gaoxiang12/lightning-lm

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1632 stars · 330 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Lightning-LM is a C++ library providing a complete 3D LiDAR SLAM system with fast LIO front-end, real-time loop closure detection, and high-precision LiDAR localization. It includes 3D-to-2D map conversion, dynamic map partition loading, and a lightweight incremental optimization library, all running efficiently on CPU.

Use cases

• build a 3D lidar SLAM system for a robot
• localize a vehicle with lidar in real time
• generate 2D grid maps from 3D lidar scans
• run lidar-inertial odometry on low-power CPU hardware
• handle dynamic scenes with separate static and dynamic map layers
• detect and correct loop closures in mapping
• map multi-floor indoor environments

When to choose

• you need a complete, efficient LiDAR mapping and localization stack in C++
• you want real-time loop closure and localization under one CPU core
• you need 2D grid map output from 3D LiDAR data
• you work with large-scale scenes requiring dynamic map partition loading

When to avoid

• you need visual or camera-based SLAM rather than LiDAR
• you need GPS or wheel odometry fusion, which is not yet implemented
• you require a permissively licensed project - no license is specified
• you want a plug-and-play ROS package with extensive documentation

Facets

library · maturity active

simulation computer-vision math concurrency robotics autonomous-vehicles cpp cross-platform slam lidar lio localization mapping point-cloud eskf loop-closure imu robotics-perception algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="gaoxiang12/lightning-lm")