• Install Ubuntu 22.04
• Install ROS2 Humble
• Install Gazebo
• Install gazebo_ros_pkgs by running:

  sudo apt install ros-humble-gazebo-*

• Install PyTorch 2.3.1

pip install -r requirements.txt

• Clone this repository:

  mkdir -p ~/drl_agent_ws/src cd ~/drl_agent_ws/src git clone git@github.com:anurye/DRL-for-Mobile-Robot-Navigation-Using-ROS2.git

• Export the environment variable DRL_AGENT_PACKAGE_PATH:

  echo 'export DRL_AGENT_PACKAGE_PATH=~/drl_agent_ws/src/drl_agent' >> ~/.bashrc source ~/.bashrc

• Install dependencies:

  cd ~/drl_agent_ws rosdep install --from-path src -yi --rosdistro humble

If everything is set up correctly, you can proceed to the training step.

• Build the workspace:

  cd ~/drl_agent_ws colcon build

• Launch the simulation:

  Terminal 1:

  cd ~/drl_agent_ws source install/setup.bash ros2 launch drl_agent_description simulation.launch.py

  Terminal 2:

  cd ~/drl_agent_ws source install/setup.bash ros2 run drl_agent environment.py 

  Terminal 3:

  cd ~/drl_agent_ws source install/setup.bash ros2 run drl_agent train_td7_agent.py

If you have closed the terminals, restart the simulation in Terminal 1 and Terminal 2 as described above.

Terminal 3:

cd ~/drl_agent_ws source install/setup.bash ros2 run drl_agent test_td7_agent.py

Feel free to contribute or ask questions by opening an issue