No version for distro humble showing github. Known supported distros are highlighted in the buttons above.

autoware_lidar_centerpoint package from autoware_universe repo

autoware_agnocast_wrapper autoware_auto_common autoware_boundary_departure_checker autoware_component_interface_specs_universe autoware_component_interface_tools autoware_component_interface_utils autoware_cuda_dependency_meta autoware_fake_test_node autoware_glog_component autoware_goal_distance_calculator autoware_grid_map_utils autoware_path_distance_calculator autoware_polar_grid autoware_time_utils autoware_traffic_light_recognition_marker_publisher autoware_traffic_light_utils autoware_universe_utils tier4_api_utils autoware_autonomous_emergency_braking autoware_collision_detector autoware_control_command_gate autoware_control_performance_analysis autoware_control_validator autoware_external_cmd_selector autoware_joy_controller autoware_lane_departure_checker autoware_mpc_lateral_controller autoware_obstacle_collision_checker autoware_operation_mode_transition_manager autoware_pid_longitudinal_controller autoware_predicted_path_checker autoware_pure_pursuit autoware_shift_decider autoware_smart_mpc_trajectory_follower autoware_spheric_collision_detector autoware_stop_mode_operator autoware_trajectory_follower_base autoware_trajectory_follower_node autoware_vehicle_cmd_gate autoware_tensorrt_vad autoware_control_evaluator autoware_evaluation_adapter autoware_kinematic_evaluator autoware_localization_evaluator autoware_perception_online_evaluator autoware_planning_evaluator autoware_scenario_simulator_v2_adapter autoware_diagnostic_graph_test_examples autoware_geo_pose_projector autoware_ar_tag_based_localizer autoware_landmark_manager autoware_lidar_marker_localizer autoware_localization_error_monitor autoware_pose2twist autoware_pose_covariance_modifier autoware_pose_estimator_arbiter autoware_pose_instability_detector yabloc_common yabloc_image_processing yabloc_monitor yabloc_particle_filter yabloc_pose_initializer autoware_map_tf_generator autoware_bevfusion autoware_bytetrack autoware_camera_streampetr autoware_cluster_merger autoware_compare_map_segmentation autoware_crosswalk_traffic_light_estimator autoware_detected_object_feature_remover autoware_detected_object_validation autoware_detection_by_tracker autoware_elevation_map_loader autoware_euclidean_cluster autoware_ground_segmentation autoware_ground_segmentation_cuda autoware_image_object_locator autoware_image_projection_based_fusion autoware_lidar_apollo_instance_segmentation autoware_lidar_centerpoint autoware_lidar_frnet autoware_lidar_transfusion autoware_map_based_prediction autoware_multi_object_tracker autoware_object_merger autoware_object_range_splitter autoware_object_sorter autoware_object_velocity_splitter autoware_occupancy_grid_map_outlier_filter autoware_predicted_path_postprocessor autoware_probabilistic_occupancy_grid_map autoware_ptv3 autoware_radar_fusion_to_detected_object autoware_radar_object_tracker autoware_radar_tracks_msgs_converter autoware_raindrop_cluster_filter autoware_shape_estimation autoware_simpl_prediction autoware_simple_object_merger autoware_tensorrt_bevdet autoware_tensorrt_bevformer autoware_tensorrt_classifier autoware_tensorrt_common autoware_tensorrt_plugins autoware_tensorrt_yolox autoware_tracking_object_merger autoware_traffic_light_arbiter autoware_traffic_light_category_merger autoware_traffic_light_classifier autoware_traffic_light_fine_detector autoware_traffic_light_map_based_detector autoware_traffic_light_multi_camera_fusion autoware_traffic_light_occlusion_predictor autoware_traffic_light_selector autoware_traffic_light_visualization perception_utils autoware_costmap_generator autoware_diffusion_planner autoware_external_velocity_limit_selector autoware_freespace_planner autoware_freespace_planning_algorithms autoware_hazard_lights_selector autoware_manual_lane_change_handler autoware_mission_planner_universe autoware_path_optimizer autoware_path_smoother autoware_remaining_distance_time_calculator autoware_rtc_interface autoware_scenario_selector autoware_surround_obstacle_checker autoware_trajectory_adapter