Skip to content

TBRO ROS2 Node and Odometry Generation#1

Open
hkandir wants to merge 2 commits into
mainfrom
develop
Open

TBRO ROS2 Node and Odometry Generation#1
hkandir wants to merge 2 commits into
mainfrom
develop

Conversation

@hkandir

@hkandir hkandir commented Aug 26, 2024

Copy link
Copy Markdown
Collaborator

Thank you for reviewing the code . This pull request includes odometry generation and ros2 node related sections. The usage of ML model and the odomentry generation is in process_data(self) method.

@hkandir hkandir requested review from Alphakyl and crheckman August 26, 2024 17:04
@hkandir hkandir self-assigned this Aug 26, 2024
hkandir added a commit that referenced this pull request Aug 26, 2024
@hkandir

hkandir commented Aug 26, 2024

Copy link
Copy Markdown
Collaborator Author

I updated the merge request as it shows ros2 and odometry related code. Please let me know if the code needs more explanation. Thank you!

@crheckman crheckman left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've reviewed the pose delta accumulation method. As far as I can tell it looks accurate. The spiral behavior could be as a result of quaternions vs. Euler angles input, or potentially a bias in yaw -- but that would seem like a really strong bias and unlikely to be the case. Are you still seeing that behavior?

@hkandir

hkandir commented Aug 30, 2024

Copy link
Copy Markdown
Collaborator Author

Yes, I still see the spiral behavior. I tested several different input configurations, the direction of the spiral changes, but the odometry is still a form of a spiral. I had a chat with Kyle today, and he said that he saw similar output on his tests.

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

Successfully merging this pull request may close these issues.

2 participants