No version for distro humble. Known supported distros are highlighted in the buttons above.
No version for distro jazzy. Known supported distros are highlighted in the buttons above.
No version for distro rolling. Known supported distros are highlighted in the buttons above.

behavior_velocity_occlusion_spot_module package from autodrrt repo

autonomous_emergency_braking control_performance_analysis control_validator external_cmd_selector joy_controller lane_departure_checker mpc_lateral_controller obstacle_collision_checker operation_mode_transition_manager pid_longitudinal_controller predicted_path_checker pure_pursuit shift_decider trajectory_follower_base trajectory_follower_node vehicle_cmd_gate diagnostic_converter kinematic_evaluator localization_evaluator planning_evaluator ekf_localizer geo_pose_projector gyro_odometer ar_tag_based_localizer landmark_manager localization_error_monitor localization_util ndt_scan_matcher pose2twist pose_initializer pose_instability_detector stop_filter tree_structured_parzen_estimator twist2accel yabloc_common yabloc_image_processing yabloc_monitor yabloc_particle_filter yabloc_pose_initializer map_height_fitter map_loader map_projection_loader map_tf_generator lanelet2_map_preprocessor ros2_bevdet ros2_bevformer bevfusion bytetrack cluster_merger compare_map_segmentation crosswalk_traffic_light_estimator detected_object_feature_remover detected_object_validation detection_by_tracker elevation_map_loader euclidean_cluster front_vehicle_velocity_estimator ground_segmentation heatmap_visualizer image_projection_based_fusion lidar_apollo_instance_segmentation lidar_apollo_segmentation_tvm lidar_apollo_segmentation_tvm_nodes lidar_centerpoint lidar_centerpoint_tvm map_based_prediction multi_object_tracker object_merger object_range_splitter object_velocity_splitter occupancy_grid_map_outlier_filter probabilistic_occupancy_grid_map radar_crossing_objects_noise_filter radar_fusion_to_detected_object radar_object_clustering radar_object_tracker radar_tracks_msgs_converter shape_estimation simple_object_merger tensorrt_classifier tensorrt_yolo tensorrt_yolox tracking_object_merger traffic_light_arbiter traffic_light_classifier traffic_light_fine_detector traffic_light_map_based_detector traffic_light_multi_camera_fusion traffic_light_occlusion_predictor traffic_light_ssd_fine_detector traffic_light_visualization behavior_path_avoidance_by_lane_change_module behavior_path_avoidance_module behavior_path_external_request_lane_change_module behavior_path_goal_planner_module behavior_path_lane_change_module behavior_path_planner behavior_path_planner_common behavior_path_side_shift_module behavior_path_start_planner_module behavior_velocity_blind_spot_module behavior_velocity_crosswalk_module behavior_velocity_detection_area_module behavior_velocity_intersection_module behavior_velocity_no_drivable_lane_module behavior_velocity_no_stopping_area_module behavior_velocity_occlusion_spot_module behavior_velocity_out_of_lane_module behavior_velocity_planner behavior_velocity_planner_common behavior_velocity_run_out_module behavior_velocity_speed_bump_module behavior_velocity_stop_line_module behavior_velocity_template_module behavior_velocity_traffic_light_module behavior_velocity_virtual_traffic_light_module behavior_velocity_walkway_module costmap_generator external_velocity_limit_selector freespace_planner freespace_planning_algorithms mission_planner motion_velocity_smoother objects_of_interest_marker_interface obstacle_avoidance_planner obstacle_cruise_planner obstacle_stop_planner obstacle_velocity_limiter path_smoother planning_debug_tools planning_test_utils planning_topic_converter planning_validator route_handler rtc_interface rtc_replayer bezier_sampler frenet_planner path_sampler sampler_common scenario_selector static_centerline_optimizer surround_obstacle_checker gnss_poser image_diagnostics image_transport_decompressor imu_corrector livox_tag_filter pointcloud_preprocessor radar_scan_to_pointcloud2 radar_static_pointcloud_filter radar_threshold_filter radar_tracks_noise_filter tier4_pcl_extensions vehicle_velocity_converter autoware_auto_msgs_adapter bluetooth_monitor component_state_monitor default_ad_api ad_api_adaptors ad_api_visualizers automatic_pose_initializer diagnostic_graph_aggregator dummy_diag_publisher dummy_infrastructure duplicated_node_checker emergency_handler mrm_comfortable_stop_operator mrm_emergency_stop_operator system_error_monitor system_monitor topic_state_monitor velodyne_monitor accel_brake_map_calibrator external_cmd_converter raw_vehicle_cmd_converter steer_offset_estimator vehicle_info_util launch launch_ros autoware_ad_api_specs autoware_adapi_v1_msgs autoware_adapi_version_msgs autoware_auto_common