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_path_planner 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_path_planner package

Additional Links

No additional links.

Maintainers

  • Zulfaqar Azmi
  • Fumiya Watanabe
  • Kyoichi Sugahara
  • Tomoya Kimura
  • Shumpei Wakabayashi
  • Tomohito Ando
  • Takamasa Horibe
  • Satoshi Ota
  • Kosuke Takeuchi
  • Kyoichi Sugahara
  • Takayuki Murooka

Authors

  • Takamasa Horibe
  • Satoshi Ota
  • Fumiya Watanabe
  • Zulfaqar Azmi
  • Kosuke Takeuchi
  • Yutaka Shimizu
  • Takayuki Murooka
  • Ryohsuke Mitsudome

Behavior Path Planner

The Behavior Path Planner’s main objective is to significantly enhance the safety of autonomous vehicles by minimizing the risk of accidents. It improves driving efficiency through time conservation and underpins reliability with its rule-based approach. Additionally, it allows users to integrate their own custom behavior modules or use it with different types of vehicles, such as cars, buses, and delivery robots, as well as in various environments, from busy urban streets to open highways.

The module begins by thoroughly analyzing the ego vehicle’s current situation, including its position, speed, and surrounding environment. This analysis leads to essential driving decisions about lane changes or stopping and subsequently generates a path that is both safe and efficient. It considers road geometry, traffic rules, and dynamic conditions while also incorporating obstacle avoidance to respond to static and dynamic obstacles such as other vehicles, pedestrians, or unexpected roadblocks, ensuring safe navigation.

Moreover, the planner actively interacts with other traffic participants, predicting their actions and accordingly adjusting the vehicle’s path. This ensures not only the safety of the autonomous vehicle but also contributes to smooth traffic flow. Its adherence to traffic laws, including speed limits and traffic signals, further guarantees lawful and predictable driving behavior. The planner is also designed to minimize sudden or abrupt maneuvers, aiming for a comfortable and natural driving experience.

!!! note

The [Planning Component Design](https://autowarefoundation.github.io/autoware-documentation/v1.0/design/autoware-architecture/planning/) Document outlines the foundational philosophy guiding the design and future development of the Behavior Path Planner module. We strongly encourage readers to consult this document to understand the rationale behind its current configuration and the direction of its ongoing development.

Purpose / Use Cases

Essentially, the module has three primary responsibilities:

  1. Creating a path based on the traffic situation.
  2. Generating drivable area, i.e. the area within which the vehicle can maneuver.
  3. Generating turn signal commands to be relayed to the vehicle interface.

Features

Supported Scene Modules

Behavior Path Planner has following scene modules

Name Description Details
Lane Following this module generates reference path from lanelet centerline. LINK
Avoidance this module generates avoidance path when there is objects that should be avoid. LINK
Dynamic Avoidance WIP LINK
Avoidance By Lane Change this module generates lane change path when there is objects that should be avoid. LINK
Lane Change this module is performed when it is necessary and a collision check with other vehicles is cleared. LINK
External Lane Change WIP LINK
Start Planner this module is performed when ego-vehicle is in the road lane and goal is in the shoulder lane. ego-vehicle will stop at the goal. LINK
Goal Planner this module is performed when ego-vehicle is stationary and footprint of ego-vehicle is included in shoulder lane. This module ends when ego-vehicle merges into the road. LINK
Side Shift (for remote control) shift the path to left or right according to an external instruction. LINK

!!! Note

click on the following images to view the video of their execution

<div align="center">
    <table>
        <tr>
            <td><img src="./image/supported_module_lane_following.svg" alt="Lane Following Module" width="300"></td>
            <td><a href="https://www.youtube.com/watch?v=A_V9yvfKZ4E"><img src="./image/supported_module_avoidance.svg" alt="Avoidance Module" width="300"></a></td>
            <td><img src="./image/supported_module_avoidance_by_lane_change.svg" alt="Avoidance by Lane Change Module" width="300"></td>
        </tr>
        <tr>
            <td><a href="https://www.youtube.com/watch?v=0jRDGQ84cD4"><img src="./image/supported_module_lane_change.svg" alt="Lane Change Module" width="300"></a></td>
            <td><a href="https://www.youtube.com/watch?v=xOjnPqoHup4"><img src="./image/supported_module_start_planner.svg" alt="Start Planner Module" width="300"></a></td>
            <td><a href="https://www.youtube.com/watch?v=ornbzkWxRWU"><img src="./image/supported_module_goal_planner.svg" alt="Goal Planner Module" width="300"></a></td>
        </tr>
    </table>
</div>

!!! Note

Users can refer to [Planning component design](https://autowarefoundation.github.io/autoware-documentation/v1.0/design/autoware-architecture/planning/#supported-functions) for some additional behavior.

How to add or implement new module?

All scene modules are implemented by inheriting base class scene_module_interface.hpp.

!!! Warning

The remainder of this subsection is work in progress (WIP).

Planner Manager

The Planner Manager’s responsibilities include:

  1. Activating the relevant scene module in response to the specific situation faced by the autonomous vehicle. For example, when a parked vehicle blocks the ego vehicle’s driving lane, the manager would engage the avoidance module.
  2. Managing the execution order when multiple modules are running simultaneously. For instance, if both the lane-changing and avoidance modules are operational, the manager decides which should take precedence.
  3. Merging paths from multiple modules when they are activated simultaneously and each generates its own path, thereby creating a single functional path.

!!! note

To check the scene module's transition, i.e.: registered, approved and candidate modules, set `verbose: true` in the [behavior path planner configuration file](https://github.com/autowarefoundation/autoware_launch/blob/0cd5d891a36ac34a32a417205905c109f2bafe7b/autoware_launch/config/planning/scenario_planning/lane_driving/behavior_planning/behavior_path_planner/behavior_path_planner.param.yaml#L3).

![Scene module's transition table](./image/checking_module_transition.png)

!!! note

For more in-depth information, refer to [Manager design](./docs/behavior_path_planner_manager_design.md) document.

Inputs / Outputs / API

Input

Name Required? Type Description
~/input/odometry nav_msgs::msg::Odometry for ego velocity.
~/input/accel geometry_msgs::msg::AccelWithCovarianceStamped for ego acceleration.
~/input/objects autoware_auto_perception_msgs::msg::PredictedObjects dynamic objects from perception module.
~/input/occupancy_grid_map nav_msgs::msg::OccupancyGrid occupancy grid map from perception module. This is used for only Goal Planner module.
~/input/traffic_signals autoware_perception_msgs::msg::TrafficSignalArray traffic signals information from the perception module
~/input/vector_map autoware_auto_mapping_msgs::msg::HADMapBin vector map information.
~/input/route autoware_auto_mapping_msgs::msg::LaneletRoute current route from start to goal.
~/input/scenario tier4_planning_msgs::msg::Scenario Launches behavior path planner if current scenario == Scenario:LaneDriving.
~/input/lateral_offset tier4_planning_msgs::msg::LateralOffset lateral offset to trigger side shift
~/system/operation_mode/state autoware_adapi_v1_msgs::msg::OperationModeState Allows planning module to know if vehicle is in autonomous mode or can be controlledref
  • ○ Mandatory: Planning Module would not work if anyone of this is not present.
  • △ Optional: Some module would not work, but Planning Module can still be operated.

Output

Name Type Description QoS Durability
~/output/path autoware_auto_planning_msgs::msg::PathWithLaneId the path generated by modules. volatile
~/output/turn_indicators_cmd autoware_auto_vehicle_msgs::msg::TurnIndicatorsCommand turn indicators command. volatile
~/output/hazard_lights_cmd autoware_auto_vehicle_msgs::msg::HazardLightsCommand hazard lights command. volatile
~/output/modified_goal autoware_planning_msgs::msg::PoseWithUuidStamped output modified goal commands. transient_local
~/output/stop_reasons tier4_planning_msgs::msg::StopReasonArray describe the reason for ego vehicle stop volatile
~/output/reroute_availability tier4_planning_msgs::msg::RerouteAvailability the path the module is about to take. to be executed as soon as external approval is obtained. volatile

Debug

Name Type Description QoS Durability
~/debug/avoidance_debug_message_array tier4_planning_msgs::msg::AvoidanceDebugMsgArray debug message for avoidance. notify users reasons for avoidance path cannot be generated. volatile
~/debug/lane_change_debug_message_array tier4_planning_msgs::msg::LaneChangeDebugMsgArray debug message for lane change. notify users unsafe reason during lane changing process volatile
~/debug/maximum_drivable_area visualization_msgs::msg::MarkerArray shows maximum static drivable area. volatile
~/debug/turn_signal_info visualization_msgs::msg::MarkerArray TBA volatile
~/debug/bound visualization_msgs::msg::MarkerArray debug for static drivable area volatile
~/planning/path_candidate/* autoware_auto_planning_msgs::msg::Path the path before approval. volatile
~/planning/path_reference/* autoware_auto_planning_msgs::msg::Path reference path generated by each modules. volatile

!!! note

For specific information of which topics are being subscribed and published, refer to [behavior_path_planner.xml](https://github.com/autowarefoundation/autoware.universe/blob/9000f430c937764c14e43109539302f1f878ed70/planning/behavior_path_planner/launch/behavior_path_planner.launch.xml#L36-L49).

How to enable or disable the modules

Enabling and disabling the modules in the behavior path planner is primarily managed through two key files: default_preset.yaml and behavior_path_planner.launch.xml.

The default_preset.yaml file acts as a configuration file for enabling or disabling specific modules within the planner. It contains a series of arguments which represent the behavior path planner’s modules or features. For example:

  • launch_avoidance_module: Set to true to enable the avoidance module, or false to disable it.
  • use_experimental_lane_change_function: Set to true to enable experimental features in the lane change module.

!!! note

Click [here](https://github.com/autowarefoundation/autoware_launch/blob/v1.0/autoware_launch/config/planning/preset/default_preset.yaml) to view the `default_preset.yaml`.

The behavior_path_planner.launch.xml file references the settings defined in default_preset.yaml to apply the configurations when the behavior path planner’s node is running. For instance, the parameter avoidance.enable_module in

<param name="avoidance.enable_module" value="$(var launch_avoidance_module)"/>

corresponds to launch_avoidance_module from default_preset.yaml.

Therefore, to enable or disable a module, simply set the corresponding module in default_preset.yaml to true or false. These changes will be applied upon the next launch of Autoware.

Generating Path

A sophisticated methodology is used for path generation, particularly focusing on maneuvers like lane changes and avoidance. At the core of this design is the smooth lateral shifting of the reference path, achieved through a constant-jerk profile. This approach ensures a consistent rate of change in acceleration, facilitating smooth transitions and minimizing abrupt changes in lateral dynamics, crucial for passenger comfort and safety.

The design involves complex mathematical formulations for calculating the lateral shift of the vehicle’s path over time. These calculations include determining lateral displacement, velocity, and acceleration, while considering the vehicle’s lateral acceleration and velocity limits. This is essential for ensuring that the vehicle’s movements remain safe and manageable.

The ShiftLine struct (as seen here) is utilized to represent points along the path where the lateral shift starts and ends. It includes details like the start and end points in absolute coordinates, the relative shift lengths at these points compared to the reference path, and the associated indexes on the reference path. This struct is integral to managing the path shifts, as it allows the path planner to dynamically adjust the trajectory based on the vehicle’s current position and planned maneuver.

Furthermore, the design and its implementation incorporate various equations and mathematical models to calculate essential parameters for the path shift. These include the total distance of the lateral shift, the maximum allowable lateral acceleration and jerk, and the total time required for the shift. Practical considerations are also noted, such as simplifying assumptions in the absence of a specific time interval for most lane change and avoidance cases.

The shifted path generation logic enables the behavior path planner to dynamically generate safe and efficient paths, precisely controlling the vehicle’s lateral movements to ensure the smooth execution of lane changes and avoidance maneuvers. This careful planning and execution adhere to the vehicle’s dynamic capabilities and safety constraints, maximizing efficiency and safety in autonomous vehicle navigation.

!!! note

If you're a math lover, refer to [Path Generation Design](./docs/behavior_path_planner_path_generation_design.md) for the nitty-gritty.

Collision Assessment / Safety check

The purpose of the collision assessment function in the Behavior Path Planner is to evaluate the potential for collisions with target objects across all modules. It is utilized in two scenarios:

  1. During candidate path generation, to ensure that the generated candidate path is collision-free.
  2. When the path is approved by the manager, and the ego vehicle is executing the current module. If the current situation is deemed unsafe, depending on each module’s requirements, the planner will either cancel the execution or opt to execute another module.

The safety check process involves several steps. Initially, it obtains the pose of the target object at a specific time, typically through interpolation of the predicted path. It then checks for any overlap between the ego vehicle and the target object at this time. If an overlap is detected, the path is deemed unsafe. The function also identifies which vehicle is in front by using the arc length along the given path. The function operates under the assumption that accurate data on the position, velocity, and shape of both the ego vehicle (the autonomous vehicle) and any target objects are available. It also relies on the yaw angle of each point in the predicted paths of these objects, which is expected to point towards the next path point.

A critical part of the safety check is the calculation of the RSS (Responsibility-Sensitive Safety) distance-inspired algorithm. This algorithm considers factors such as reaction time, safety time margin, and the velocities and decelerations of both vehicles. Extended object polygons are created for both the ego and target vehicles. Notably, the rear object’s polygon is extended by the RSS distance longitudinally and by a lateral margin. The function finally checks for overlap between this extended rear object polygon and the front object polygon. Any overlap indicates a potential unsafe situation.

However, the module does have a limitation concerning the yaw angle of each point in the predicted paths of target objects, which may not always accurately point to the next point, leading to potential inaccuracies in some edge cases.

!!! note

For further reading on the collision assessment  method, please refer to [Safety check utils](./docs/behavior_path_planner_safety_check.md)

Generating Drivable Area

Static Drivable Area logic

The drivable area is used to determine the area in which the ego vehicle can travel. The primary goal of static drivable area expansion is to ensure safe travel by generating an area that encompasses only the necessary spaces for the vehicle’s current behavior, while excluding non-essential areas. For example, while avoidance module is running, the drivable area includes additional space needed for maneuvers around obstacles, and it limits the behavior by not extending the avoidance path outside of lanelet areas.

Before expansion
After expansion

Static drivable area expansion operates under assumptions about the correct arrangement of lanes and the coverage of both the front and rear of the vehicle within the left and right boundaries. Key parameters for drivable area generation include extra footprint offsets for the ego vehicle, the handling of dynamic objects, maximum expansion distance, and specific methods for expansion. Additionally, since each module generates its own drivable area, before passing it as the input to generate the next running module’s drivable area, or before generating a unified drivable area, the system sorts drivable lanes based on the vehicle’s passage order. This ensures the correct definition of the lanes used in drivable area generation.

!!! note

Further details can is provided in [Drivable Area Design](./docs/behavior_path_planner_drivable_area_design.md).

Dynamic Drivable Area Logic

Large vehicles require much more space, which sometimes causes them to veer out of their current lane. A typical example being a bus making a turn at a corner. In such cases, relying on a static drivable area is insufficient, since the static method depends on lane information provided by high-definition maps. To overcome the limitations of the static approach, the dynamic drivable area expansion algorithm adjusts the navigable space for an autonomous vehicle in real-time. It conserves computational power by reusing previously calculated path data, updating only when there is a significant change in the vehicle’s position. The system evaluates the minimum lane width necessary to accommodate the vehicle’s turning radius and other dynamic factors. It then calculates the optimal expansion of the drivable area’s boundaries to ensure there is adequate space for safe maneuvering, taking into account the vehicle’s path curvature. The rate at which these boundaries can expand or contract is moderated to maintain stability in the vehicle’s navigation. The algorithm aims to maximize the drivable space while avoiding fixed obstacles and adhering to legal driving limits. Finally, it applies these boundary adjustments and smooths out the path curvature calculations to ensure a safe and legally compliant navigable path is maintained throughout the vehicle’s operation.

