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

install issue #11

Closed wenzhi-zhang closed 2 years ago

wenzhi-zhang commented 2 years ago

when i successfully install according to the official instructions,I run python3 velodyne_td3.pyto train,but I meet the follow issue and gazebo has not started

image

reiniscimurs commented 2 years ago

Hi,

Please provide more information about your setup. Mainly Ubuntu and ROS versions.

wenzhi-zhang commented 2 years ago

thank you for your prompt reply ubuntu18.04 ros melodic and pytorch 1.10

reiniscimurs commented 2 years ago

That should work out-of-the-box then. I don't see any errors in the terminal either. Is this the first time running the repo? Sometimes, in my experience if you are running it for the first time, you just might need to wait for the model to load for 10 ~ 15 minutes. I am not sure of the reason, but I suspect it is downloading some Gazebo models in the background and waiting for them to be loaded. Try running it and leaving it in this state for some time and see if it loads.

wenzhi-zhang commented 2 years ago

thank you, l will try your suggestion

reiniscimurs commented 2 years ago

Sorry for the confusion. You didn't need to change anything, no need to delete and reinstall the repo. This image shows that your ROS cannot find the repo anymore.

Here are the steps:

  1. Clone the repository
  2. Follow the instructions in the readme
  3. Start the training with python3 velodyne_td3.py (this is how far it got according to the first image)
  4. Wait for some time (let's say 30 min to be sure that all the models have been downloaded in the background)
  5. See if the training has started.
wenzhi-zhang commented 2 years ago

l've got it,thank you very much