NVIDIA Jetson Xavier NX部署VINS-fusion-GPU

一、環(huán)境配置（Ubuntu 18.04）

1、Cuda 10.2的安裝

sudo apt-get update
sudo apt-get install cuda-toolkit-10-2

安裝好之后，在 .bashrc中配置環(huán)境變量。source之后，nvcc – version 即可查看cuda版本。

export PATH=/usr/local/cuda-10.2/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export CUDA_ROOT=/usr/local/cuda

2、Eigen（用ROS自帶的也可以）

# Remove pre-built Eigen
 sudo apt-get remove libeigen3-dev 
cd ~/Downloads/
wget -O eigen.zip https://gitlab.com/libeigen/eigen/-/archive/3.3.7/eigen-3.3.7.zip #check version
unzip eigen.zip
mkdir eigen-build && cd eigen-build
cmake ../eigen-3.3.7/ && sudo make install
pkg-config --modversion eigen3 # Check Eigen Version

3、Ceres solver

cd ~/Downloads/
sudo apt-get install -y cmake libgoogle-glog-dev libatlas-base-dev libsuitesparse-dev
wget http://ceres-solver.org/ceres-solver-1.14.0.tar.gz
tar zxf ceres-solver-1.14.0.tar.gz
mkdir ceres-bin
mkdir solver && cd ceres-bin
cmake ../ceres-solver-1.14.0 -DEXPORT_BUILD_DIR=ON -DCMAKE_INSTALL_PREFIX="../solver" 
 
  #good for build without being root privileged and at wanted directory
  
make -j3 # 6 : number of cores
make install
bin/simple_bundle_adjuster ../ceres-solver-1.14.0/data/problem-16-22106-pre.txt # to check version

4、Opencv 安裝

關(guān)于Opencv 的安裝需要特別謹慎，不建議頻繁刪除以前的庫，因為多個項目使用的版本可能不同，所以可以將常用的版本安裝在/usr/local下，將其余版本安裝在自己Download或者home下。
如果需要刪除原來的版本，執(zhí)行以下命令：

# remove prebuilt opencv
sudo apt-get purge libopencv* python-opencv 
sudo apt-get update
sudo apt-get install -y build-essential pkg-config
 
## libeigen3-dev # recommend to build from source
 
sudo apt-get install -y cmake libavcodec-dev libavformat-dev libavutil-dev \
    libglew-dev libgtk2.0-dev libgtk-3-dev libjpeg-dev libpng-dev libpostproc-dev \
    libswscale-dev libtbb-dev libtiff5-dev libv4l-dev libxvidcore-dev \
    libx264-dev qt5-default zlib1g-dev libgl1 libglvnd-dev pkg-config \
    libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev mesa-utils     
 
sudo apt-get install python2.7-dev python3-dev python-numpy python3-numpy

# To fix OpenGL related compilation problems 
 cd /usr/lib/aarch64-linux-gnu/
sudo ln -sf libGL.so.1.0.0 libGL.so
sudo vim /usr/local/cuda/include/cuda_gl_interop.h
 # Comment (line #62~68) of cuda_gl_interop.h 
 //#if defined(__arm__) || defined(__aarch64__)
//#ifndef GL_VERSION
//#error Please include the appropriate gl headers before including cuda_gl_interop.h
//#endif
//#else
 #include <GL/gl.h>
//#endif

安裝新的版本（因為VINS-FUSION-GPU版本需要支持CUda的OpenCV，所以選擇3.4.1版本）
Then once linking is done, go to Downloads to begin opencv installation

cd ~/Downloads/
wget -O opencv.zip https://github.com/opencv/opencv/archive/3.4.1.zip # check version
unzip opencv.zip
cd opencv-3.4.1/ && mkdir build && cd build
cmake -D CMAKE_BUILD_TYPE=RELEASE \
        -D CMAKE_INSTALL_PREFIX=/usr/local \     #這里的/usr/local可以換成自己的安裝路徑，到時候在Cmakelist里設(shè)置自己設(shè)置的路徑即可。
        -D WITH_CUDA=ON \
        -D CUDA_ARCH_BIN=7.2 \     #對于NX和AGX,選7.2，Nano，TX2選6.2 
        -D CUDA_ARCH_PTX="" \
        -D ENABLE_FAST_MATH=ON \
        -D CUDA_FAST_MATH=ON \
        -D WITH_CUBLAS=ON \
        -D WITH_LIBV4L=ON \
        -D WITH_GSTREAMER=ON \
        -D WITH_GSTREAMER_0_10=OFF \
        -D WITH_QT=ON \
        -D WITH_OPENGL=ON \
        -D CUDA_NVCC_FLAGS="--expt-relaxed-constexpr" \
        -D WITH_TBB=ON \
         ../
make  # running in single core is good to resolve the compilation issues         
sudo make install
cd ../../ && sudo rm -rf opencv-3.4.1 # optional (can save 10GB Disk Space)
pkg-config --modversion opencv # Check opencv Version

OpenCV 在NX上的安裝比較慢，差不多需要1個小時。OpenCV安裝好以后，需要進一步編譯CV-Bridge( cv_bridge是在ROS圖像消息和OpenCV圖像之間進行轉(zhuǎn)換的一個功能包)。

5、CV-Bridge的編譯

CV-Bridge的安裝需要下載對應的版本，由于NX 是基于Ubuntu 18.04的ARM系統(tǒng),因此下載melodic版本的CV-Bridge。首先，通過以下連接進入下載頁面：

https://github.com/ros-perception/vision_opencv

如圖所示:

# 選擇下載melodic版本到catkin_ws/src目錄下，
gedit vision_opencv/cv_bridge/CMakeLists.txt
# Edit OpenCV PATHS in CMakeLists and include cmake file
# /usr/local/share/OpenCV 選擇自己安裝的OpenCV對應路徑
find_package(OpenCV 3 REQUIRED PATHS /usr/local/share/OpenCV NO_DEFAULT_PATH 
  COMPONENTS
    opencv_core
    opencv_imgproc
    opencv_imgcodecs
  CONFIG
)
include(/usr/local/share/OpenCV/OpenCVConfig.cmake)  #under catkin_python_setup()
# Save and close CMakeLists
#  Build the package
cd .. && catkin_make

二、Vins-Fusion GPU編譯安裝

1、Vins-Fusion GPU

cd ~/catkin_ws/src && git clone https://github.com/pjrambo/VINS-Fusion-gpu #GPU

sudo apt-get install ros-melodic-tf
sudo apt-get install ros-melodic-image-transport
sudo apt-get install ros-melodic-rviz

# Edit CMakeLists.txt for loop_fusion and vins_estimator
cd ~/catkin_ws/src/VINS-Fusion-gpu/loop_fusion && gedit CMakeLists.txt

##For loop_fusion : line 19
#find_package(OpenCV)
# /usr/local/share/OpenCV/ OpenCVConfig.cmake 選擇自己安裝的OpenCV對應路徑
include(/usr/local/share/OpenCV/OpenCVConfig.cmake)

cd ~/catkin_ws/src/VINS-Fusion-gpu/vins_estimator && gedit CMakeLists.txt

##For vins_estimator : line 20
#find_package(OpenCV REQUIRED)
# /usr/local/share/OpenCV/ OpenCVConfig.cmake 選擇自己安裝的OpenCV對應路徑
include(/usr/local/share/OpenCV/OpenCVConfig.cmake)

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

2、數(shù)據(jù)測試。

2.1公開數(shù)據(jù)集測試【以EuRoC（Stereo cameras + IMU）為例】

 roslaunch vins vins_rviz.launch
    rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_imu_config.yaml 
    (optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_imu_config.yaml 
rosbag play YOUR_DATASET_FOLDER/MH_01_easy.bag

數(shù)據(jù)可以通過一下鏈接下載到：

http://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets
如果下載慢的話，也可以通過以下連接獲取

KITTI
鏈接: https://pan.baidu.com/s/1UIoP1TgGLLWWpKYVrre9WA 密碼: dbsb
EuRoC
鏈接: https://pan.baidu.com/s/1zvxyN1KlIk28_LvC36WU5Q 密碼: f1rv
shapenet
鏈接: https://pan.baidu.com/s/1pdRk3FOxRe5YRBVGP0ACJw 密碼: 4knl
TUM
鏈接: https://pan.baidu.com/s/1GFy8MZmH4TZGakzGWudyhQ 密碼: ptga
數(shù)據(jù)來源原文鏈接：https://blog.csdn.net/weixin_43828675/article/details/117049952（感謝囂張的叉燒包同志）

2.2 測試自己的設(shè)備（D435i+阿木P450）

在配置參數(shù)文件中加入以下參數(shù)，使得GPU起作用

In the config file, there are two parameters for gpu acceleration.
use_gpu: 0 for off, 1 for on
use_gpu_acc_flow: 0 for off, 1 for on
If your GPU resources is limitted or you want to use GPU for other computaion. You can set
use_gpu: 1
use_gpu_acc_flow: 0
If your other application do not require much GPU resources, I recommanded you to set
use_gpu: 1
use_gpu_acc_flow: 1

IMU和相機外參標定可以通過VINS實時在線標定或者使用Kalibr工具包進行標定，相關(guān)資料比多了，不再贅述。

下期給各位鐵子們匯報在阿木實驗室P450上部署VINS+Prometheus+Ggo-Planner的工作。

文獻參考

1、無人機自主導航（ARM架構(gòu)的vins-fusion-GPU部署）

https://blog.csdn.net/weixin_45600405/article/details/125249964?spm=1001.2101.3001.6650.3&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EESLANDING%7Edefault-3-125249964-blog-119830683.pc_relevant_landingrelevant&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EESLANDING%7Edefault-3-125249964-blog-119830683.pc_relevant_landingrelevant&utm_relevant_index=4

2、安裝環(huán)境OpenCV

https://github.com/arjunskumar/vins-fusion-gpu-tx2-nano

3、調(diào)內(nèi)外參數(shù)

https://www.bilibili.com/video/BV1WZ4y167me?p=11&vd_source=1682913523e03074db0225c9475c4c71

4、技術(shù)分享 | 帶你具體部署VINS_FUSION_GPU版本文章來源地址http://www.zghlxwxcb.cn/news/detail-812038.html

https://mp.weixin.qq.com/s/FaE05W2vAvHCZc7R39M7Pw

到了這里，關(guān)于NVIDIA Jetson Xavier NX部署VINS-fusion-GPU的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！