[ktro2828]

What

This PR cherry-picks PRs from exp/pointcloud_semseg_v4.4.

The following PR is also required to merge:

• https://github.com/tier4/autoware_launch.x2/pull/2311

This pull request introduces a new label-based Euclidean clustering node to the autoware_euclidean_cluster package, along with its configuration and launch files. It also implements the previously unimplemented clustering logic for the voxel grid-based method and adds a new object fusion merger node to the autoware_object_merger package. The most important changes are summarized below.

Label-Based Euclidean Clustering Node

• Added a new LabelBasedEuclideanClusterNode implementation, including its header file (label_based_euclidean_cluster_node.hpp), CMake registration, and dependencies on autoware_shape_estimation for shape estimation capabilities. [1] [2] [3] [4]
• Introduced a configuration file (label_based_euclidean_cluster.param.yaml) specifying clustering parameters, semantic label mappings, and shape estimation options.
• Provided launch files (label_based_euclidean_cluster.launch.py and .launch.xml) for starting the new node with configurable arguments for input/output topics and parameters. [1] [2]
• Updated the README with documentation for the new node, its parameters, and behavior regarding label mapping and probability handling. [1] [2]

Voxel Grid-Based Clustering Logic

• Implemented the actual clustering logic for VoxelGridBasedEuclideanCluster::cluster, including voxel grid filtering, 2D centroid clustering, and output filtering based on cluster size.

Object Merger Enhancements

• Added a new ObjectFusionMergerNode to the autoware_object_merger package, including CMake registration, source file addition, and a corresponding configuration YAML. Also included a test for this node. [1] [2] [3]

These changes collectively expand the perception capabilities by enabling label-aware clustering of semantic point clouds and improved object fusion.

[github-actions]

@ktro2828 Thank you for contributing to TIER IV E2E branch! Edit the checklist below and check the boxes as you complete the items.

Things to check before merging

Please check the following points before merging:

• Write a brief description of this PR that can be understood by coding-agents.
• Contact the branch manager on when the PR will be tested on vehicle.
• Recommend to use Squash and Merge to merge the PR.
• Report in #team-product-dev channel on the contents of the PR. @ branch manager.

After merging

Please check the following points after merging:

• Wait for the automatic hash synchronization, which will automatically create a PR to update the hash, you should check the PR and merge it.

[badai-nguyen]

@a-maumau we are going to merger ptv3 pipeline with e2e branch here

[badai-nguyen]

Confirmed launch with "use_semantic_segmentation_ptv3" default="true"

[sonarqubecloud]

Quality Gate passed

Issues
28 New issues
0 Accepted issues

Measures
2 Security Hotspots
0.0% Coverage on New Code
6.3% Duplication on New Code

See analysis details on SonarQube Cloud