autoware_lidar_transfusion

Purpose

The autoware_lidar_transfusion package is used for 3D object detection based on lidar data (x, y, z, intensity).

Inner-workings / Algorithms

The implementation bases on TransFusion [1] work. It uses TensorRT library for data process and network inference.

We trained the models using https://github.com/open-mmlab/mmdetection3d.

Inputs / Outputs

Input

Output

Parameters

TransFusion node

{{ json_to_markdown(“perception/autoware_lidar_transfusion/schema/transfusion.schema.dummy.json”) }}

TransFusion model

{{ json_to_markdown(“perception/autoware_lidar_transfusion/schema/transfusion_ml_package.schema.json”) }}

Detection class remapper

{{ json_to_markdown(“perception/autoware_lidar_transfusion/schema/detection_class_remapper.schema.json”) }}

The build_only option

The autoware_lidar_transfusion node has build_only option to build the TensorRT engine file from the ONNX file. Although it is preferred to move all the ROS parameters in .param.yaml file in Autoware Universe, the build_only option is not moved to the .param.yaml file for now, because it may be used as a flag to execute the build as a pre-task. You can execute with the following command:

ros2 launch autoware_lidar_transfusion lidar_transfusion.launch.xml build_only:=true

The log_level option

The default logging severity level for autoware_lidar_transfusion is info. For debugging purposes, the developer may decrease severity level using log_level parameter:

ros2 launch autoware_lidar_transfusion lidar_transfusion.launch.xml log_level:=debug

Assumptions / Known limits

This library operates on raw cloud data (bytes). It is assumed that the input pointcloud message has following format:

[
  sensor_msgs.msg.PointField(name='x', offset=0, datatype=7, count=1),
  sensor_msgs.msg.PointField(name='y', offset=4, datatype=7, count=1),
  sensor_msgs.msg.PointField(name='z', offset=8, datatype=7, count=1),
  sensor_msgs.msg.PointField(name='intensity', offset=12, datatype=2, count=1)
]

This input may consist of other fields as well - shown format is required minimum. For debug purposes, you can validate your pointcloud topic using simple command:

ros2 topic echo <input_topic> --field fields

Trained Models

The model bundle (transfusion.onnx and transfusion_ml_package.param.yaml) is hosted on Hugging Face. The ansible artifacts role downloads it into ~/autoware_data/ml_models/lidar_transfusion.

The model was trained in TIER IV’s internal database (~11k lidar frames) for 50 epochs.

Changelog

(Optional) Error detection and handling

File truncated at 100 lines see the full file

Changelog for package autoware_lidar_transfusion

0.53.0 (2026-09-29)

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

• fix(design): align the perception node designs with the packages they describe (#13339) The lanelet filter components register under the lanelet_filter:: namespace, and the apollo instance segmentation and transfusion nodes are built with the autoware_ prefix on the executable name. BEVFusion, StreamPetr and LidarFRNet name param file defaults that resolve to nothing: the first two are missing the config/ prefix, and the three files LidarFRNet names are called frnet.param.yaml, ml_package_frnet_ot128.param.yaml and diagnostics_frnet.param.yaml. ElevationMapLoader pins its map_hash input with global:, which keeps the port out of the design graph: link_manager skips any connection whose target is a global input port and the exporter emits no remap. remap_target: keeps the same fixed topic name while letting the port take part in the graph.

• refactor(lidar-transfusion): replace NMS with perception_utils::IouBevNms (#13176) refactor: replace NMS with perception_utils::IouBevNms

• 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(autoware_universe): use autoware_ament_auto_package in perception DNN packages (#12277) Co-authored-by: github-actions <<github-actions@github.com>> Co-authored-by: Taekjin LEE <<taekjin.lee@tier4.jp>>

• Contributors: Kotaro Uetake, Mete Fatih Cırıt, Ryohsuke Mitsudome, Taekjin LEE, Vishal Chauhan

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
  • perception/autoware_bevfusion/launch/bevfusion.launch.xml
  • perception/autoware_camera_streampetr/launch/streampetr.launch.xml
  • perception/autoware_image_projection_based_fusion/launch/pointpainting_fusion.launch.xml
  • perception/autoware_lidar_apollo_instance_segmentation/launch/lidar_apollo_instance_segmentation.launch.xml
  • perception/autoware_lidar_centerpoint/launch/lidar_centerpoint.launch.xml
  • perception/autoware_lidar_frnet/launch/lidar_frnet.launch.xml
  • perception/autoware_lidar_transfusion/launch/lidar_transfusion.launch.xml
  • perception/autoware_ptv3/launch/ptv3.launch.xml
  • perception/autoware_shape_estimation/launch/shape_estimation.launch.xml
  • perception/autoware_simpl_prediction/launch/simpl.launch.xml
  • perception/autoware_tensorrt_bevdet/launch/tensorrt_bevdet.launch.xml
  • perception/autoware_tensorrt_bevformer/launch/bevformer.launch.xml
  • perception/autoware_tensorrt_yolox/launch/{yolox_traffic_light_detector,yolox_tiny,yolox_s_plus_opt}.launch.xml
  • perception/autoware_traffic_light_classifier/launch/{car,pedestrian}_traffic_light_classifier.launch.xml

File truncated at 100 lines see the full file