环境搭建ubuntu20.04.5"/>
AirVO环境搭建ubuntu20.04.5
/
GitHub - xukuanHIT/AirVO: An Illumination-Robust Point-Line Visual Odometry
建议采用docker方式
docker pull xukuanhit/air_slam:v1
//下面指令不需要任何修改,直接运行
docker run -it --env DISPLAY=$DISPLAY
--volume /tmp/.X11-unix:/tmp/.X11-unix
--privileged --runtime nvidia
--gpus all
--volume ${PWD}:/workspace
--workdir /workspace
--name air_slam xukuanhit/air_slam:v1 /bin/bash //进入容器后执行cd ~/catkin_ws/srcgit clone .gitcd ../catkin_makesource ~/catkin_ws/devel/setup.bash
operation system :ubuntu20.04.5
Dependencies:
- OpenCV 4.2 :OpenCV: Installation in Linux
[compiler] sudo apt-get install build-essential
[required] sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
[optional] sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-devcd ~/<my_working_directory>
git clone .git
git clone .git
//move the opencv_contrib-4.2.0 to the directory of opencv-4.2.0
mv opencv_contrib-4.2.0 opencv-4.2.0/cd ~/opencv
mkdir build
cd build//opencv install path is /usr/local/opencv-4.2.0/
cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local/opencv-4.2.0/ ..
make -j7 # runs 7 jobs in parallel
sudo make install#test
git clone .git
<cmake_build_dir>/bin/opencv_test_core
- Eigen 3:Eigen
sudo apt install libeigen3-dev
- G2O:
sudo apt install libsuitesparse-dev qtdeclarative5-dev qt5-qmake libqglviewer-dev-qt5
git clone .git
mkdir build
cd build
cmake ../
make
- TensorRT 8.4:GitHub - NVIDIA/TensorRT: NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
version="8.x.x.x-1+cudax.x"
sudo apt-get install tensorrt-dev=${version}sudo apt-mark hold tensorrt-devsudo apt-get update
sudo apt-get install tensorrt
python3 -m pip install numpy
sudo apt-get install python3-libnvinfer-dev
python3 -m pip install protobuf
sudo apt-get install uff-converter-tf
python3 -m pip install numpy onnx
sudo apt-get install onnx-graphsurgeon
# 验证安装
dpkg -l | grep TensorRT
- CUDA 11.6 :CUDA Toolkit Archive | NVIDIA Developer
cuda卸载:
ru@ru:/usr/local/cuda-12.1/bin$ sudo ./cuda-uninstaller*
CUDA 版本切换:
wget .pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget .6.0/local_installers/cuda-repo-ubuntu2004-11-6-local_11.6.0-510.39.01-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2004-11-6-local_11.6.0-510.39.01-1_amd64.deb
sudo apt-key add /var/cuda-repo-ubuntu2004-11-6-local/7fa2af80.pub
sudo apt-get update
sudo apt-get -y install cuda
The NVIDIA CUDA® Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.
- cuDnn: CUDA Deep Neural Network (cuDNN) | NVIDIA Developer
- python
- onnx
- ROS noetic :noetic/Installation/Ubuntu - ROS Wiki (服务器版本ubuntu20.04)
sudo sh -c '. /etc/lsb-release && echo "deb / `lsb_release -cs` main" > /etc/apt/sources.list.d/ros-latest.list'
sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654
sudo apt update
sudo apt install ros-noetic-desktop-full
sudo apt install ros-noetic-slam-gmapping
#apt search ros-noetic //查看或搜索所有可用的软件包
source /opt/ros/noetic/setup.bash#Bash
echo "source /opt/ros/noetic/setup.bash" >> ~/.bashrc
source ~/.bashrc
#zsh
#echo "source /opt/ros/noetic/setup.zsh" >> ~/.zshrc
#source ~/.zshrc
- Boost
- Glog : GitHub - google/glog: C++ implementation of the Google logging module
git clone .git
cd glog
cmake -S . -B build -G "Unix Makefiles"
