Overview

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

API Docs
Browse Code
Wiki

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.

Overview

The Extend Kalman Filter Localizer estimates robust and less noisy robot pose and twist by integrating the 2D vehicle dynamics model with input ego-pose and ego-twist messages. The algorithm is designed especially for fast moving robot such as autonomous driving system.

Flowchart

The overall flowchart of the ekf_localizer is described below.

Features

This package includes the following features:

Time delay compensation for input messages, which enables proper integration of input information with varying time delay. This is important especially for high speed moving robot, such as autonomous driving vehicle. (see following figure).
Automatic estimation of yaw bias prevents modeling errors caused by sensor mounting angle errors, which can improve estimation accuracy.
Mahalanobis distance gate enables probabilistic outlier detection to determine which inputs should be used or ignored.
Smooth update, the Kalman Filter measurement update is typically performed when a measurement is obtained, but it can cause large changes in the estimated value especially for low frequency measurements. Since the algorithm can consider the measurement time, the measurement data can be divided into multiple pieces and integrated smoothly while maintaining consistency (see following figure).

####

Launch

The ekf_localizer starts with the default parameters with the following command.

roslaunch ekf_localizer ekf_localizer.launch

The parameters and input topic names can be set in the ekf_localizer.launch file.

Node

Subscribed Topics

measured_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input pose source with measurement covariance matrix, used when use_pose_with_covariance is true.
measured_twist_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Input twist source with measurement covariance matrix, used when use_twist_with_covariance is true.
measured_pose (geometry_msgs/PoseStamped)

Input pose source, used when use_pose_with_covariance is false.
measured_twist (geometry_msgs/TwistStamped)

Input twist source, used when use_twist_with_covariance is false.
initialpose (geometry_msgs/PoseWithCovarianceStamped)

Initial pose for EKF. The estimated pose is initialized with zeros at start. It is initialized with this message whenever published.

Published Topics

ekf_pose (geometry_msgs/PoseStamped)

Estimated pose.
ekf_pose_with_covariance (geometry_msgs/PoseWithCovarianceStamped)

Estimated pose with covariance.
ekf_twist (geometry_msgs/TwistStamped)

Estimated twist.
ekf_twist_with_covariance (geometry_msgs/TwistWithCovarianceStamped)

Estimated twist with covariance.

Published TF

ekf_pose

TF from “map” coordinate to estimated pose.

Functions

Predict

The current robot state is predicted from previously estimated data using a given prediction model. This calculation is called at constant interval (predict_frequency [Hz]). The prediction equation is described at the end of this page.

File truncated at 100 lines see the full file

CHANGELOG

No CHANGELOG found.

Package Dependencies

Deps	Name
	catkin
	amathutils_lib
	autoware_build_flags
	autoware_msgs
	geometry_msgs
	roscpp
	sensor_msgs
	std_msgs
	tf2
	tf2_ros

System Dependencies

No direct system dependencies.

Dependant Packages

Name	Deps
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch
tier4_localization_launch

Launch files

launch/ekf_localizer.launch
- - show_debug_info [default: false]
  - enable_yaw_bias_estimation [default: True]
  - predict_frequency [default: 50.0]
  - extend_state_step [default: 50]
  - use_pose_with_covariance [default: false]
  - input_pose_name [default: in_pose]
  - input_pose_with_cov_name [default: in_pose_with_covariance]
  - pose_additional_delay [default: 0.0]
  - pose_measure_uncertainty_time [default: 0.01]
  - pose_rate [default: 10.0]
  - pose_gate_dist [default: 10000.0]
  - pose_stddev_x [default: 0.05]
  - pose_stddev_y [default: 0.05]
  - pose_stddev_yaw [default: 0.025]
  - use_twist_with_covariance [default: false]
  - input_twist_name [default: in_twist]
  - input_twist_with_cov_name [default: in_twist_with_covariance]
  - twist_additional_delay [default: 0.0]
  - twist_rate [default: 10.0]
  - twist_gate_dist [default: 10000.0]
  - twist_stddev_vx [default: 0.2]
  - twist_stddev_wz [default: 0.03]
  - proc_stddev_yaw_c [default: 0.005]
  - proc_stddev_yaw_bias_c [default: 0.001]
  - proc_stddev_vx_c [default: 0.1]
  - proc_stddev_wz_c [default: 0.05]

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `ekf_localizer` at Robotics Stack Exchange

API Docs Browse Code Wiki

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

ekf_localizer package from autoware_learn repo

amathutils_lib autoware_build_flags autoware_health_checker emergency_handler gnss lanelet2_extension libvectormap libwaypoint_follower map_file object_map op_planner op_ros_helpers op_simu op_utility ros_observer tvm_utility vector_map vector_map_server vehicle_sim_model autoware_connector ekf_localizer gnss_localizer image_processor imm_ukf_pda_track lidar_apollo_cnn_seg_detect lidar_euclidean_cluster_detect lidar_fake_perception lidar_kf_contour_track lidar_localizer lidar_naive_l_shape_detect lidar_point_pillars lidar_shape_estimation naive_motion_predict ndt_cpu ndt_gpu ndt_tku obj_db pcl_omp_registration pixel_cloud_fusion points_downsampler points_preprocessor pos_db range_vision_fusion road_occupancy_processor roi_object_filter trafficlight_recognizer twist_generator vel_pose_diff_checker vision_beyond_track vision_darknet_detect vision_lane_detect vision_segment_enet_detect vision_ssd_detect astar_search costmap_generator decision_maker dp_planner ff_waypoint_follower freespace_planner lane_planner lattice_planner ll2_global_planner mpc_follower op_global_planner op_local_planner op_simulation_package op_utilities pure_pursuit state_machine_lib twist_filter twist_gate way_planner waypoint_maker waypoint_planner autoware_quickstart_examples autoware_can_msgs autoware_config_msgs autoware_external_msgs autoware_lanelet2_msgs autoware_map_msgs autoware_msgs autoware_system_msgs tablet_socket_msgs vector_map_msgs carla_autoware_bridge gazebo_camera_description gazebo_imu_description lgsvl_simulator_bridge vehicle_gazebo_simulation_interface vehicle_gazebo_simulation_launcher wf_simulator autoware_bag_tools autoware_camera_lidar_calibrator autoware_launcher autoware_launcher_rviz calibration_publisher data_preprocessor graph_tools kitti_box_publisher kitti_launch kitti_player lanelet_aisan_converter log_tools map_tf_generator map_tools marker_downsampler mqtt_socket multi_lidar_calibrator oculus_socket pc2_downsampler rosbag_controller runtime_manager sound_player system_monitor tablet_socket twist2odom udon_socket vehicle_engage_panel vehicle_socket decision_maker_panel detected_objects_visualizer fastvirtualscan gazebo_world_description glviewer integrated_viewer points2image rosinterface autoware_rviz_plugins vehicle_description vehicle_model adi_driver as autoware_driveworks_gmsl_interface autoware_driveworks_interface vlg22c_cam custom_msgs garmin hokuyo javad_navsat_driver kvaser sick_lms5xx memsic_imu microstrain_driver nmea_navsat autoware_pointgrey_drivers sick_ldmrs_description sick_ldmrs_driver sick_ldmrs_laser sick_ldmrs_msgs sick_ldmrs_tools vectacam xsens_driver ymc ds4 ds4_driver ds4_msgs lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation mrt_cmake_modules

ROS Distro
github

API Docs
Browse Code
Wiki

Package Summary

Tags	No category tags.
Version	1.12.0
License	Apache 2.0
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Description	autoware.ai perf
Checkout URI	https://github.com/is-whale/autoware_learn.git
VCS Type	git
VCS Version	1.14
Last Updated	2025-03-14
Dev Status	UNKNOWN
Released	UNRELEASED
Tags	No category tags.
Contributing	Help Wanted (-) Good First Issues (-) Pull Requests to Review (-)

Package Description

The ekf_localizer package

Additional Links

No additional links.

Maintainers

horibe

Authors

No additional authors.