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

About Image Sensors #149

Open nlnlnl1 opened 2 days ago

nlnlnl1 commented 2 days ago

Hello, thank you very much for sharing your work. I would like to ask if the car is equipped with a depth camera that can detect the following depth images. If there is a depth camera, where should I obtain it? If not, how can I improve the car model? I hope you can give me some advice. Thank you 微信图片_20240701100401

reiniscimurs commented 1 day ago

Hi,

Yes, there is depth camera available as a sensor that is available on the robot. You can use rviz to see available sensors by topic. If it can be used for semantic segmentation, I do not know. You will have to test it for yourself.

nlnlnl1 commented 1 day ago

Hello, I checked the topic on rviz and found the depth camera sensor, 4

but it doesn't seem to be working. I checked the screen and it kept showing completely black 1 Then my terminal has the following information, it seems that the depth camera is not properly configured， 2

When I used the command image_saver to save the topic camera/depth/imageraw, I got the following image, which doesn't seem to be the depth image I wanted. 微信图片_20240701162133 Sorry, I am a beginner in ROS. I am not sure if it is a file configuration issue with the robot, so I would like to ask you about it

reiniscimurs commented 1 day ago

The debug information looks fine. That is just an information output, not a warning or an error.

You should check what the raw information is from the camera topics with rostopic echo. I cannot look into this as I have no way of testing this, but you can try to see some information in ros tutorials: https://classic.gazebosim.org/tutorials/?tut=ros_depth_camera