search

reiniscimurs / DRL-robot-navigation

Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.
MIT License
571 stars 119 forks source link

Problem with the starting training #94

Closed Ethan0207 closed 5 months ago

Ethan0207 commented 9 months ago

First of all, thank you for your sharing. This a great project .I am trying to train the agent you created with the codes you provided and I did everything as you mentioned. But I have a problem about it. When I start training, it just start only “roscore launched”.I have no idea. Is there something wrong with the environment? 6U1B182 {IIP5) K()B}4DD_tmb

reiniscimurs commented 9 months ago

Hi,

Yes, seems there is an issue with your ros launch. The program should automatically launch roscore and you should see the logs. Which repo version and which ros version are you using?

Ethan0207 commented 9 months ago

Thank you very much for your reply. My ROS version is ROS noetic. But repo has not been installed. Does this need to be installed?

reiniscimurs commented 9 months ago

Repo does not need to be installed, just compiled. It does however have 3 different branches and I would need to know which branch you have cloned.

What seems to be the issue that roscore is not being launched. Can you launch roscore on its own in an empty terminal?

Ethan0207 commented 9 months ago

Thank you for your reply. Firstly, I have cloned "main". And I can launch roscore on its own in an empty terminal branch roscore

reiniscimurs commented 9 months ago

Seems to me that subprocess.Popen(["roscore", "-p", port]) is not working in your setup. You could test it in a dummy script or debug in the current setup.

Alternatively, you can manually start roscore and the gazebo before running the training script.

Ethan0207 commented 9 months ago

Hello，thank you for your reply. These days, I try to solve my problems , but it still has some mistakes .These mistakes are similar to the issue of "Problem with the starting training" mentioned by the friend below. When I try to do it without exporting this commands; export ROS_HOSTNAME=localhost export ROS_MASTER_URI=http://localhost:11311/ export ROS_PORT_SIM=11311 export GAZEBO_RESOURCE_PATH=~/DRL-robot-navigation/catkin_ws/src/multi_robot_scenario/launch source ~/.bashrc cd ~/DRL-robot-navigation/catkin_ws source devel_isolated/setup.bash In my terminal . it says roscore on the top and nothing happens. Ubuntu12 28 1 if I export this In my terminal . it still says roscore on the top and nothing happens. Ubuntu12 28 2 So I am stuck at this point and I can't train the agent . If you can help me with this problem I would be so glad. Thanks in advance. additionally this is my .bashrc file Ubuntu12 28 3