autoware_auto_geometry autoware_auto_control_msgs autoware_auto_geometry_msgs autoware_auto_mapping_msgs autoware_auto_msgs autoware_auto_perception_msgs autoware_auto_planning_msgs autoware_auto_system_msgs autoware_auto_vehicle_msgs autoware_auto_perception_rviz_plugin autoware_auto_tf2 autoware_cmake autoware_lint_common autoware_utils lanelet2_extension autoware_common_msgs autoware_control_msgs autoware_localization_msgs autoware_map_msgs autoware_perception_msgs autoware_planning_msgs autoware_sensing_msgs autoware_system_msgs autoware_vehicle_msgs autoware_point_types autoware_testing bag_time_manager_rviz_plugin component_interface_specs component_interface_tools component_interface_utils cuda_utils fake_test_node geography_utils global_parameter_loader glog_component goal_distance_calculator grid_map_utils interpolation kalman_filter motion_utils object_recognition_utils osqp_interface path_distance_calculator perception_utils polar_grid qp_interface rtc_manager_rviz_plugin signal_processing tensorrt_common tier4_adapi_rviz_plugin tier4_api_utils tier4_automatic_goal_rviz_plugin tier4_autoware_utils tier4_calibration_rviz_plugin tier4_camera_view_rviz_plugin tier4_control_rviz_plugin tier4_datetime_rviz_plugin tier4_debug_rviz_plugin tier4_debug_tools tier4_localization_rviz_plugin tier4_perception_rviz_plugin tier4_planning_rviz_plugin tier4_screen_capture_rviz_plugin tier4_simulated_clock_rviz_plugin tier4_state_rviz_plugin tier4_system_rviz_plugin tier4_target_object_type_rviz_plugin tier4_traffic_light_rviz_plugin tier4_vehicle_rviz_plugin time_utils simulator_compatibility_test traffic_light_recognition_marker_publisher traffic_light_utils tvm_utility dma_customer_msg dma_transfer eagleye_coordinate eagleye_navigation eagleye_msgs eagleye_rt eagleye_can_velocity_converter eagleye_fix2kml eagleye_geo_pose_converter eagleye_geo_pose_fusion eagleye_gnss_converter eagleye_tf llh_converter morai_msgs mussp ndt_omp orocos_kdl python_orocos_kdl pointcloud_to_laserscan rtklib_bridge rtklib_msgs autoware_external_api_msgs autoware_iv_external_api_adaptor autoware_iv_internal_api_adaptor awapi_awiv_adapter tier4_api_msgs tier4_auto_msgs_converter tier4_control_msgs tier4_debug_msgs tier4_external_api_msgs tier4_hmi_msgs tier4_localization_msgs tier4_map_msgs tier4_perception_msgs tier4_planning_msgs tier4_rtc_msgs tier4_simulation_msgs tier4_system_msgs tier4_v2x_msgs tier4_vehicle_msgs io_opt tier4_autoware_api_launch tier4_control_launch tier4_localization_launch tier4_map_launch tier4_perception_launch tier4_planning_launch tier4_sensing_launch tier4_simulator_launch tier4_system_launch tier4_vehicle_launch fastrtps cyclonedds lanelet2 lanelet2_core lanelet2_examples lanelet2_io lanelet2_maps lanelet2_matching lanelet2_projection lanelet2_python lanelet2_routing lanelet2_traffic_rules lanelet2_validation sophus angles behaviortree_cpp_v3 bond bond_core bondcpp bondpy smclib test_bond cudnn_cmake_module diagnostic_aggregator diagnostic_common_diagnostics diagnostic_updater diagnostics self_test filters geodesy geographic_info geographic_msgs grid_map grid_map_cmake_helpers grid_map_core grid_map_costmap_2d grid_map_cv grid_map_demos grid_map_filters grid_map_loader grid_map_msgs grid_map_octomap grid_map_pcl grid_map_ros grid_map_rviz_plugin grid_map_sdf grid_map_visualization mrt_cmake_modules nav2_amcl nav2_behavior_tree nav2_behaviors nav2_bringup nav2_bt_navigator nav2_collision_monitor nav2_common nav2_controller nav2_core nav2_costmap_2d costmap_queue dwb_core dwb_critics dwb_msgs dwb_plugins nav2_dwb_controller nav_2d_msgs nav_2d_utils nav2_lifecycle_manager nav2_map_server nav2_msgs nav2_navfn_planner nav2_planner nav2_regulated_pure_pursuit_controller nav2_rotation_shim_controller nav2_rviz_plugins nav2_simple_commander nav2_smac_planner nav2_smoother nav2_system_tests nav2_theta_star_planner nav2_util nav2_velocity_smoother nav2_voxel_grid nav2_waypoint_follower navigation2 dynamic_edt_3d octomap octovis octomap_msgs osqp_vendor pacmod3_msgs pcl_msgs pcl_conversions pcl_ros perception_pcl point_cloud_msg_wrapper radar_msgs can_msgs rqt_tf_tree tensorrt_cmake_module topic_tools topic_tools_interfaces tvm_vendor cv_bridge image_geometry opencv_tests vision_opencv xacro rviz2 rviz_assimp_vendor rviz_common rviz_default_plugins rviz_ogre_vendor rviz_rendering rviz_rendering_tests rviz_visual_testing_framework dummy_perception_publisher fault_injection simple_planning_simulator classformsg node_v2x image_view v4l2_camera can_interface_custom cgi430_can_driver cgi610_driver ARS408_driver data_format_dump data_preprocess_launch lidar_centerpoint_collect lidar_saver message_sync time_cal camera_calibration direct_visual_lidar_calibration multi_lidar_calibration

