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

Failed execute Dock Action #9

Open
vanphong97 opened this issue Jun 14, 2022 · 5 comments
Open

Failed execute Dock Action #9

vanphong97 opened this issue Jun 14, 2022 · 5 comments

Comments

@vanphong97
Copy link

My robot could not dock successfully.
The robot oscillates and then stops
Error image and my launch file: https://drive.google.com/drive/folders/17mxb9oIhngnC1gab4QLsPD7fjn2v7lWh?usp=sharing
Can someone help me with it?

@LKSeng
Copy link

LKSeng commented Jun 14, 2022

Without more information on how the robot moves (apart from it oscillates), try setting the number of predock_tf_samples to 1.

This is based on the observation that the robot was initially able to see both markers, but after capturing the first sample, it was not able to to see fiducial_10. So we'll work with 1 sample for now.

Does the "tf" seem to lag behind what the robot camera should be seeing?

@vanphong97
Copy link
Author

My robot still can't dock successfully =((
Is there any documentation that explains what the parameters mean?

@LKSeng
Copy link

LKSeng commented Jun 16, 2022

Looking at the RViz screenshot, and the debug messages from terminal, it looks like the robot base_link to marker is at least 2.6m away. Have you tried to docking at a distance closer to the markers?

It might be camera dependent, but I could not get docking to work reliably from 2.1m away from fiducial with a 1280x720p video.

Most of the explanation of the parameters can be found in the config .yaml file. Otherwise, issue #6 elaborates a few of the parameters.

@vanphong97
Copy link
Author

What is the accuracy of this docking method?
thanks !

@LKSeng
Copy link

LKSeng commented Jul 12, 2022

Off the top of my head, ±2cm for y-coords, and ±1cm for x-coords for a ~1m sized should be doable. Perhaps other users can chime in on their experience with the accuracy as well.

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

2 participants