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

Possible for initial pose input for the multi-session mode? #27

Open
WilliamWoo45 opened this issue Oct 26, 2024 · 1 comment
Open

Possible for initial pose input for the multi-session mode? #27

WilliamWoo45 opened this issue Oct 26, 2024 · 1 comment

Comments

@WilliamWoo45
Copy link

Hi @zuhaozou2017,

Thanks for the great work and detailed user guidance!
The multi-session mode indeed has great practical values and solves the long term mapping issues.

However, I'm wondering does LTAOM supports the manual input of initial pose (i.e., transformations) when running the multi-session mode? I found the function addInitialPoseValues and the variable pose_prior, and guess they maybe related to the initial pose.

In some challenging degenerated scenarios, LTAOM may fail to merge the results from two mapping sessions. So the manual input of initial pose maybe of help in such scenarios.

@zuhaozou2017
Copy link
Collaborator

Sorry, this is not supported yet. Generally speaking, pose_prior is related to the first pose in your saved prior pose file during first session (try modify it? not sure). "void addPriorPoses(int pose_index, gtsam::Pose3 pose_prior)" is the key. Please use this function to set your pose prior mannully some where.

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