This page describes the interface of the Planning component. See the Planning component design for the concepts and the data flow.
The tables show the default setup of autoware_launch, where the planning_setting launch argument is rule_based. With diffusion_planner, a learned planner makes the trajectory instead of the scenario planning modules. The outputs of the component stay the same, and the planner also uses the tracked objects (/perception/object_recognition/tracking/objects).
Set of perceived objects around ego that need to be avoided or followed when planning a trajectory. This contains semantic information such as the object class (for example, vehicle or pedestrian) or a shape of the objects.
Set of perceived obstacles around ego that need to be avoided or followed when planning a trajectory. This only contains a primitive information of the obstacle. No shape nor velocity information.
Contains the traffic signal information such as a color (green, amber, red) and an arrow (right, left, straight).
The type of the Obstacles information is a sensor message type (PointCloud2) today. The plan is to replace it with a type that does not depend on a sensor.
Clears the MRM route. The normal route then becomes active again.
The AD API routing services (/api/routing/set_route, /api/routing/set_route_points, /api/routing/change_route, /api/routing/change_route_points, and /api/routing/clear_route) call the three route services above. The route selector of autoware_mission_planner_universe picks between the normal route and the MRM route.
The path that a module of the behavior path planner is about to take. Users can interrupt the operation based on the path candidate information. There is one topic for each module.
Why a module stops, slows down, shifts, or turns the vehicle. There is one topic for each module. The AD API converts them into velocity factors and steering factors.
A sequence of approximate vehicle positions for driving, along with information on the maximum speed and the drivable areas. Modules receiving this message are expected to make changes to the path within the constraints of the drivable areas and the maximum speed, generating the desired final trajectory.
A sequence of precise vehicle positions, speeds, and accelerations required for driving. The planning validator checks it and publishes it as /planning/trajectory.
With the diffusion_planner setting, the validator takes /planning/trajectory_generator/trajectory instead.