Package Summary

Tags No category tags.
Version 0.1.0
License Apache License 2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/ieiauto/autodrrt.git
VCS Type git
VCS Version main
Last Updated 2024-09-19
Dev Status UNMAINTAINED
CI status No Continuous Integration
Released UNRELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

The behavior_velocity_occlusion_spot_module package

Additional Links

No additional links.

Maintainers

  • Taiki Tanaka
  • Tomoya Kimura
  • Shumpei Wakabayashi

Authors

  • Taiki Tanaka

Occlusion Spot

Role

This module plans safe velocity to slow down before reaching collision point that hidden object is darting out from occlusion spot where driver can’t see clearly because of obstacles.

brief

Activation Timing

This module is activated if launch_occlusion_spot becomes true. To make pedestrian first zone map tag is one of the TODOs.

Limitation and TODOs

This module is prototype implementation to care occlusion spot. To solve the excessive deceleration due to false positive of the perception, the logic of detection method can be selectable. This point has not been discussed in detail and needs to be improved.

  • Make occupancy grid for planning.
  • Make map tag for occlusion spot.
  • About the best safe motion.

TODOs are written in each Inner-workings / Algorithms (see the description below).

Inner-workings / Algorithms

Logics Working

There are several types of occlusions, such as “occlusions generated by parked vehicles” and “occlusions caused by obstructions”. In situations such as driving on road with obstacles, where people jump out of the way frequently, all possible occlusion spots must be taken into account. This module considers all occlusion spots calculated from the occupancy grid, but it is not reasonable to take into account all occlusion spots for example, people jumping out from behind a guardrail, or behind cruising vehicle. Therefore currently detection area will be limited to to use predicted object information.

Note that this decision logic is still under development and needs to be improved.

DetectionArea Polygon

This module considers TTV from pedestrian velocity and lateral distance to occlusion spot. TTC is calculated from ego velocity and acceleration and longitudinal distance until collision point using motion velocity smoother. To compute fast this module only consider occlusion spot whose TTV is less than TTC and only consider area within “max lateral distance”.

brief

Occlusion Spot Occupancy Grid Base

This module considers any occlusion spot around ego path computed from the occupancy grid. Due to the computational cost occupancy grid is not high resolution and this will make occupancy grid noisy so this module add information of occupancy to occupancy grid map.

TODO: consider hight of obstacle point cloud to generate occupancy grid.

Collision Free Judgement

obstacle that can run out from occlusion should have free space until intersection from ego vehicle

brief

Partition Lanelet

By using lanelet information of “guard_rail”, “fence”, “wall” tag, it’s possible to remove unwanted occlusion spot.

By using static object information, it is possible to make occupancy grid more accurate.

To make occupancy grid for planning is one of the TODOs.

brief

Possible Collision

obstacle that can run out from occlusion is interrupted by moving vehicle.

brief

About safe motion

brief

The Concept of Safe Velocity and Margin

The safe slowdown velocity is calculated from the below parameters of ego emergency braking system and time to collision. Below calculation is included but change velocity dynamically is not recommended for planner.

  • jerk limit[m/s^3]
  • deceleration limit[m/s2]
  • delay response time[s]
  • time to collision of pedestrian[s] with these parameters we can briefly define safe motion before occlusion spot for ideal environment.

    occupancy_grid

This module defines safe margin to consider ego distance to stop and collision path point geometrically. While ego is cruising from safe margin to collision path point, ego vehicle keeps the same velocity as occlusion spot safe velocity.

brief

Note: This logic assumes high-precision vehicle speed tracking and margin for decel point might not be the best solution, and override with manual driver is considered if pedestrian really run out from occlusion spot.

TODO: consider one of the best choices

  1. stop in front of occlusion spot
  2. insert 1km/h velocity in front of occlusion spot
  3. slowdown this way
  4. etc… .
Maximum Slowdown Velocity

The maximum slowdown velocity is calculated from the below parameters of ego current velocity and acceleration with maximum slowdown jerk and maximum slowdown acceleration in order not to slowdown too much.

  • $j_{max}$ slowdown jerk limit[m/s^3]
  • $a_{max}$ slowdown deceleration limit[m/s2]
  • $v_{0}$ current velocity[m/s]
  • $a_{0}$ current acceleration[m/s]

brief

Module Parameters

Parameter Type Description
pedestrian_vel double [m/s] maximum velocity assumed pedestrian coming out from occlusion point.
pedestrian_radius double [m] assumed pedestrian radius which fits in occlusion spot.
Parameter Type Description
use_object_info bool [-] whether to reflect object info to occupancy grid map or not.
use_partition_lanelet bool [-] whether to use partition lanelet map data.
Parameter /debug Type Description
is_show_occlusion bool [-] whether to show occlusion point markers. 
is_show_cv_window bool [-] whether to show open_cv debug window.
is_show_processing_time bool [-] whether to show processing time.
Parameter /threshold Type Description
detection_area_length double [m] the length of path to consider occlusion spot
stuck_vehicle_vel double [m/s] velocity below this value is assumed to stop
lateral_distance double [m] maximum lateral distance to consider hidden collision
Parameter /motion Type Description
safety_ratio double [-] safety ratio for jerk and acceleration
max_slow_down_jerk double [m/s^3] jerk for safe brake
max_slow_down_accel double [m/s^2] deceleration for safe brake
non_effective_jerk double [m/s^3] weak jerk for velocity planning.
non_effective_acceleration double [m/s^2] weak deceleration for velocity planning.
min_allowed_velocity double [m/s] minimum velocity allowed
safe_margin double [m] maximum error to stop with emergency braking system.
Parameter /detection_area Type Description
min_occlusion_spot_size double [m] the length of path to consider occlusion spot
slice_length double [m] the distance of divided detection area
max_lateral_distance double [m] buffer around the ego path used to build the detection_area area.
Parameter /grid Type Description
free_space_max double [-] maximum value of a free space cell in the occupancy grid
occupied_min double [-] buffer around the ego path used to build the detection_area area.

Flowchart

Rough overview of the whole process
@startuml
title modifyPathVelocity (Occupancy/PredictedObject)
start

partition process_path {
:clip path by length;
:interpolate path;
note right
  using spline interpolation and interpolate (x,y,z,v)
end note
:calc closest path point from ego;
}

partition process_sensor_data {
if (road type is PredictedObject) then (yes)
  :preprocess dynamic object;
else if (road type is Occupancy) then (yes)
  :preprocess occupancy grid map info;
else (no)
  stop
endif
}
:calculate offset from start to ego;
partition generate_detection_area_polygon {
:convert path to path lanelet;
:generate left/right slice of polygon that starts from path start;
:generate interpolated polygon created from ego TTC and lateral distance that pedestrian can reach within ego TTC.;
}
partition find_possible_collision {
:generate possible collision;
:calculate collision path point and intersection point;
note right
  - occlusion spot is calculated by the longitudinally closest point of unknown cells.
  - intersection point is where ego front bumper and the darting object will crash.
  - collision path point is calculated by arc coordinate consider ego vehicle's geometry.
  - safe velocity and safe margin is calculated from performance of ego emergency braking system.
end note
:calculate safe velocity and safe margin for possible collision;
note right
  - safe velocity and safe margin is calculated from performance of ego emergency braking system.
end note
}
partition process_possible_collision {
:filter possible collision by road type;
note right
filter by target road type start and end pair
end note
:calculate slow down points for possible collision;
note right
calculate original velocity and height for the possible collision
end note
:handle collision offset;
note right
consider offset from path start to ego vehicle for possible collision
end note
:apply safe velocity comparing with allowed velocity;
note right
calculated by
- safe velocity calculated from emergency brake performance.
- maximum allowed deceleration [m/s^2]
- min velocity [m/s] the velocity that is allowed on the road.
- original_velocity [m/s]
set minimum velocity for path point after occlusion spot.
end note
}
stop
@enduml

Detail process for predicted object(not updated)
@startuml
title modifyPathVelocity
start

partition process_path {
:clip path by length;
note right
  100m considering perception range
end note
:interpolate ego path;
:get closest index from ego position in interpolated path;
:extract target road type start/end distance by arc length;
}
partition preprocess_dynamic_object {
:get parked vehicle from dynamic object array;
note right
  target parked vehicle is define as follow .
  - dynamic object's semantic type is "car","bus","track".
  - velocity is below `stuck_vehicle_vel`.
end note
}
:generate_detection_area_polygon;
partition find_possible_collision {
:generate possible collision behind parked vehicle;
note right
  - occlusion spot candidate is stuck vehicle polygon 2 points farther which is closer to ego path.
end note
:calculate collision path point and intersection point;
note right
  - occlusion spot is calculated by stuck vehicle polygon.
  - intersection point is where ego front bumper and darting object will crash.
  - collision path point is calculated by arc coordinate consider ego vehicle's geometry.
end note
:calculate safe velocity and safe margin for possible collision;
note right
  - safe velocity and safe margin is calculated from performance of ego emergency braking system.
end note
}
partition process_possible_collision {
:filter collision by road type;
:calculate slow down points for possible collision;
:handle collision offset;
:apply safe velocity comparing with allowed velocity;
:insert safe velocity to path;
}
stop
@enduml

Detail process for Occupancy grid base
@startuml
title modifyPathVelocity For Occupancy
start

partition process_path {
:clip path by length;
note right
  50m considering occupancy grid range
end note
:interpolate ego path;
:get closest index from ego position in interpolated path;
}
partition occupancy_grid_preprocess {
:convert occupancy grid to image;
note right
  convert from occupancy grid to image to use opencv functions.
end note
:remove noise from occupancy to apply dilate and erode;
note right
  applying dilate and erode is much better and faster than rule base noise reduction.
end note
:quantize image to categorize to free_space,unknown,occupied;
:convert image to occupancy grid;
note right
  convert from occupancy grid to image to use opencv functions.
end note
}
:generate_detection_area_polygon;
partition generate_possible_collision {
:calculate offset from path start to ego;
:generate possible collision from occlusion spot;
note right
  - occlusion spot candidate is N by N size unknown cells.
  - consider occlusion spot in detection area polygon.
end note
:filter occlusion spot by partition lanelets;
note right
  - filter occlusion spot by partition lanelets which prevent pedestrians come out.
end note
:calculate collision path point and intersection point;
note right
  - use pedestrian polygon to judge "collision_free" or not.
end note
:calculate safe velocity and safe margin for possible collision;
note right
  - safe velocity and safe margin is calculated from the performance of ego emergency braking system.
end note
}
partition handle_possible_collision {
:filter collision by road type;
:calculate slow down points for possible collision;
:handle collision offset;
:apply safe velocity comparing with allowed velocity;
:insert safe velocity to path;
}
stop
@enduml

CHANGELOG
No CHANGELOG found.

Wiki Tutorials

This package does not provide any links to tutorials in it's rosindex metadata. You can check on the ROS Wiki Tutorials page for the package.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged behavior_velocity_occlusion_spot_module at Robotics Stack Exchange

No version for distro noetic. Known supported distros are highlighted in the buttons above.
No version for distro ardent. Known supported distros are highlighted in the buttons above.
No version for distro bouncy. Known supported distros are highlighted in the buttons above.
No version for distro crystal. Known supported distros are highlighted in the buttons above.
No version for distro eloquent. Known supported distros are highlighted in the buttons above.
No version for distro dashing. Known supported distros are highlighted in the buttons above.
No version for distro galactic. Known supported distros are highlighted in the buttons above.
No version for distro foxy. Known supported distros are highlighted in the buttons above.
No version for distro iron. Known supported distros are highlighted in the buttons above.
No version for distro lunar. Known supported distros are highlighted in the buttons above.
No version for distro jade. Known supported distros are highlighted in the buttons above.
No version for distro indigo. Known supported distros are highlighted in the buttons above.
No version for distro hydro. Known supported distros are highlighted in the buttons above.
No version for distro kinetic. Known supported distros are highlighted in the buttons above.
No version for distro melodic. Known supported distros are highlighted in the buttons above.