Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can AWSIM simulates the camera_lidar_fusion perception mode of Autoware.Universe? #254

Open
ZiweiSong96 opened this issue Jan 29, 2024 · 4 comments

Comments

@ZiweiSong96
Copy link

ZiweiSong96 commented Jan 29, 2024

AWSIM quick start demo only use camera for traffic light detection, and the perception mode was selected as "lidar", So I changed the perception mode in launch file and set the traffic light camera sensing topic as the input of 2D camera perception (tensorrt_yolo).
Screenshot from 2024-01-29 18-55-44
Screenshot from 2024-01-29 18-55-09
Screenshot from 2024-01-29 19-01-06
But I found that this cannot work well. So I wonder is that possible for users to simulate the camera_lidar_fusion perception mode in AWSIM?
Thank you for your kind help during this time.

@mackierx111
Copy link
Collaborator

I have not tried it yet. It's a future task.

@ZiweiSong96
Copy link
Author

I wrote a ROS2 node and remapped the camera topic of traffic light classification to the camera perception topic, I found that the yolov function was launched in this way. Maybe this can be used for 2D 3D fusion simulation as an alternative plan.

@l7u7ch
Copy link

l7u7ch commented Jun 10, 2024

I would like to do this too.

@ZiweiSong96

Could you please tell me the code or procedure for the remapping?

@ZiweiSong96
Copy link
Author

I would like to do this too.

@ZiweiSong96

Could you please tell me the code or procedure for the remapping?

It is really a naive solution, if you want to do soo, you can find the repo in my github repositories. Feel free to connect with me anytime.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants