hku-mars/FAST_LIO

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5099 stars · 1669 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

FAST-LIO is a computationally efficient and robust LiDAR-inertial odometry package that tightly couples LiDAR feature points with IMU data via an iterated extended Kalman filter. Version 2.0 adds incremental mapping with ikd-Tree and direct raw-point odometry supporting spinning and solid-state LiDARs at over 100Hz.

Use cases

• estimate robot trajectory from LiDAR and IMU data
• build 3D maps in real time on a UAV
• navigate robustly in fast-motion or cluttered environments
• support Livox solid-state and Velodyne/Ouster spinning LiDARs
• use as a LiDAR-inertial front-end for localization or fusion systems

When to choose

• you need real-time, low-latency LiDAR-inertial odometry on embedded hardware
• your platform uses Livox or common spinning LiDARs with an IMU
• you want a well-established, widely cited SLAM front-end for robotics research

When to avoid

• you need visual or multi-sensor fusion out of the box (consider FAST-LIVO or R3LIVE)
• you have no IMU data available
• you require a permissive license (it is GPL-2.0)

Facets

library · maturity stable

robotics computer-vision simulation robotics autonomous-vehicles cpp lidar-inertial-odometry slam kalman-filter ikd-tree livox point-cloud algorithms linux ros

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hku-mars/FAST_LIO")