wh200720041/floam

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1143 stars · 281 forks observed · 2026-08-28

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

FLOAM is a fast and optimized Lidar Odometry And Mapping (LOAM) implementation for indoor and outdoor localization, modified from LOAM and A-LOAM with computational cost reduced up to 3x. It is a ROS package written in C++ using Ceres Solver and PCL, published at IROS 2021.

Use cases

• real-time lidar odometry for mobile robots
• build 3D maps from lidar point clouds
• localize a robot indoors or outdoors using lidar
• run SLAM on KITTI dataset sequences
• reduce computational cost of A-LOAM
• estimate robot trajectory from lidar scans

When to choose

• you need faster lidar odometry than A-LOAM with comparable or better accuracy
• you work in ROS with Ubuntu and want a ready-to-build catkin package
• you need both odometry and dense mapping from a spinning lidar
• you want GPU-accelerated optimization via Ceres 2.1+

When to avoid

• you need visual-inertial or camera-based SLAM rather than lidar-only
• you are not using ROS or Linux
• you need a maintained product with a permissive license (license is non-standard)
• you need support for solid-state lidars out of the box

Facets

library · maturity stable

robotics computer-vision robotics autonomous-vehicles cpp slam lidar-odometry mapping localization loam point-cloud ros-package ceres-solver pcl optimization algorithms linux ros

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wh200720041/floam")