cmake --build build
cmake --build build --target test
sudo cmake --build build --target install
- Ceres :Installation — Ceres Solver
# CMake
sudo apt-get install cmake
# google-glog + gflags
sudo apt-get install libgoogle-glog-dev libgflags-dev
# Use ATLAS for BLAS & LAPACK
sudo apt-get install libatlas-base-dev
# Eigen3
sudo apt-get install libeigen3-dev
# SuiteSparse (optional)
sudo apt-get install libsuitesparse-devgit clone
tar zxf ceres-solver-2.1.0.tar.gz
mkdir ceres-bin
cd ceres-bin
cmake ../ceres-solver-2.1.0
make -j3
make test
# Optionally install Ceres, it can also be exported using CMake which
# allows Ceres to be used without requiring installation, see the documentation
# for the EXPORT_BUILD_DIR option for more information.
sudo make install#You can also try running the command line bundling application with one of the #included problems, which comes from the University of Washington’s BAL dataset #[Agarwal].bin/simple_bundle_adjuster ../ceres-solver-2.1.0/data/problem-16-22106-pre.txt
- CMake :Download | CMake
参考博客:
ubuntu查看显卡型号:Ubuntu系统查看显卡型号_桂花很香,旭很美的博客-CSDN博客_nvidia corporation device 2204
.html#2cuda_105?login=from_csdn
Ubuntu系统安装 OpenCV4.2.0_Serinus的博客-CSDN博客_opencv4.2.0安装教程
遇到的问题:
1、ubuntu 由于没有公钥,无法验证下列签名_act50的博客-CSDN博客_a4b469963bf863cc
pip3 install -i evo --upgrade --no-binary evo
pip3 install -i evo --upgrade --no-binary evo
-i : 指定清华的镜像源,速度更快
numpy-1.24.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 类似的whl文件,直接通过 pip3 install fileName 进行安装。
2、对于Could NOT find CUDA (missing: CUDA_TOOLKIT_ROOT_DIR CUDA_INCLUDE_DIRS CUDA_CUDART_LIBRARY) 问题的解决_seaun163的博客-CSDN博客
3、docker: Error response from daemon: Unknown runtime specified nvidia. See ‘docker run --help‘.报错的解决_年少轻与狂的博客-CSDN博客
主要就是这文件格式的问题,这个文件格式要求比较严格,如果有多余空格什么的也容易出错。
(base) ru@ru:~$ cat /etc/docker/daemon.json
{"registry-mirrors": [""],"runtimes": {"nvidia": {"path": "/usr/bin/nvidia-container-runtime","runtimeArgs": []}}
}
然后重新加载,重启docker:我还出现重启docker也没用的情况,最后把电脑重启两次就好了。
root@test:~# systemctl daemon-reload
root@test:~# systemctl restart docker
4、安多个cuda卸载不干净,nvcc -V查到的cuda版本和自己装的版本不一致的情况。
我电脑的cuda版本是12.1,显卡是RTX4080,目前可以正常跑Air_vo。
oot@ru:/home/ru/桌面# nvidia-smi
Thu Mar 16 15:14:15 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 530.30.02 Driver Version: 530.30.02 CUDA Version: 12.1 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4080 L... On | 00000000:01:00.0 Off | N/A |
| N/A 46C P5 30W / 115W| 659MiB / 12282MiB | 7% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------++---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 1176 G /usr/lib/xorg/Xorg 311MiB |
| 0 N/A N/A 1444 G /usr/bin/gnome-shell 91MiB |
| 0 N/A N/A 4236 G /usr/lib/firefox/firefox 160MiB |
| 0 N/A N/A 9782 G ...AAAAAAAACAAAAAAAAAA= --shared-files 24MiB |
| 0 N/A N/A 10151 G ...ures=SpareRendererForSitePerProcess 68MiB |
+---------------------------------------------------------------------------------------+
卸载cuda:
apt purge nvidia-cuda-dev nvidia-cuda-doc nvidia-cuda-toolkit
vim /etc/bash.bashrc
export CUDA_HOME=/usr/local/cuda
export PATH="/usr/local/cuda/bin:$PATH"
export LD_LIBRARY_PATH="/usr/local/cuda/lib64:$LD_LIBRARY_PATH"
source ~/.bashrc
Google了很多办说是有个uninstall 的程序。我装了11.6、12.0、12.1都没有那个卸载程序。
保证nvcc -V查到的版本和安装的版本一致就大概没问题了。
5、catlin_make成功编译之后,运行roslaunch air_vo oivio.launch或其他launch文件还是遇到各种问题:比如super_point 编译失败、 特征点提取失败等等,我目前也不太清楚是什么问题,对super_point不太熟悉。有个办法可以试一试就是删掉catkin_ws/路径下的/build 、/devel文件夹重新编译,再或者直接删掉src文件夹重新mkdir src , git pull 代码,然后编译,我遇到解决不了的报错崩溃的时候,经常用这种办法,很多次都是有用的。
6、将glog的日志打印等级修改为kINFO: vim AirVO/src/super_point.cpp
SuperPoint::SuperPoint(const SuperPointConfig &super_point_config): super_point_config_(super_point_config), engine_(nullptr) {setReportableSeverity(Logger::Severity::kINFO);
}
还有一个bug就是代码没有创建debug文件夹,需要自己创建一下,这样traj.txt才能找到。
OpenCV多版本的问题:
我的 OpenCV安装路径:/usr/local/opencv-4.2.0
1、find_package(OpenCV REQUIRED)
sudo vim ~/.bashrc
文件末尾追加:
export PKG_CONFIG_PATH=/usr/local/opencv-4.2.0/lib/pkgconfig
export LD_LIBRARY_PATH=/usr/local/opencv-4.2.0/lib
查询OpenCV版本:查看opencv 3以及以下版本:
pkg-config --modversion opencv
查看opencv4版本:
pkg-config --modversion opencv4
OpenCV多版本切换修改上述~/.bashrc 文件追加的变量的路径即可。
运行roslaunch air_vo oivio.launch 命令后。出现process[air_vo-2]: started with pid [2146756]
/home/ru/catkin_ws/devel/lib/air_vo/air_vo: error while loading shared libraries: libopencv_calib3d.so.4.2: cannot open shared object file: No such file or directory 。
解决方法:/etc/ld.so.conf.d/opencv.conf 文件如果不存在就创建该文件:文件内容改成opencv的安装目录
ru@ru:/etc/ld.so.conf.d$ cat opencv.conf
/usr/local/opencv-4.2.0
8、OpenCV多版本问题:CMakeLists.txt里面指定了4.2.0版本,但因为之前装过其他版本的OpenCV,没有找到4.2.0版本的OpenCV。就可能出现类似下面的问题。
解决方法:1、卸载残留的其他版本文件:首先,在源码安装build 目录下面执行 sudo make uninstall 。 其次,将安装目录下的文件全部删除。如果源码安装文件已删除,搜索locate libopencv_calib3d.so.407 定位版本所有相关的文件然后删除。
[100%] Linking CXX executable /home/ru/catkin_ws/devel/lib/air_vo/air_vo /usr/bin/ld: warning: libopencv_calib3d.so.407, needed by /home/ru/catkin_ws/devel/lib/libair_vo_lib.so, may conflict with libopencv_calib3d.so.4.2 /usr/bin/ld: warning: libopencv_core.so.407, needed by /home/ru/catkin_ws/devel/lib/libair_vo_lib.so, may conflict with libopencv_core.so.4.2 /usr/bin/ld: warning: libopencv_video.so.4.2, needed by /usr/lib/x86_64-linux-gnu/libopencv_ximgproc.so.4.2.0, may conflict with libopencv_video.so.407 [100%] Built target air_vo
CUDA多版本问题:(Ubuntu 20.04)
1、如果要安装多个版本的CUDA需要先安装低版本的,再安装高版本的CUDA。否则,安装低版本的CUDA时会出现包版本依赖无法安装的情况。
2、在roslaunch 启动 AirVO的过程中出现CUDA initialization failure的问题。具体原因如下图所示:出现问题的原因是因为CUDA driver version 太低导致的。可以通过安装高版本的CUDA driver version 解决。
CUDA Toolkit 12.1 Downloads | NVIDIA Developer
wget .1.0/local_installers/cuda_12.1.0_530.30.02_linux.run
sudo sh cuda_12.1.0_530.30.02_linux.run
通过run file进行安装时不要安装driver,会导致安装失败。run 文件中的数字第12.1.0一个是cuda版本号,第二个530.30.02是对应的驱动版本,驱动安装通过下面的命令:
sudo apt-get install cuda-drivers-530 //530是驱动版本,可以直接更换版本数字进行不同版本的驱动安装
[05/10/2023-16:31:56] [W] [TRT] Unable to determine GPU memory usage
[05/10/2023-16:31:56] [W] [TRT] Unable to determine GPU memory usage
[05/10/2023-16:31:56] [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 34, GPU 0 (MiB)
[05/10/2023-16:31:56] [W] [TRT] CUDA initialization failure with error: 803. Please check your CUDA installation: .html
Error in SuperPoint building
[air_vo-2] process has finished cleanly
log file: /home/ru/.ros/log/1f3322fe-ef0d-11ed-ba9b-7b16572d89c2/air_vo-2*.log
CUDA 版本切换:/usr/local/cuda是软连接,stat cuda 查看指向CUDA的版本
首先,cd /usr/local :然后执行下图中的命令
ru@ru:/usr/local$ sudo rm -rf cuda //首先,删除当前cuda软连接
ru@ru:/usr/local$ sudo ln -s /usr/local/cuda-12.1 /usr/local/cuda //将软连接指向cuda-12.1版本
ru@ru:/usr/local$ stat cuda //确认软连接是否成功指向cuda-12.1版本文件:cuda -> /usr/local/cuda-12.1大小:20 块:0 IO 块:4096 符号链接
设备:10302h/66306d Inode:31589559 硬链接:1
权限:(0777/lrwxrwxrwx) Uid:( 0/ root) Gid:( 0/ root)
最近访问:2023-05-11 10:52:23.962156056 +0800
最近更改:2023-05-11 10:52:23.962156056 +0800
最近改动:2023-05-11 10:52:23.962156056 +0800
创建时间:-
[ 95%] Building CXX object AirVO-Mono/CMakeFiles/air_vo.dir/main.cpp.o
[100%] Linking CXX executable /home/ru/catkin_ws/devel/lib/air_vo/air_vo
/usr/bin/ld: warning: libcublas.so.12, needed by /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8, not found (try using -rpath or -rpath-link)
/usr/bin/ld: warning: libcublasLt.so.12, needed by /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8, not found (try using -rpath or -rpath-link)
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulDescDestroy@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasHgemm@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasCreate_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulDescCreate@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatrixLayoutDestroy@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoCapGetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasGemmEx@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasDestroy_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtDestroy@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSetStream_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulPreferenceSetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasGetMathMode@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulPreferenceCreate@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatrixLayoutSetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSgemm_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoConfigGetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasGemmStridedBatchedEx@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatrixLayoutCreate@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoGetIds@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSetPointerMode_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSetMathMode@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmul@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSasum_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulDescSetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoConfigSetAttribute@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulPreferenceDestroy@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoInit@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtMatmulAlgoCheck@libcublasLt.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSgemmStridedBatched@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasSscal_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasGetPointerMode_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasScopy_v2@libcublas.so.12'
/usr/bin/ld: /lib/x86_64-linux-gnu/libnvinfer_plugin.so.8: undefined reference to `cublasLtCreate@libcublasLt.so.12'
collect2: error: ld returned 1 exit status
make[2]: *** [AirVO-Mono/CMakeFiles/air_vo.dir/build.make:244:/home/ru/catkin_ws/devel/lib/air_vo/air_vo] 错误 1
make[1]: *** [CMakeFiles/Makefile2:569:AirVO-Mono/CMakeFiles/air_vo.dir/all] 错误 2
make: *** [Makefile:141:all] 错误 2
下面是我成功运行的一个命令行输出:
(base) ru@ru:~/catkin_ws$ roslaunch air_vo oivio.launch
... logging to /home/ru/.ros/log/ca5e6626-c3ba-11ed-b1dc-a311c7f96f5d/roslaunch-ru-308172.log
Checking log directory for disk usage. This may take a while.
Press Ctrl-C to interrupt
Done checking log file disk usage. Usage is <1GB.started roslaunch server http://ru:36181/SUMMARY
========PARAMETERS* /air_vo/camera_config_path: /home/ru/catkin_w...* /air_vo/config_path: /home/ru/catkin_w...* /air_vo/dataroot: /home/ru/oivio/MN...* /air_vo/model_dir: /home/ru/catkin_w...* /air_vo/saving_dir: /home/ru/catkin_w...* /air_vo/traj_path: /home/ru/catkin_w...* /rosdistro: noetic* /rosversion: 1.16.0NODES/air_vo (air_vo/air_vo)ROS_MASTER_URI=http://localhost:11311process[air_vo-1]: started with pid [308209]
config_file = /home/ru/catkin_ws/src/AirVO/configs/configs_oivio.yaml
path = /home/ru/oivio/MN_015_GV_01/husky0/cam0/data
[03/16/2023-16:12:54] [I] [TRT] Loaded engine size: 3 MiB
[03/16/2023-16:12:54] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +2, now: CPU 0, GPU 2 (MiB)
i ===== 0
One Frame Processinh Time: 16 ms.
i ===== 1
One Frame Processinh Time: 17 ms.
i ===== 2
One Frame Processinh Time: 17 ms.
i ===== 3
Failed when extracting point features !
One Frame Processinh Time: 15 ms.
i ===== 4
One Frame Processinh Time: 590 ms.
i ===== 5.....i ===== 7465
One Frame Processinh Time: 15 ms.
i ===== 7466
One Frame Processinh Time: 17 ms.
i ===== 7467
One Frame Processinh Time: 18 ms.
i ===== 7468
One Frame Processinh Time: 15 ms.
Save file to /home/ru/catkin_ws/src/AirVO/debug/traj.txt
_keyframe_ids.size = 110
terminate called without an active exception
[air_vo-1] process has died [pid 292872, exit code -6, cmd /home/ru/catkin_ws/devel/lib/air_vo/air_vo __name:=air_vo __log:=/home/ru/.ros/log/ca5e6626-c3ba-11ed-b1dc-a311c7f96f5d/air_vo-1.log].
log file: /home/ru/.ros/log/ca5e6626-c3ba-11ed-b1dc-a311c7f96f5d/air_vo-1*.log
all processes on machine have died, roslaunch will exit
shutting down processing monitor...
... shutting down processing monitor complete
done
更多推荐
AirVO环境搭建ubuntu20.04.5
发布评论