FAST-LIVO2 is a LiDAR-inertial odometry framework and factor-graph SLAM implementation designed for real-time robot localization and 3D mapping. It functions as a multi-sensor fusion pipeline and state estimator that integrates LiDAR, inertial, and camera inputs to track a robot's position and orientation.
The system employs a tightly-coupled sensor fusion approach to maintain stable navigation, particularly in degraded environments. It utilizes a voxel-based 3D mapping tool to organize point clouds into volumetric grids, which optimizes memory usage and search speed during spatial reconstruction.
The framework covers a broad range of capabilities including autonomous robot localization, real-time 3D environment reconstruction, and odometry estimation. These are supported by a processing architecture that incorporates factor graph optimization, Kalman filter state estimation, and iterative closest point matching to resolve sensor drift and contradictions.
