Ubuntu16.04下turtlebot的DQN算法进行路径规划及其安装运行

环境安装

利用anoconda创建虚拟环境，取名为tensorflow。(最好用anoconda3,取名可随便取)

conda create -n tensorflow pip python=2.7

激活虚拟环境

conda activate tensorflow

安装显卡驱动、cuda、cudnn

conda install cudatoolkit==9.0
conda install cudnn==7.1.2

在虚拟环境中安装tensorflow_gpu=1.8, keras=2.1.6, ros包, 画图工具包等

pip install -U rosinstall msgpack empy defusedxml netifaces
 
pip install --ignore-installed --upgrade https://download.tensorflow.google.cn/linux/gpu/tensorflow_gpu-1.8.0-cp27-none-linux_x86_64.whl
 
pip install keras==2.1.6
 
pip install pyqtgraph
 
conda install pyqt

下载源码包并编译

mkdir -p catkin_ws/src
cd ~/catkin_ws/src/
 
git clone https://github.com/ROBOTIS-GIT/turtlebot3_msgs.git
git clone https://github.com/ROBOTIS-GIT/turtlebot3.git
git clone https://github.com/ROBOTIS-GIT/turtlebot3_simulations.git
git clone https://github.com/ROBOTIS-GIT/turtlebot3_machine_learning.git

若上面４个链接下载慢可用下面４个代替

git clone https://gitee.com/zthcool/turtlebot3_msgs.git
git clone https://gitee.com/zthcool/turtlebot3.git
git clone https://gitee.com/zthcool/turtlebot3_simulations.git
git clone https://gitee.com/oliver_zxh/turtlebot3_machine_learning.git

Make

cd ~/catkin_ws && catkin_make

打开用gedit打开 .bashrc文件

gedit ~/.bashrc

然后在.bashrc文件中添加：

source /home/xxx/catkin_ws/devel/setup.bash
export TURTLEBOT3_MODEL=burger

设置参数并运行

设置参数：
打开源码文件 turtlebot3/turtlebot3_description/urdf/turtlebot3_burger.gazebo.xacro，修改一下两处：

<xacro:arg name="laser_visual" default="false"/>   # 如果想看到激光扫描线,设置成 'true'

<scan>
  <horizontal>
    <samples>360</samples>            # 修改成24
    <resolution>1</resolution>
    <min_angle>0.0</min_angle>
    <max_angle>6.28319</max_angle>
  </horizontal>
</scan>

运行程序

打开一个终端执行如下命令开启仿真环境：

roslaunch turtlebot3_gazebo turtlebot3_stage_1.launch

再打开一个终端执行如下命令启动DQN节点：

conda activate tensorflow
roslaunch turtlebot3_dqn turtlebot3_dqn_stage_1.launch

安装运行问题及解决方法

运行roslaunch turtlebot3_gazebo turtlebot3_stage_1.launch时出现以下错误：

Invalid <arg> tag: environment variable 'TURTLEBOT3_MODEL' is not set.

解决方法：

export TURTLEBOT3_MODEL=burger

运行roslaunch turtlebot3_dqn turtlebot3_dqn_stage_1.launch时出现以下错误：

ImportError: libcublas.so.9.0: cannot open shared object file: No such file or directory Failed to load the native TensorFlow runtime

原因是没有安装cuda,在conda虚拟环境中安装cuda和cudnn:

conda install cudatoolkit==9.0
conda install cudnn==7.1.2

运行roslaunch turtlebot3_dqn turtlebot3_dqn_stage_1.launch时出现以下错误：

rospy.service.ServiceException: transport error completing service call: receive_once[/controller_manager/load_controller]: DeserializationError cannot deserialize: unknown error handler name 'rosmsg

解决方法:在普通环境(不是conda虚拟环境)下执行

sudo apt-get install ros-kinetic-rosmsg 
sudo apt-get install ros-kinetic-genpy

运行roslaunch turtlebot3_dqn result_graph.launch时出现以下错误：

ModuleNotFoundError: No module named 'PyQt5.QtWidgets'

解决方法：

conda install pyqt

以上内容参考链接：
参考的链接