search

Zhefan-Xu / CERLAB-UAV-Autonomy

[CMU] A Versatile and Modular Framework Designed for Autonomous Unmanned Aerial Vehicles [UAVs] (C++/ROS/PX4)
MIT License
295 stars 40 forks source link

dynamic navigation #19

Closed jmwang0117 closed 4 months ago

jmwang0117 commented 5 months ago

Thank you for your excellent work.

During the dynamic navigation process, I want to display the dynamic obstacles in RVIZ in the form of point cloud instead of the current GT Box. How can I do it?

Looking forward to your reply!

Screenshot 2024-06-10 05:45:48

Zhefan-Xu commented 5 months ago

Hi @jmwang0117, thanks for the question. The GT bounding boxes are obtained from the gazebo model states indicating that they are not from the sensor reading. So, it would not be straightforward to get the pointcloud from that data. However, you might be able to do it if you could perform collision checking in Gazebo (which I am not sure how) with each model and find the occupied points within those bounding boxes. Please let me know if you have further questions.