a commit in the last 90 days
Newest commit: 19 Oct 2026 on main
Latest release: v1.3.0 — Public-bag replay and localization reliability (9 Oct 2026)

Checked on GitHub on 22 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.