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

fix(autoware_lidar_centerpoint): fix twist covariance orientation #8996

Conversation

technolojin
Copy link
Contributor

@technolojin technolojin commented Oct 1, 2024

Description

Fix the twist covariance converter considering the twist covariance matrix is based on the object coordinate.

Before

Screenshot from 2024-10-01 16-29-22

The twist (velocity) estimation of the centerpoint is based on the base_link frame. The covariance is also the same.
In the shown case, a vehicle in front has velocity negative Y direction to the ego vehicle, and the covariance of the velocity is large in Y direction.
However, the twist covariance is directly inserted to Y coordinate of the object message, and it showed large twist covariance in lateral object velocity.

After

Screenshot from 2024-10-01 16-35-32

The twist covariance is translated to the object coordinate, which is by its definition.
As result, the twist covariance is oriented in Y direction to the ego vehicle, as expected.

NOTE: There is not inference of covariance of XY and YX. The covariance eclipse always oriented in the same direction to the base_link frame.

Related links

Parent Issue:

  • Link

How was this PR tested?

Notes for reviewers

None.

Interface changes

None.

Effects on system behavior

None.

… the twist covariance matrix is based on the object coordinate

Signed-off-by: Taekjin LEE <[email protected]>

fix style
@technolojin technolojin self-assigned this Oct 1, 2024
@github-actions github-actions bot added component:perception Advanced sensor data processing and environment understanding. (auto-assigned) tag:require-cuda-build-and-test labels Oct 1, 2024
Copy link

github-actions bot commented Oct 1, 2024

Thank you for contributing to the Autoware project!

🚧 If your pull request is in progress, switch it to draft mode.

Please ensure:

@technolojin technolojin marked this pull request as ready for review October 1, 2024 07:39
Copy link
Contributor

@yukkysaito yukkysaito left a comment

Choose a reason for hiding this comment

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

LGTM

@technolojin technolojin added the run:build-and-test-differential Mark to enable build-and-test-differential workflow. (used-by-ci) label Oct 1, 2024
Copy link

codecov bot commented Oct 1, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 26.06%. Comparing base (21f547d) to head (4ba2a65).
Report is 18 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main    #8996   +/-   ##
=======================================
  Coverage   26.05%   26.06%           
=======================================
  Files        1315     1315           
  Lines       98503    98475   -28     
  Branches    40113    40095   -18     
=======================================
+ Hits        25668    25669    +1     
+ Misses      70117    70089   -28     
+ Partials     2718     2717    -1     
Flag Coverage Δ *Carryforward flag
differential 3.64% <ø> (?)
total 26.06% <ø> (+0.01%) ⬆️ Carriedforward from 21f547d

*This pull request uses carry forward flags. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link
Contributor

@knzo25 knzo25 left a comment

Choose a reason for hiding this comment

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

LGTM!

note:

Cov_{object} = R^{T} Cov_{ego} R

@technolojin technolojin merged commit 6a24683 into autowarefoundation:main Oct 1, 2024
47 of 48 checks passed
@technolojin technolojin deleted the fix/centerpoint/twist-covariance-orientation branch October 1, 2024 09:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:perception Advanced sensor data processing and environment understanding. (auto-assigned) run:build-and-test-differential Mark to enable build-and-test-differential workflow. (used-by-ci) tag:require-cuda-build-and-test
Projects
No open projects
Development

Successfully merging this pull request may close these issues.

3 participants