autoware_trajectory_concatenator autoware_trajectory_modifier autoware_trajectory_optimizer autoware_trajectory_ranker autoware_trajectory_safety_filter autoware_trajectory_traffic_rule_filter autoware_behavior_path_avoidance_by_lane_change_module autoware_behavior_path_bidirectional_traffic_module autoware_behavior_path_dynamic_obstacle_avoidance_module autoware_behavior_path_external_request_lane_change_module autoware_behavior_path_goal_planner_module autoware_behavior_path_lane_change_module autoware_behavior_path_planner autoware_behavior_path_planner_common autoware_behavior_path_sampling_planner_module autoware_behavior_path_side_shift_module autoware_behavior_path_start_planner_module autoware_behavior_path_static_obstacle_avoidance_module autoware_behavior_velocity_blind_spot_module autoware_behavior_velocity_crosswalk_module autoware_behavior_velocity_detection_area_module autoware_behavior_velocity_intersection_module autoware_behavior_velocity_no_drivable_lane_module autoware_behavior_velocity_no_stopping_area_module autoware_behavior_velocity_occlusion_spot_module autoware_behavior_velocity_roundabout_module autoware_behavior_velocity_rtc_interface autoware_behavior_velocity_speed_bump_module autoware_behavior_velocity_template_module autoware_behavior_velocity_traffic_light_module autoware_behavior_velocity_virtual_traffic_light_module autoware_behavior_velocity_walkway_module autoware_motion_velocity_boundary_departure_prevention_module autoware_motion_velocity_dynamic_obstacle_stop_module autoware_motion_velocity_obstacle_cruise_module autoware_motion_velocity_obstacle_slow_down_module autoware_motion_velocity_obstacle_velocity_limiter_module autoware_motion_velocity_out_of_lane_module autoware_motion_velocity_road_user_stop_module autoware_motion_velocity_run_out_module autoware_planning_validator autoware_planning_validator_intersection_collision_checker autoware_planning_validator_latency_checker autoware_planning_validator_rear_collision_checker autoware_planning_validator_test_utils autoware_planning_validator_trajectory_checker autoware_bezier_sampler autoware_frenet_planner autoware_path_sampler autoware_sampler_common autoware_calibration_status_classifier autoware_cuda_pointcloud_preprocessor autoware_cuda_utils autoware_image_diagnostics autoware_image_transport_decompressor autoware_imu_corrector autoware_pcl_extensions autoware_pointcloud_preprocessor autoware_radar_objects_adapter autoware_radar_scan_to_pointcloud2 autoware_radar_static_pointcloud_filter autoware_radar_threshold_filter autoware_radar_tracks_noise_filter autoware_livox_tag_filter autoware_carla_interface autoware_dummy_perception_publisher autoware_fault_injection autoware_learning_based_vehicle_model autoware_simple_planning_simulator autoware_vehicle_door_simulator tier4_dummy_object_rviz_plugin autoware_bluetooth_monitor autoware_command_mode_decider autoware_command_mode_decider_plugins autoware_command_mode_switcher autoware_command_mode_switcher_plugins autoware_command_mode_types autoware_component_monitor autoware_component_state_monitor autoware_adapi_visualizers autoware_automatic_pose_initializer autoware_default_adapi_universe autoware_diagnostic_graph_aggregator autoware_diagnostic_graph_utils autoware_dummy_diag_publisher autoware_dummy_infrastructure autoware_duplicated_node_checker autoware_hazard_status_converter autoware_mrm_comfortable_stop_operator autoware_mrm_emergency_stop_operator autoware_mrm_handler autoware_pipeline_latency_monitor autoware_processing_time_checker autoware_system_monitor autoware_topic_relay_controller autoware_topic_state_monitor autoware_velodyne_monitor autoware_accel_brake_map_calibrator autoware_external_cmd_converter autoware_raw_vehicle_cmd_converter autoware_steer_offset_estimator autoware_bag_time_manager_rviz_plugin autoware_traffic_light_rviz_plugin tier4_adapi_rviz_plugin tier4_camera_view_rviz_plugin tier4_control_mode_rviz_plugin tier4_datetime_rviz_plugin tier4_manual_lane_change_rviz_plugin tier4_perception_rviz_plugin tier4_planning_factor_rviz_plugin tier4_state_rviz_plugin tier4_traffic_light_rviz_plugin tier4_vehicle_rviz_plugin

ROS Distro
github

API Docs
Browse Code

Package Summary

Version	0.50.0
License	Apache License 2.0
Build type	AMENT_CMAKE
Use	RECOMMENDED

Repository Summary

Description
Checkout URI	https://github.com/autowarefoundation/autoware_universe.git
VCS Type	git
VCS Version	main
Last Updated	2026-02-25
Dev Status	UNKNOWN
Released	UNRELEASED
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The autoware_lidar_centerpoint package

Maintainers

Kenzo Lobos-Tsunekawa
Amadeusz Szymko
Kotaro Uetake
Masato Saeki
Taekjin Lee
Kok Seang Tan

Authors

No additional authors.

perception/autoware_lidar_centerpoint/README.md

autoware_lidar_centerpoint

Purpose

autoware_lidar_centerpoint is a package for detecting dynamic 3D objects.

Inner-workings / Algorithms

In this implementation, CenterPoint [1] uses a PointPillars-based [2] network to inference with TensorRT.

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

Inputs / Outputs

Input

Name	Type	Description
`~/input/pointcloud`	`sensor_msgs::msg::PointCloud2`	input pointcloud

Output

Name	Type	Description
`~/output/objects`	`autoware_perception_msgs::msg::DetectedObjects`	detected objects
`debug/cyclic_time_ms`	`autoware_internal_debug_msgs::msg::Float64Stamped`	cyclic time (msg)
`debug/processing_time_ms`	`autoware_internal_debug_msgs::msg::Float64Stamped`	processing time (ms)

Parameters

ML Model Parameters

Note that these parameters are associated with ONNX file, predefined during the training phase. Be careful to change ONNX file as well when changing this parameter. Also, whenever you update the ONNX file, do NOT forget to check these values.

{{ json_to_markdown(“perception/autoware_lidar_centerpoint/schema/centerpoint_ml_package.schema.json”) }}

Core Parameters

Name	Type	Default Value	Description
`encoder_onnx_path`	string	`""`	path to VoxelFeatureEncoder ONNX file
`encoder_engine_path`	string	`""`	path to VoxelFeatureEncoder TensorRT Engine file
`head_onnx_path`	string	`""`	path to DetectionHead ONNX file
`head_engine_path`	string	`""`	path to DetectionHead TensorRT Engine file
`build_only`	bool	`false`	shutdown the node after TensorRT engine file is built
`trt_precision`	string	`fp16`	TensorRT inference precision: `fp32` or `fp16`
`post_process_params.yaw_norm_thresholds`	list[double]	[0.3, 0.3, 0.3, 0.3, 0.0]	An array of distance threshold values of norm of yaw [rad].
`post_process_params.iou_nms_search_distance_2d`	double	-	If two objects are farther than the value, NMS isn’t applied.
`post_process_params.iou_nms_threshold`	double	-	IoU threshold for the IoU-based Non Maximum Suppression
`post_process_params.has_twist`	boolean	false	Indicates whether the model outputs twist value.
`densification_params.world_frame_id`	string	`map`	the world frame id to fuse multi-frame pointcloud
`densification_params.num_past_frames`	int	`1`	the number of past frames to fuse with the current frame

The `build_only` option

The autoware_lidar_centerpoint 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_centerpoint lidar_centerpoint.launch.xml model_name:=centerpoint_tiny model_path:=/home/autoware/autoware_data/lidar_centerpoint model_param_path:=$(ros2 pkg prefix autoware_lidar_centerpoint --share)/config/centerpoint_tiny.param.yaml build_only:=true

Assumptions / Known limits

The object.existence_probability is stored the value of classification confidence of a DNN, not probability.

Trained Models

You can download the onnx format of trained models by clicking on the links below.

Centerpoint: pts_voxel_encoder_centerpoint.onnx, pts_backbone_neck_head_centerpoint.onnx
Centerpoint tiny: pts_voxel_encoder_centerpoint_tiny.onnx, pts_backbone_neck_head_centerpoint_tiny.onnx

Centerpoint was trained in nuScenes (~28k lidar frames) [8] and TIER IV’s internal database (~11k lidar frames) for 60 epochs. Centerpoint tiny was trained in Argoverse 2 (~110k lidar frames) [9] and TIER IV’s internal database (~11k lidar frames) for 20 epochs.

Training CenterPoint Model and Deploying to the Autoware

Overview

This guide provides instructions on training a CenterPoint model using the mmdetection3d repository and seamlessly deploying it within Autoware.

Installation

Install prerequisites

Step 1. Download and install Miniconda from the official website.

Step 2. Create a conda virtual environment and activate it

conda create --name train-centerpoint python=3.8 -y
conda activate train-centerpoint

Step 3. Install PyTorch

Please ensure you have PyTorch installed, and compatible with CUDA 11.6, as it is a requirement for current Autoware.

