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

how to compare two bags that one is gt_path and another is recordder path? #1

Open
mohaichuan opened this issue Jun 17, 2022 · 5 comments

Comments

@mohaichuan
Copy link

Great work!Thank you!It gives me great help. I have a question that if i use PathRecorder to record a bag_path.How to compare the bag i record with the gt_bag?Thank you very much!

@haeyeoni
Copy link
Owner

The bag should have path topic. The result path obtained from LiDAR SLAM algorithms can be recorded to bagfile using path_recorder package. After recording the resulting path bagfile, the errors can be calculated relative to gt_bag using the compare.py.

@mohaichuan
Copy link
Author

Thank you.I understand that,use the command '--no_play' to compare two bags,but I can not find the dataset 2011_09_26_0067,which is 03 dataset in your work.Could you find it and share it with me?Thank you very much!

@mohaichuan
Copy link
Author

The sequence traces of 00 , 04 ,06 and 08 I ran cannot be aligned with the truth trace. it cause its APE is very big,and its track graph cannot be aligned.How I to solve these problem?Thank you very much!

@haeyeoni
Copy link
Owner

I think 2011_09_26_0067 should be corrected as 2011_09_26_0027. I will fix that ASAP, thank you! You can download the data with the command that is written in the README.
And could you be more specific about your situation? The possible cause would be the ground truth pose. Please be sure you match the gt pose properly. Or, you can check the results by visualizing the trajectories.

@mohaichuan
Copy link
Author

mohaichuan commented Jun 28, 2022 via email

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