1   Definition

Basic Environment Descriptors (BED) digitally represent the environment traversed by a CAV. BED result from the integration of a subset of all data sensed by a CAV:

  1. Spatial information (e.g., GNSS, odometry).
  2. Audio-Visual Scene Descriptors obtained from the fusion of Environment Sensing Technology (EST)-specific Scene Descriptors.
  3. Road State.

2   Functional Requirements

  1. Is a snapshot of the Environment at a given Time that includes:
    1. Available information enabling the Autonomous Motion Subsystem (AMS) to operate.
    2. Scene Descriptors of the Environment (including static objects, e.g., from Offline Maps).
  2. Enables object tracking, inference of motion vectors, etc. by referencing a sufficient number of BERS.
  3. Describes each Object with the following attributes:
    • Object Identifier retained until the Object disappears.
    • AIM Identifier of the AIM that provided the Data used to represent the Object though Object Data Qualifier.
    • Object dimensionality (2D, 2.5D and 3D), shape, and Format through its Qualifier.
    • Parent Object(s).
    • Spatial Attitude of Object.
    • Object . Applicable only to Visual Objects.
    • Relationship with other Objects, e.g., groups of Objects (platoon) deduced from platoon components broadcasting Platooning Information, or from observation of a group of CAVs .
    • Accuracy of Object values.
  4. Allows for easy verification of the feasibility of a Trajectory, e.g., to enable the AMS to check that the intended Trajectory of the ego CAV does not collide with other Visual Objects in the Decision Horizon.
  5. Has a scalable representation to allow for:
    • Refinement of BED when new EST-specific Scene Descriptors are added.
    • Extraction of part of the BED based on a required Level of Detail, e.g., Object bounding boxes and their Spatial Attitudes.
    • Addition of new data, e.g., the shape of an Object when there was only the bounding box.
    • Fast access to Object metadata, such as Spatial Attitude and Shape (e.g., bounding box for a Visual Object).
    • Selected (read) access to data required by different AIMs, e.g., the RADAR Scene Description AIM accesses the current BED to improve its description.
    • Update of Objects and Scenes from one Scene to another.
    • Possibility to communicate a subset of BED to another CAV with different details, e.g., starting from Position, Bounding Box, depending on the available bandwidth.

3   Syntax

https://schemas.mpai.community/CAV2/V1.0/data/BasicEnvironmentDescriptors.json

4   Semantics

Label Size Description
Header N1 Bytes Basic Environment Descriptors Headers
·       Standard-BasicEnvironmentDescriptors 9 Bytes The characters “CAV-BED-V”
·       Version N2 Bytes Major version – 1 or 2 Bytes
·       Dot-separator 1 Byte The character “.”
·       Subversion N3 Bytes Minor version – 1 or 2 Bytes
MInstance N4 Bytes Virtual Space where BED is (intended) to be placed.
AudioVisualSceneDescriptors N5 Bytes Audio Visual Scene Descriptors of Environment.
RoadState N7 Bytes Road State
DescrMetadata N8 Bytes Descriptive Metadata.