yabloc_pose_initializer

This package contains a node related to initial pose estimation.

• camera_pose_initializer

This package requires the pre-trained semantic segmentation model for runtime. This model is usually downloaded by the ansible artifacts role during the installation. It is also possible to download it manually. Even if the model is not downloaded, initialization will still complete, but the accuracy may be compromised.

The model is hosted on Hugging Face. To download it manually with the hf CLI:

hf download AutowareFoundation/yabloc_pose_initializer --revision v1.0 --local-dir ~/autoware_data/ml_models/yabloc_pose_initializer

Note

This package makes use of external code. The trained files are provided by apollo. The trained files are automatically downloaded during env preparation.

Original model URL

https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/road-segmentation-adas-0001

Open Model Zoo is licensed under Apache License Version 2.0.

Converted model URL

https://github.com/PINTO0309/PINTO_model_zoo/tree/main/136_road-segmentation-adas-0001

model conversion scripts are released under the MIT license

Special thanks

• openvinotoolkit/open_model_zoo
• PINTO0309

camera_pose_initializer

Purpose

• This node estimates the initial position using the camera at the request of ADAPI.

Input

Output

Parameters

{{ json_to_markdown(“localization/yabloc/yabloc_pose_initializer/schema/camera_pose_initializer.schema.json”) }}

Services

Changelog for package yabloc_pose_initializer

0.53.0 (2026-09-29)

• Merge remote-tracking branch 'origin/main' into prepare-0.53.0-changelog

• fix(yabloc): declare the actual service names and shared topics in the node designs (#13292) The align, trigger and switch services are created as ~/<name>, not ~/service/<name>; CameraPoseInitializer also subscribes ~/input/camera_info. weighted_particles is published by both correctors and consumed by the predictor, so it is pinned with global: on all three ports.

• fix(yabloc_pose_initializer): load the ONNX model to survive OpenCV 4.9 (#13206) From OpenCV 4.9 the TensorFlow importer applies the final softmax of model_float32.pb along the width axis, so the node returns an empty mask with no error. The ONNX export of the same network is correct on every version tested, but it declares an NHWC input, so the node needs an NHWC blob and an NHWC output conversion for it. The launch default moves to the ONNX. The .pb path stays for an explicit model_path override.

• docs: replace retired model hosting URLs with Hugging Face links (#13204)

  * docs: replace retired model hosting URLs with Hugging Face links The model artifacts moved from awf.ml.dev.web.auto and the autoware-files S3 bucket to Hugging Face repositories under the AutowareFoundation org (autowarefoundation/autoware#7223). The READMEs still pointed manual downloads at the old hosts, and the yabloc README still gave wget instructions for the retired archive. The two dataset links on the S3 bucket stay: the bucket keeps serving datasets, maps and rosbags. Only the model objects are retired. The centerpoint v0 and v1 files were never migrated and stop being distributed, so their changelog rows lose the download links.

  * docs: name the ML package configs in the model download notes The launch files read transfusion_ml_package.param.yaml and ml_package_camera_streampetr.param.yaml from the model directory. The download notes did not name them, so a manual download missed two required files. ---------

• refactor(localization): move node design files into each package (#13101) Co-authored-by: Claude Opus 5 (1M context) <<noreply@anthropic.com>>

• chore(pre-commit): update clang-format to v22.1.5 (#13126)

  • chore(pre-commit): update clang-format to v22.1.5

  * style(pre-commit): autofix ---------

• docs(yabloc_pose_initializer): fix output topic name in README.md (#13037)

  • update README

  * style(pre-commit): autofix ---------Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>

• Contributors: Kento Yabuuchi, Mete Fatih Cırıt, Ryohsuke Mitsudome, Taekjin LEE

0.52.0 (2026-06-30)

0.51.0 (2026-05-01)

• Merge remote-tracking branch 'origin/main' into tmp/bot/bump_version_base

• feat: default artifact paths to ~/autoware_data/ml_models (#12523) feat(launches,configs): default artifact paths to ~/autoware_data/ml_models Roll every per-package [data_path]{.title-ref} / [model_path]{.title-ref} launch-arg default from [$(env HOME)/autoware_data[/...]]{.title-ref} to [$(env HOME)/autoware_data/ml_models[/...]]{.title-ref} so standalone universe launches resolve artifacts under the new [~/autoware_data/ml_models/]{.title-ref} layout (autowarefoundation/autoware#7068). When invoked through autoware_launch the parent overrides cascade and already pin the new root (autowarefoundation/autoware_launch#1835); this commit closes the gap for users who launch a perception / localization / sensing / planning component directly with [ros2 launch <pkg>]{.title-ref}. 22 launch files updated (one-line default change each):

  • e2e/autoware_tensorrt_vad/launch/vad_carla_tiny.launch.xml
  • localization/yabloc/yabloc_pose_initializer/launch/yabloc_pose_initializer.launch.xml

File truncated at 100 lines see the full file