ROS index logo ROS Index
Package List
Repository List
System Dependencies
  1. Home
  2. Packages
  3. world_model
 
No version for distro humble showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro kilted showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro lyrical showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro rolling showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro ardent showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro bouncy showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro crystal showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro eloquent showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro dashing showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro galactic showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro foxy showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro iron showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code
No version for distro lunar showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro jade showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro indigo showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro hydro showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro kinetic showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro melodic showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki
No version for distro noetic showing jazzy. Known supported distros are highlighted in the buttons above.
Package symbol

world_model package from wato_monorepo repo

ackermann_pure_pursuit action_bringup freeroam_planner global_planning lattice_planning lattice_planning_markers lattice_planning_msgs model_predictive_control mpc_controller osqp_eigen_vendor trajectory_planner wato_trajectory_msgs infrastructure_bringup tf_static_relay vision_msgs_markers wato_lifecycle_manager ackermann_mux camera_calib lidar_imu_calib lidar_lidar_calib can_state_estimator dummy_ackermann eve_description interfacing_bringup joystick_interfacing lidar_aggregator oscc_interfacing oscc_mux pid_control pid_msgs roscco_msg sensor_interfacing topic_healthchecker attribute_assigner bevfusion cuda_bevfusion_vendor depth_estimation feature_extraction patchworkpp patchworkpp_vendor perception_bringup perception_utils spatial_association bytetrack_cpp_vendor track_viz_2d tracking traffic_light_detection carla_bringup carla_common carla_control carla_lifecycle carla_localization carla_msgs carla_perception carla_pygame carla_ros_bridge carla_sample_description carla_scenarios carla_teleop simulation_bringup wato_test behaviortree_ros2_vendor behaviour behaviour_markers behaviour_msgs costmap costmap_markers costmap_msgs eidos eidos_msgs eidos_tools eidos_transform lanelet_markers lanelet_msgs lidar_localization prediction world_model world_model_markers world_model_msgs world_modeling_bringup

ROS Distro
jazzy

API Docs
Browse Code
Wiki

Package Summary

Version 0.1.0
License Apache-2.0
Build type AMENT_CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/WATonomous/wato_monorepo.git
VCS Type git
VCS Version main
Last Updated 2026-11-05
Dev Status DEVELOPED
Released UNRELEASED
Contributing Help Wanted (-)
Good First Issues (-)
Pull Requests to Review (-)

Package Description

Central world state database providing lanelet services, entity tracking, and traffic light state

Maintainers

  • WATonomous

Authors

No additional authors.
src/world_modeling/world_model/README.md

World Model

ROS2 Lifecycle Node that maintains a unified view of the world for autonomous driving.

Overview

The world model aggregates data from multiple sources (perception, prediction, HD map) into a single queryable state. It provides:

  • Entity tracking: Cars, humans, bicycles, motorcycles, traffic lights
  • Lanelet map queries: Routes, corridors, regulatory elements
  • Lane context: Current lanelet, distances to events

Parameters

Parameter Type Default Description
osm_map_path string ”” Path to OSM lanelet map
map_frame string “map” Map frame ID
base_frame string “base_footprint” Robot base frame ID
projector_type string “utm” Projector: “utm” or “local_cartesian”
alignment_mode string “fixed” “fixed” uses the configured origin directly; “tf” applies a full projected-frame-to-map transform
projected_frame string “utm” Source TF frame in “tf” mode; absolute UTM for the UTM projector, configured local ENU for Local Cartesian
origin_lat double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_lon double 0.0 Geographic origin; in UTM TF mode, selects the UTM zone only
origin_alt double 0.0 Origin altitude in metres; subtracted in fixed mode, not in UTM TF mode
entity_history_duration_sec double 5.0 How long to keep entity history
entity_prune_timeout_sec double 2.0 Prune entities not seen for this long
traffic_light_timeout_sec double 1.0 Traffic light prune timeout
cleanup_interval_ms double 1000.0 Cleanup worker interval
lane_context_publish_rate_hz double 10.0 Lane context publish rate
map_viz_publish_rate_hz double 1.0 Map visualization publish rate
map_viz_radius_m double 100.0 Radius for map visualization
world_objects_enriched_publish_rate_hz double 10.0 World objects enriched publish rate
route_ahead_publish_rate_hz double 10.0 Route ahead publish rate
route_ahead_lookahead_m double 100.0 Lookahead distance for route lanelets

Projection and map alignment

projector_type converts OSM latitude/longitude into metric coordinates. alignment_mode specifies how those coordinates relate to the ROS map_frame. Both projectors honour the configured latitude, longitude, and altitude.

With alignment_mode: fixed, projection output is already in map_frame: UTM subtracts the projected geographic origin and origin altitude; Local Cartesian produces ENU coordinates relative to that origin. No alignment TF is required. CARLA maps must use the same projection and origin as their XODR.

With alignment_mode: tf, the node waits for lookupTransform(map_frame, projected_frame, ...) and applies its complete rotation and translation to every OSM point during parsing. UTM projection produces absolute easting, northing, and OSM elevation, so Eidos’s absolute UTM transform is applied once without subtracting another origin. For Local Cartesian, the source frame must describe ENU coordinates relative to the configured origin. All Lanelet2 geometry and indices are constructed after alignment. The transform is sampled once per map load; deactivate, clean up, configure, and activate again to load a different map or realign after a TF change.

Unsupported modes, invalid origins, and invalid transforms fail explicitly. A missing TF is retried; a bad map file stops the load with an error.

Named oval, Town10HD, and test-track configs and launch examples are documented in world_modeling_bringup. The former wait_for_utm_transform and utm_frame parameters are replaced by alignment_mode and projected_frame. The unused utm_origin_x/y arguments have been removed from the loader API.

Topics

Subscribed

| Topic | Type | Description | |——-|——|————-| | detections | vision_msgs/Detection3DArray | 3D object detections | | traffic_light_detections | vision_msgs/Detection2DArray | Traffic light detections | | predictions | prediction_msgs/PredictionHypothesesArray | Predicted trajectories |

Published

| Topic | Type | Description | |——-|——|————-| | lane_context | lanelet_msgs/CurrentLaneContext | Current lane information (route-aware) | | route_ahead | lanelet_msgs/RouteAhead | Route lanelets ahead within lookahead distance | | map_visualization | lanelet_msgs/MapVisualization | Nearby lanelets for viz | | world_objects_enriched | world_model_msgs/WorldObjectArray | All tracked entities (enriched) |

Services

Service Type Description
set_route lanelet_msgs/SetRoute Set destination and cache route
get_shortest_route lanelet_msgs/GetShortestRoute Get entire shortest route from ego to goal
get_lanelets_by_reg_elem lanelet_msgs/GetLaneletsByRegElem Find lanelets by regulatory element

License

Apache 2.0 - Copyright (c) 2025-present WATonomous

CHANGELOG
No CHANGELOG found.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged world_model at Robotics Stack Exchange

API Docs Browse Code Wiki