LVI-SAM

Introduction

LVISAM is a framework for tightly-coupled lidar-visual-inertial odometry via smoothing and mapping, that achieves real-time state estimation and map-building with high accuracy and robustness. LVI-SAM is built atop a factor graph and is composed of two sub-systems: a visual-inertial system (VIS) and a lidar-inertial system (LIS). The two sub- systems are designed in a tightly-coupled manner, in which the VIS leverages LIS estimation to facilitate initialization. The accuracy of the VIS is improved by extracting depth information for visual features using lidar measurements. In turn, the LIS utilizes VIS estimation for initial guesses to support scan-matching. Loop closures are first identified by the VIS and further refined by the LIS. LVI-SAM can also function when one of the two sub-systems fails, which increases its robustness in both texture-less and feature-less environments. LVI-SAM is extensively evaluated on datasets gathered from several platforms over a variety of scales and environments. Here are some reference links: code link. paper link.

Image description — Fig. 1. Workflow diagram of LVISAM

2 Compilation Process

2.1 Requirement

ubuntu20.04 、ros-noetic、cmake、gcc、g++、opencv、cv-bridge、eigen、pcl1.10、ceres-solver-1.14.0、gtsam、code、bag。
During the installation of third-party libraries, there may be many version mismatch issues.
Below are just examples of installation.
Please make sure to match the versions, otherwise compilation will have significant problems.
If there are any issues during the appeal process, please search online to resolve them.

install dependence


            sudo apt-get update 

            sudo apt-get install git gcc g++ vim make cmake

install Pangolin


            sudo apt-get install libglew-dev libboost-dev libboost-thread-dev libboost-filesystem-dev 

            sudo apt-get install ffmpeg libavcodec-dev libavutil-dev libavformat-dev libswscale-dev libpng-dev 

            download Pangolin 

            cd Pangolin 

            mkdir build && cd build

            cmake -DCPP11_NO_BOOST=1 .. 

            make 

            sudo make install

install OpenCV


            sudo apt-get install build-essential libgtk2.0-dev libavcodec-dev  

            sudo apt-get install libavformat-dev libjpeg.dev libtiff5.dev  

            sudo apt-get install libswscale-dev libjasper-dev  

            sudo apt-get install libcanberra-gtk-module libcanberra-gtk3-module  

            download opencv 

            cd opencv 

            mkdir build && cd build 

            cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ..

            make 

            sudo make install

install Eigen3


            download Eigen3 

            cd eigen3

            mkdir build && cd build

            cmake ..

            make

            sudo make install

install Ceres


            sudo apt-get install libgoogle-glog-dev libgflags-dev

            sudo apt-get install libatlas-base-dev

            download Ceres 

            mkdir ceres-bin 

            cd ceres-bin 

            cmake ../ceres-solver-1.14.0 

            make  

            sudo make install

install gtsam


            wget -O ~/Downloads/gtsam.zip https://github.com/borglab/gtsam/archive/4.0.0-alpha2.zip

            cd ~/Downloads/ && unzip gtsam.zip -d ~/Downloads/

            cd ~/Downloads/gtsam-4.0.0-alpha2/

            mkdir build && cd build

            cmake ..

            make

            sudo make install

2.2 Build LVI-SAM

Due to the unique IMU ratio and sensor installation external parameters used by the author, many people do not know how to set external parameters if they change datasets or their own devices, and almost all datasets cannot run after changing. Here is a reference link. After the modification, using this code, you only need to configure the external parameters between LiDAR and IMU (T_imu_lidar), the external parameters between Camera and IMU (T_imu_camera), and the properties of IMU itself (which coordinate axis to rotate counterclockwise to output a positive Euler angle), and then you can run LVI-SAM on different devices.

Clone the repository and catkin_make:


            cd ~/catkin_ws/src

            git clone https://github.com/Cc19245/LVI-SAM-Easyused 

            cd ../

            catkin_make

            source ~/catkin_ws/devel/setup.bash

2.3 Run LVI-SAM


            roslaunch lvi_sam xxx.launch

            rosbag play xxxx.bag

Evaluation

Platforms	Sequences	Length(m)	ATE
A Handheld Device	Escalator	77.460	3.382
	MCR normal dark	76.499	0.043
	MCR aggressive 6dof light	100.871	0.073
	Parkway loop night	461.049	26.366
	Forest	130.937	0.060
A UGV	Elevator	39.336	48.131
	Indoor loop	270.674	0.117
	MCR hdr	193.918	0.043
	Street day	2064.475	5.159
	Parkway loop night	461.051	13.805
A QR	Underground	98.312	0.045
	MCR hdr	85.08	0.036
	Forest	108.037	0.053
A UAV	MCR loop light	104.989	LiDARs not supported
A Car	Urban night loop	1807.884	3.258