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

Could you please provide some suggestions on how to adjust parameters on KITTI dataset? #4

Closed
edward456 opened this issue Dec 29, 2020 · 3 comments

Comments

@edward456
Copy link

Hi, yue pan,

Thank you very much for sharing your code! Your work is awesome, which gives me a lot of inspiration. However, when I try to test KITTI00 data and run your code with your configuration (lo_gflag_list_kitti_urban.txt). I cannot obtain same results as you presented. Meanwhile, It seems that I cannot achieve real-time performance when testing your code. I think there must be something wrong with my configuration. However, I didn't change anything. Do you know the potential reasons? Thank you very much for your help!

Here is the odometry result

kitti00_odometry

Here is the SLAM result with loop closure

kitti00_odometry_loop

Thank you very much!

@YuePanEdward
Copy link
Owner

Thanks a lot for your feedback.
I wonder if your KITTI 00 data is the un-distorted data or the raw data. If the motion compensation has not been done yet, the LiDAR odometry may have some problem.

Here's my result using the KITTI 00 un-distorted data with the configuration file provided in this repository (lo_gflag_list_kitti_urban.txt):

Here is the odometry result
lidar_odom_kitti_00

Here is the SLAM result with loop closure
mulls_slam_kitti_00

@edward456
Copy link
Author

Thanks for your quick reply! Yes, you are right! The results are pretty good. Congratulations!

@kefa27
Copy link

kefa27 commented Aug 9, 2022

This post is quite helpful. I would like to ask which of the motion_compensation_method was chosen to get these results? (0: disabled, 1: uniform motion model, 2: from azimuth, 3: imu-assisted)
Thanks!

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