FAST-LIVO2

改进内容

1. 将sophus1.24.6和vikit整合至项目内，现在不再需要安装这两项依赖
2. 添加了LRU内存管理，控制内存增长速度
3. 使用谷歌风格对部分变量函数等进行了重命名，添加了部分注释
4. 引入了glog和gflags（可按照后续步骤安装），在程序崩溃时可以便捷地找到出错的位置，便于调试，同时便于外部参数输入
5. 添加了glibc malloc内存分配优化，避免长时间占用空闲内存(2025-09-03新增)
6. 删去了LO模式和若干冗余变量，主要处理流程更加清晰(2025-09-03新增)

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

📢 News

• 🔓 2025-01-23: Code released!
• 🎉 2024-10-01: Accepted by T-RO '24!
• 🚀 2024-07-02: Conditionally accepted.

📬 Contact

For further inquiries or assistance, please contact [email protected].

1. Introduction

FAST-LIVO2 is an efficient and accurate LiDAR-inertial-visual fusion localization and mapping system, demonstrating significant potential for real-time 3D reconstruction and onboard robotic localization in severely degraded environments.

Developer: Chunran Zheng 郑纯然

1.1 Related video

Our accompanying video is now available on Bilibili and YouTube.

1.2 Related paper

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

FAST-LIVO2 on Resource-Constrained Platforms

FAST-LIVO: Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry

FAST-Calib: LiDAR-Camera Extrinsic Calibration in One Second

1.3 Our hard-synchronized equipment

We open-source our handheld device, including CAD files, synchronization scheme, STM32 source code, wiring instructions, and sensor ROS driver. Access these resources at this repository: LIV_handhold.

1.4 Our associate dataset: FAST-LIVO2-Dataset

Our associate dataset FAST-LIVO2-Dataset used for evaluation is also available online.

1.5 Our LiDAR-camera calibration method

The FAST-Calib toolkit is recommended. Its output extrinsic parameters can be directly filled into the YAML file.

2. Prerequisited

2.1 Ubuntu and ROS

Ubuntu 18.04~20.04. ROS Installation.

2.2 PCL && Eigen && OpenCV

PCL>=1.8, Follow PCL Installation.

Eigen>=3.3.4, Follow Eigen Installation.

OpenCV>=4.2, Follow Opencv Installation.

3. Build

Clone the repository and catkin_make:

cd ~/catkin_ws/src
git clone https://github.com/yqmy0814/FAST-LIVO2

# 安装glog和gflags,已安装则跳过
cd FAST-LIVO2/thirdparty
tar -xvf gflags-2.2.2.tar.gz 
cd gflags-2.2.2 
mkdir build && cd build 
cmake -DBUILD_SHARED_LIBS=ON -DCMAKE_CXX_FLAGS=-fPIC .. 
make -j4 
sudo make install
cd ../..
tar -xvf glog-0.4.0.tar.gz 
cd glog-0.4.0 
mkdir build && cd build 
cmake -DBUILD_SHARED_LIBS=ON .. 
make -j4 
sudo make install

cd ~/catkin_ws
catkin_make
source ~/catkin_ws/devel/setup.bash

4. Run our examples

Download our collected rosbag files via OneDrive (FAST-LIVO2-Dataset).

roslaunch fast_livo mapping_avia.launch
rosbag play YOUR_DOWNLOADED.bag

5. License

The source code of this package is released under the GPLv2 license. For commercial use, please contact me at [email protected] and Prof. Fu Zhang at [email protected] to discuss an alternative license.