← Projects
completed

LiDAR-Inertial Mapping with FAST-LIO2 and Livox Avia

ROS 2 Humble workspace integrating the Livox Avia LiDAR with FAST-LIO2 for real-time LiDAR-inertial odometry and dense 3D mapping. Fuses LiDAR and IMU data via an incremental k-d tree for efficient, drift-resilient state estimation on Ubuntu 22.04.

ROS 2 LiDAR SLAM State Estimation 3D Mapping Autonomous Robotics
View on GitHub ↗

Overview

This ROS 2 Humble workspace bundles the Livox Avia Ethernet driver and the FAST-LIO2 LiDAR-inertial odometry algorithm into a single, ready-to-run package. The system fuses high-frequency IMU measurements with Livox Avia point clouds to produce real-time 6-DoF pose estimates and a globally consistent 3D map saved as a PCD file on shutdown.

Key Features

  • FAST-LIO2 Integration: Tightly-coupled LiDAR-inertial odometry using an iterated extended Kalman filter (iEKF) for low-drift state estimation
  • ikd-Tree Spatial Indexing: Incremental k-d tree enables efficient point cloud registration without full map rebuilds at each step
  • Livox Avia Driver: Custom ROS 2 driver for the Livox Avia sensor over Ethernet, publishing point cloud and IMU topics
  • Self-Contained SDK: Bundles Livox-SDK as a shared library to avoid system-level library conflicts
  • Rosbag Replay Support: Includes sample rosbag data for hardware-free testing and algorithm validation

Outputs

  • /Odometry — 6-DoF pose estimates in world frame
  • /cloud_registered — accumulated point cloud aligned to world frame
  • PCD map file persisted on node shutdown