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
486 stars 97 forks source link

Gazebo environment（Problems encountered during training） #130

Open Heritagecll opened 2 months ago

Heritagecll commented 2 months ago

Hello! When I started training, it seemed like I was successful, but only rviz appeared without gazebo. Is this normal? rviz I noticed that there are:Unable to register with master node [http://localhost:11311]: master may not be running yet. Will keep trying. Is that the reason? What do I need to do to correct the error? node die

Heritagecll commented 2 months ago

It seems that we can enter the training phase normally. train But I can't see anything through TensorBoard, and I'm not sure if the current situation is correct. tensor Thank you very much for your sharing and help!

reiniscimurs commented 2 months ago

Hi,

Please see the tutorial parts 1 (for tensorboard) and 5 (for gazebo).

Heritagecll commented 2 months ago

Thank you very much for your help. I have resolved these issues. Additionally, I found that the code seems to be unable to run successfully in the virtual environment created by anaconda3, possibly due to conflicting versions of ROS

reiniscimurs commented 2 months ago

You should be able to set any version of ROS you want in a virtual env. For virtual env problems, see other issues on the topic.