!!! note

The feature can be enabled in the [drivable_area_expansion.param.yaml](https://github.com/autowarefoundation/autoware_launch/blob/0cd5d891a36ac34a32a417205905c109f2bafe7b/autoware_launch/config/planning/scenario_planning/lane_driving/behavior_planning/behavior_path_planner/drivable_area_expansion.param.yaml#L10).

Generating Turn Signal

The Behavior Path Planner module uses the autoware_auto_vehicle_msgs::msg::TurnIndicatorsCommand to output turn signal commands (see TurnIndicatorsCommand.idl). The system evaluates the driving context and determines when to activate turn signals based on its maneuver planning—like turning, lane changing, or obstacle avoidance.

Within this framework, the system differentiates between desired and required blinker activations. Desired activations are those recommended by traffic laws for typical driving scenarios, such as signaling before a lane change or turn. Required activations are those that are deemed mandatory for safety reasons, like signaling an abrupt lane change to avoid an obstacle.

The TurnIndicatorsCommand message structure has a command field that can take one of several constants: NO_COMMAND indicates no signal is necessary, DISABLE to deactivate signals, ENABLE_LEFT to signal a left turn, and ENABLE_RIGHT to signal a right turn. The Behavior Path Planner sends these commands at the appropriate times, based on its rules-based system that considers both the desired and required scenarios for blinker activation.

!!! note

For more in-depth information, refer to [Turn Signal Design](./docs/behavior_path_planner_turn_signal_design.md) document.

Rerouting

!!! warning

Rerouting is a feature that was still under progress. Further information will be included on a later date.

Parameters and Configuration

The configuration files are organized in a hierarchical directory structure for ease of navigation and management. Each subdirectory contains specific configuration files relevant to its module. The root directory holds general configuration files that apply to the overall behavior of the planner. The following is an overview of the directory structure with the respective configuration files.

behavior_path_planner
├── behavior_path_planner.param.yaml
├── drivable_area_expansion.param.yaml
├── scene_module_manager.param.yaml
├── avoidance
│   └── avoidance.param.yaml
├── avoidance_by_lc
│   └── avoidance_by_lc.param.yaml
├── dynamic_avoidance
│   └── dynamic_avoidance.param.yaml
├── goal_planner
│   └── goal_planner.param.yaml
├── lane_change
│   └── lane_change.param.yaml
├── side_shift
│   └── side_shift.param.yaml
└── start_planner
    └── start_planner.param.yaml

Similarly, the common directory contains configuration files that are used across various modules, providing shared parameters and settings essential for the functioning of the Behavior Path Planner:

common
├── common.param.yaml
├── costmap_generator.param.yaml
└── nearest_search.param.yaml

The preset directory contains the configurations for managing the operational state of various modules. It includes the default_preset.yaml file, which specifically caters to enabling and disabling modules within the system.

preset
└── default_preset.yaml

Limitations & Future Work

  1. Goal Planner module cannot be simultaneously executed together with other modules.
  2. Module is not designed as plugin. Integrating custom module is not straightforward and user have to modify some part of the behavior path planner main code.
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

  • launch/behavior_path_planner.launch.xml
      • common_param_path
      • vehicle_param_file
      • nearest_search_param_path
      • behavior_path_planner_launch_modules
      • behavior_path_config_path
      • behavior_path_planner_common_param_path
      • behavior_path_planner_scene_module_manager_param_path
      • behavior_path_planner_side_shift_module_param_path
      • behavior_path_planner_avoidance_module_param_path
      • behavior_path_planner_avoidance_by_lc_module_param_path
      • behavior_path_planner_dynamic_avoidance_module_param_path
      • behavior_path_planner_lane_change_module_param_path
      • behavior_path_planner_goal_planner_module_param_path
      • behavior_path_planner_start_planner_module_param_path
      • behavior_path_planner_drivable_area_expansion_param_path

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged behavior_path_planner 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.