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
488 stars 98 forks source link

Odom seems not been published and the map cannot load in RVIZ. #35

Closed 525753936 closed 1 year ago

525753936 commented 1 year ago

Thanks for sharing your great work. Some thing strange happens. There is no error or warning in the terminator when i launch the code "python3 train_velodyne_td3.py" in ''TD3" dir. And I modified the "false" to " true" for the "gui" in empty_world.launch to see if the gazebo works. It turned out the gazebo was working well. But the Rviz still cannot load the map. Here are my outputs and resuts. I would like to ask that could you please give me some suggestions or advice? 1 2 3

reiniscimurs commented 1 year ago

Hi

Can you specify what are the displayed errors in the Rviz? I see you are using ROS Melodic. Did you clone the Melodic version of this repository?

525753936 commented 1 year ago

Hi

Can you specify what are the displayed errors in the Rviz? I see you are using ROS Melodic. Did you clone the Melodic version of this repository?

Thanks for your reply. I found the question is the rp version i used was not compatible with my ROS_Version, i checked it out, and after changing the version of the rp version, this problem has been solved and the rviz runs perfectly. Thank you again for your time and your promising work sincerely.