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

Compatibility and Testing of ROS Melodic Branch #109

Closed HazelFannn closed 3 months ago

HazelFannn commented 5 months ago

Hi,

I've been successfully running the main branch for ROS Noetic and now wish to use the Melodic branch. However, I've encountered issues establishing the simulation properly after several attempts. Could you please confirm:

  1. Has the Melodic branch been thoroughly tested?
  2. Are there any known issues or limitations with this branch?

Thanks for your help!

reiniscimurs commented 5 months ago

Hi,

The melodic branch is deprecated and should be taken "as is" as I will not be able to test it nor update it. It should work out of the box without an issue if set up properly. In principle it is the same code as in Noetic version and was tested when implemented. However, if you encounter any issues I would probably not be able to help as I am not planning on supporting it and it is here for legacy reasons.

HazelFannn commented 5 months ago

Thank you very much for the reply! I will try to adjust my setup again.