Scenario Generation

Generate scenario from recorded real-world sensor data

In automated driving applications, scenario generation is the process of building virtual scenarios from real-world vehicle data recorded from global positioning system (GPS), inertial measurement unit (IMU), camera, and lidar sensors. Automated Driving Toolbox™ provides functions and tools to automate scenario generation process. You can preprocess sensor data, extract roads, localize actors, and get actor trajectories to create an accurate digital twin of a real-world scenario. Simulate the generated scenario and test your automated driving algorithms against real-world data.

To generate scenarios from recorded sensor data, download the Scenario Builder for Automated Driving Toolbox support package from the Add-On Explorer. For more information on downloading add-ons, see Get and Manage Add-Ons.

Functions

expand all

Sensor Data Processing

`GPSData`	Store GPS data (Since R2024b)
`Trajectory`	Create trajectory using timestamps and waypoints (Since R2024b)
`CameraData`	Store sequence of camera data (Since R2024b)
`LidarData`	Store sequence of lidar data (Since R2024b)
`recordedSensorData`	Create sensor data object from recorded sensor data (Since R2024b)
`getMapROI`	Geographic bounding box coordinates from GPS data (Since R2022b)

Scene Generation

`roadprops`	Extract road properties from road network file or map data (Since R2022b)
`selectActorRoads`	Extract properties of roads in path of actor (Since R2022b)
`updateLaneSpec`	Update lane specifications using sensor detections (Since R2022b)
`laneData`	Store recorded lane boundary data with timestamps (Since R2023a)
`laneBoundaryDetector`	Detector for lane boundaries in images (Since R2023a)
`laneBoundaryTracker`	Track lane boundaries (Since R2023a)
`egoToWorldLaneBoundarySegments`	Convert tracked lane boundaries to lane boundary segments in world coordinates (Since R2024a)
`laneBoundarySegment`	Store lane boundary information of road segment (Since R2024a)
`laneBoundaryGroup`	Group lane boundaries in lane boundary segment objects (Since R2024a)
`smoothBoundaries`	Smooth lane boundaries (Since R2024a)
`getLanesInRoadRunnerHDMap`	Create RoadRunner HD Map from lane information (Since R2024a)
`roadrunnerLaneInfo`	Generate lane information in RoadRunner HD Map format from lane boundary points (Since R2023a)
`roadrunnerStaticObjectInfo`	Generate static object and sign information in RoadRunner HD Map format (Since R2023a)
`addElevation`	Add elevation to scene data using georeferenced point cloud (Since R2024a)

Scenario Generation

`actorprops`	Generate actor properties from track list (Since R2022b)
`actorTracklist`	Store recorded actor track list data with timestamps (Since R2023a)
`importFromObjectTrack`	Import track list from `objectTrack` object (Since R2023a)
`exportToDrivingScenario`	Export trajectory to driving scenario (Since R2024b)
`exportToRoadRunner`	Export trajectory to RoadRunner (Since R2024b)
`writeCSV`	Write trajectory data into CSV file (Since R2024b)

Topics

Getting Started

Overview of Scenario Generation from Recorded Sensor Data
Learn the basics of generating scenarios from recorded sensor data.
Extract Key Scenario Events from Recorded Sensor Data
Extract key scenario events from recorded sensor data.

Scene Generation

Generate RoadRunner Scene Using Processed Camera Data and GPS Data
Generate RoadRunner scene using labeled camera images and GPS data.
Generate RoadRunner Scene from Recorded Lidar Data
Generate RoadRunner HD map from recorded lidar data using pretrained deep learning model.
Generate High Definition Scene from Lane Detections and OpenStreetMap
Generate HD road scene using recorded lane detections, GPS data, and OpenStreetMap^® data.
Generate RoadRunner Scene with Traffic Signs Using Recorded Sensor Data
Generate RoadRunner scene with traffic signs using recorded sensor data.
Generate RoadRunner Scene Using Aerial Lidar Data
Generate RoadRunner scenario from aerial lidar data.
Generate RoadRunner Scene Using Aerial Hyperspectral and Lidar Data
Generate RoadRunner scene from aerial hyperspectral and lidar data.
Georeference Sequence of Point Clouds for Scene Generation
Georeference sequence of point clouds for scene generation.
Georeference Aerial Point Cloud for Scene Generation
Georeference aerial point cloud for scene generation.

Scenario Generation

Preprocess Lane Detections for Scenario Generation
Format lane detection data to update lane specifications for scenario generation.
Smooth GPS Waypoints for Ego Localization
Create jitter-limited ego trajectory by smoothing GPS and IMU sensor data.
Generate Scenario from Actor Track List and GPS Data
Generate ASAM OpenSCENARIO^® v1.0 file using recorded actor tracklist and GPS data.
Extract Vehicle Track List from Recorded Camera Data for Scenario Generation
Extract actor track list from raw camera data for scenario generation.
Extract 3D Vehicle Information from Recorded Monocular Camera Data for Scenario Generation
Extract 3D vehicle information from recorded monocular camera data for scenario generation.

Featured Examples

Generate RoadRunner Scenario from Recorded Sensor Data

Generate RoadRunner Scenario from recorded GPS data and preprocessed actor track list.

Open Live Script

Ego Vehicle Localization Using GPS and IMU Fusion for Scenario Generation

Localize ego vehicle by fusing GPS and IMU sensor data to generate virtual driving scenario.

Open Live Script

Ego Localization Using Lane Detections and HD Map for Scenario Generation

Perform lane-level localization of ego vehicle using lane detections, HD map data, and GPS data.

Open Live Script

Extract Lane Information from Recorded Camera Data for Scene Generation

Extract lane information from raw camera data to generate ASAM OpenDRIVE^® scene or RoadRunner scene.

Open Live Script

Generate RoadRunner Scene Using Labeled Camera Images and Raw Lidar Data

Generate road scene with lanes from labeled camera images and raw lidar data.

Open Live Script

Extract Vehicle Track List from Recorded Lidar Data for Scenario Generation

Extract actor track list from recorded lidar data using pretrained vehicle detection model and JPDA tracker.

Open Live Script

Fuse Prerecorded Lidar and Camera Data to Generate Vehicle Track List for Scenario Generation

Generate scenario by fusing and smoothing tracked lidar data and camera data.

Open Live Script

Generate RoadRunner Scene with Trees and Buildings Using Recorded Lidar Data

Generate RoadRunner scene with trees and buildings using recorded lidar data.

Open Live Script