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

Gazebo Not publish TF frame /odom and /cmd/vel #69

Closed hzxBuaa closed 1 year ago

hzxBuaa commented 1 year ago

Hi, excuse me, after I changed the robot model, it can’t run normally. I checked all the nodes and topics, and found that node "/gazebo" can’t send "/odom"/ and "/cmd_vel" topics like your original one. How can I solve this question? Thank you in advance!

hzxBuaa commented 1 year ago

Also, I see that you included 'base_link' and 'r1/base_link', what is the difference between these two? In rviz, after I changed the Fixed Frame to 'r1/base_link', I found that the car does not move, but the scene moves, but You can also train normally, no difference, right?

reiniscimurs commented 1 year ago

Please provide full log outputs, Node Graph and TF Tree from rqt of your setup.

Ethan0207 commented 8 months ago

Hello, I have met the same problem. I checked all the nodes and topics, and found that node "/gazebo" can’t send "/odom"/ and "/cmd_vel" topics. Could you tell me how you solved the problem? Thank you