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

Combine GPS and distance to dected objects to improve localization #458

Open
Lukasnol opened this issue Nov 6, 2024 · 2 comments
Open

Comments

@Lukasnol
Copy link
Collaborator

Lukasnol commented Nov 6, 2024

Detailed Description

Use the distance to recognised objects in combination with the data measured by the GPS to better estimate your own position and thus reduce noise.
First make sure that the distance calculation to recognised objects works well enough.

Definition of Done

  • see description above

Effort Estimate

No response

Testability

No response

Dependencies

No response

@ll7
Copy link
Member

ll7 commented Nov 7, 2024

In my opinion, this issue appears to be very difficult. If I understand you correctly, you would like to use dynamic objects for your localization?

Before you use this approach, I would recommend spending at least a small amout of time looking in to point cloud localization methods. If I am correct, high definition maps of the static buildings should be available. You should be able to use these buildings as reference point. However, filtering #459 would be my first approach.

These are only my thoughts, you can do whatever you like.

@Toni2go Toni2go added the p3 label Nov 7, 2024
@Toni2go
Copy link
Collaborator

Toni2go commented Nov 7, 2024

Yes, we also thought that this issue might be quite difficult and take a lot of time so we are planning on solving the other issues first.
To improve the localization (in particular the estimation of the position) we were planning on using static objects like traffic lights or speed limit signs but buildings as reference points seem to be a good solution as well.

@SirMDA SirMDA removed the p3 label Nov 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Status: No status
Development

No branches or pull requests

4 participants