File truncated at 100 lines see the full file

CHANGELOG

Changelog for package autoware_lidar_centerpoint

0.50.0 (2026-02-14)

Merge remote-tracking branch 'origin/main' into humble
feat(autoware_lidar_centerpoint): add distance-based confidence thresholds to CenterPoint (#12026)
- Add temp
- Add score_threshold_upper and score_thresholds to CenterPoint postprocessing
- Fix naming errors
- Revert changes in roi_cluster_fusion_pipeline
- Revert changes in roi_cluster_fusion markdown
- Revert changes in image_projection_based_fusion
- Update score_threshold configs in pointpainting_fusion
- Remove unnecessary comments
- Update float class_score_threshold to const float
- Update autoware_lidar_centerpoint readme
- Remove param_version from configs
- Return postprocessing of boxes if label == -1
- Add the checking of score_upper_bounds greater than 0
- Update score_threshold values to class-wise distance
- Fix pointpainting class-wise distance thresholds
- Update centerpoint params in README by json_to_markdown
- Update docstring comment in centerpoint postprocess
- style(pre-commit): autofix
- Rename configs to detection_score_thresholds with distance_bin_upper_limits and min_confidence_scores
- Update schema docstring
- Resolve missing distance_bin_upper_limits_ in CenterPointConfig
* Update pointpainting ml package schema ---------Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
feat(autoware_lidar_centerpoint): update nvcc flags (#12049)
feat!: remove ROS 2 Galactic codes (#11905)
chore(autoware_lidar_centerpoint): remove cudnn dependency (#11885)
Contributors: Amadeusz Szymko, Kok Seang Tan, Ryohsuke Mitsudome

0.49.0 (2025-12-30)

Merge remote-tracking branch 'origin/main' into prepare-0.49.0-changelog
fix(lidar_centerpoint): correct index check in shufflePoints_kernel (#11711) fix(lidar_centerpoint): correct index check in shufflePoints_kernel function
fix(centerpoint): fix insufficient buffer clearing (#11675)
- fix(lidar_centerpoint): clear auxiliary points buffer in preprocessing
* fix(centerpoint_trt): move cudaStreamCreate to constructor initialization ---------
Contributors: Ryohsuke Mitsudome, Taekjin LEE, jakor97

0.48.0 (2025-11-18)

0.47.1 (2025-08-14)

0.47.0 (2025-08-11)

feat(autoware_lidar_centerpoint): add class-wise confidence thresholds to CenterPoint (#10881)
- Add PreprocessCuda to CenterPoint
- style(pre-commit): autofix
- style(pre-commit): autofix
- Add intensity preprocessing
- style(pre-commit): autofix
- Fix config_.point_feature_size_ typo
- style(pre-commit): autofix
- Fix point typo
- style(pre-commit): autofix
- Change score_threshold to score_thresholds
- Use <autoware/cuda_utils/cuda_utils.hpp> for clear_async
- Rename pre_ptr_ to pre_proc_ptr_
- Remove unused getCacheSize() and getIdx
- Use template in generateVoxels_random_kernel instead
- style(pre-commit): autofix
- Remove references in generateVoxels_random_kernel
- Remove references in generateVoxels_random_kernel
- style(pre-commit): autofix
- Remove generateIntensityFeatures_kernel and add the case of 11 to ENCODER_IN_FEATURE_SIZE for generateFeatures_kernel

File truncated at 100 lines see the full file

Package Dependencies

Deps	Name
	ament_cmake_auto
	ament_cmake_python
	autoware_cmake
	ament_lint_auto
	autoware_lint_common
	autoware_cuda_dependency_meta
	autoware_cuda_utils
	autoware_object_recognition_utils
	autoware_perception_msgs
	autoware_tensorrt_common
	autoware_utils
	cuda_blackboard
	pcl_ros
	rclcpp
	rclcpp_components
	tf2_eigen
	tf2_geometry_msgs
	tf2_sensor_msgs

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_perception_launch
autoware_image_projection_based_fusion

Launch files

launch/lidar_centerpoint.launch.xml
- - input/pointcloud [default: /sensing/lidar/pointcloud]
  - output/objects [default: objects]
  - data_path [default: $(env HOME)/autoware_data]
  - node_name [default: lidar_centerpoint]
  - model_name [default: centerpoint_tiny]
  - model_path [default: $(var data_path)/$(var node_name)]
  - model_param_path [default: $(find-pkg-share autoware_lidar_centerpoint)/config/$(var model_name).param.yaml]
  - ml_package_param_path [default: $(var model_path)/$(var model_name)_ml_package.param.yaml]
  - class_remapper_param_path [default: $(var model_path)/detection_class_remapper.param.yaml]
  - common_param_path [default: $(find-pkg-share autoware_lidar_centerpoint)/config/centerpoint_common.param.yaml]
  - build_only [default: false]
  - use_pointcloud_container [default: false]
  - pointcloud_container_name [default: pointcloud_container]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `autoware_lidar_centerpoint` at Robotics Stack Exchange

API Docs Browse Code

No version for distro jazzy showing github. Known supported distros are highlighted in the buttons above.