Skip to content

refactor(perception): refactor launch file and add parameter file #1336

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

Merged

Conversation

MasatoSaeki
Copy link
Contributor

@MasatoSaeki MasatoSaeki commented Feb 21, 2025

Description

Refactoring the launcher around TLR pipeline.
See this PR for information.

Related link

autowarefoundation/autoware_universe#10186

How was this PR tested?

See this PR for information.

For @yukkysaito and @mitsudome-r as e2e_simulator.launch.xml owner
I checked on AWSIM like below.

 ros2 launch autoware_launch e2e_simulator.launch.xml vehicle_model:=sample_vehicle sensor_model:=awsim_sensor_kit map_path:=/home/masatosaeki/awsim/shinjuku_map/map
Screencast.from.03-01-2025.06.14.58.PM.webm

Notes for reviewers

None.

Effects on system behavior

None.

Signed-off-by: MasatoSaeki <[email protected]>
Copy link

github-actions bot commented Feb 21, 2025

Thank you for contributing to the Autoware project!

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

Please ensure:

Signed-off-by: MasatoSaeki <[email protected]>
@MasatoSaeki MasatoSaeki marked this pull request as ready for review March 1, 2025 14:13
@MasatoSaeki MasatoSaeki added the component:perception Advanced sensor data processing and environment understanding. (auto-assigned) label Mar 1, 2025
Comment on lines 4 to 7
precision: fp16
mean: [123.675, 116.28, 103.53]
std: [58.395, 57.12, 57.375]
backlight_threshold: 0.85
Copy link
Contributor

Choose a reason for hiding this comment

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

I think these apartments should be dependent on the ML model description in the autoware data for the future?
If you agree please add some comment in this file.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I think these apartments should be dependent on the ML model description in the autoware data for the future?

Yes, I think so, but description in onnx file is used as version. So I want to use this function in the future. So now, I only left the comment for causion on 401d504.

ros__parameters:
max_vibration_pitch: 0.01745329251 # -0.5 ~ 0.5 deg
max_vibration_yaw: 0.01745329251 # -0.5 ~ 0.5 deg
max_vibration_height: 0.5 # -0.25 ~ 0.25 m
Copy link
Contributor

Choose a reason for hiding this comment

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

Want better comments around these params.
Parameter name should include absolute or something🫠(not in this pr)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

This mean x < |max_vibration_hoge/2|.
But it is not easy to understand, so I will modify another PR like x < |max_vibration_hoge_abs| (of course, I will modify the logic to make it so.)
What do you think?(It is okay to tell me when another PR is opened)

Signed-off-by: MasatoSaeki <[email protected]>
Copy link
Contributor

@technolojin technolojin left a comment

Choose a reason for hiding this comment

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

LGTM

<arg name="traffic_light_recognition/classification/car/model_path" value="$(var data_path)/traffic_light_classifier/traffic_light_classifier_mobilenetv2_batch_6.onnx"/>
<arg name="traffic_light_recognition/classification/car/label_path" value="$(var data_path)/traffic_light_classifier/lamp_labels.txt"/>
<arg name="traffic_light_recognition/classification/pedestrian/model_path" value="$(var data_path)/traffic_light_classifier/ped_traffic_light_classifier_mobilenetv2_batch_6.onnx"/>
<arg name="traffic_light_recognition/classification/pedestrian/label_path" value="$(var data_path)/traffic_light_classifier/lamp_labels_ped.txt"/>
Copy link
Contributor

Choose a reason for hiding this comment

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

MEMO:
All model paths became launcher arguments and defined at the top of the launcher (here).

@github-actions github-actions bot added the component:map Map creation, storage, and loading. (auto-assigned) label Mar 10, 2025
Signed-off-by: MasatoSaeki <[email protected]>
@MasatoSaeki MasatoSaeki merged commit edcdb79 into autowarefoundation:main Mar 11, 2025
12 checks passed
@MasatoSaeki MasatoSaeki deleted the chore/refactor_tlr_launch branch March 26, 2025 05:52
MasatoSaeki added a commit to tier4/autoware_launch that referenced this pull request May 26, 2025
…towarefoundation#1336)

* fundamental change

Signed-off-by: MasatoSaeki <[email protected]>

* style(pre-commit): autofix

* change params name

Signed-off-by: MasatoSaeki <[email protected]>

* remove param

Signed-off-by: MasatoSaeki <[email protected]>

* integrate model and label path

Signed-off-by: MasatoSaeki <[email protected]>

* for awsim

Signed-off-by: MasatoSaeki <[email protected]>

* add comment

Signed-off-by: MasatoSaeki <[email protected]>

* fix typo

Signed-off-by: MasatoSaeki <[email protected]>

* change param name

Signed-off-by: MasatoSaeki <[email protected]>

* chore

Signed-off-by: MasatoSaeki <[email protected]>

---------

Signed-off-by: MasatoSaeki <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Kenzo Lobos Tsunekawa <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:map Map creation, storage, and loading. (auto-assigned) component:perception Advanced sensor data processing and environment understanding. (auto-assigned) run:build-and-test-differential
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants