gjcliff/ORB_SLAM3_ROS2

Implementing ORB_SLAM3 in ROS2 humble

35
/ 100
Emerging

This project helps robotics engineers and researchers create detailed 3D maps of environments using real-time camera and IMU data from a D435i RealSense camera. It takes live monocular video and inertial measurements as input, producing a dynamic 3D point cloud and occupancy grid map. This tool is ideal for anyone developing or deploying robots that need to understand and navigate physical spaces autonomously.

Use this if you need to build accurate, real-time 3D maps of an indoor environment with a D435i RealSense camera, or localize existing maps within an ORB_SLAM3 generated map.

Not ideal if you plan to process pre-recorded datasets offline, or require stereo/RGB-D camera inputs, as those modes are not yet fully supported.

robotics SLAM 3D mapping localization autonomous navigation
No License No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

C++

License

Last pushed

Mar 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/gjcliff/ORB_SLAM3_ROS2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.