1   Definition

Basic Environment Representation (BER) is the digital representation of the environment traversed by a CAV is called. The BER results from the integration of all data sensed by a CAV:

  1. Spatial information (e.g., GNSS, odometry).
  2. Audio-Visual Scene Descriptors obtained the fusion of EST-specific Scene Descriptors.
  3. Road Topology.
  4. Environmental data (e.g., weather, temperature, air pressure, ice and water on the road, wind, fog etc.).

2   Functional Requirements

The functional requirements of the BER format are:

  1. Includes all available information that enables the Autonomous Motion Subsystem (AMS) to define a Path to be executed in a Decision Horizon Time.
  2. Describes the Environment in terms of Scene Descriptors (including static objects, e.g., from Offline Maps) and Topology (e.g., roads and lanes).
  3. Enables object tracking, inference of motion vectors, etc. by referencing the BERs of sufficient prior snapshots.
  4. Describes each Object with the following attributes:
    • This is specified as Start and End Time of the validity of the Object Description.
    • Object Identifier. An Identifier is assigned to an Object that is retained until the Object disappears.
    • AIM Identifier. This identifies the AIM that provided the initial Data used to represent the Object.
    • Object Format ID. MPAI is identifying a set of Object Format specifications that enable unambiguous reference to an Object Format.
    • Identifiers of parent Objects corresponding to the current Object.
    • Identifier of a parent Object that has spawned more than one current Object.
    • ID of spatially corresponding Object of different Type.
    • Spatial Attitude of Object.
    • Object dimensionality (2D, 2.5D and 3D). Applicable only to Visual Objects.
    • Visual Object shape.
    • Semantic relationship with other Objects, e.g., identification of groups of Objects (platoon). The components of a platoon may broadcast Platooning Information, or a CAV may be able to deduce it by observing the behaviour of a group of CAVs over a period.
    • Accuracy of all Object values.
  5. Allows for easy verification of the feasibility of a Trajectory (e.g., the AMS can easily check that the intended Trajectory of the ego CAV designed to reach the intended point does not collide with other Visual Objects in the Decision Horizon based on the current state of the BER).
  6. Has a scalable representation, i.e., it allows for:
    • Gradual refinement of a BER when new EST-specific Scene Descriptors are added.
    • Extraction of part of the BER based on a required Level of Detail (e.g., Object bounding boxes and their Spatial Attitudes).
    • Easy addition of new data (e.g., adding shape of an Object when there was only the bounding box).
    • Fast access to Object metadata, e.g.:
      • Spatial Attitude.
      • 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 BER to improve its description.
    • Easy update of Objects and Scene from one snapshot to another.
    • Possibility that a CAV communicates a subset of its BER to another CAV. E.g., Objects have different degrees of details, starting from bounding boxes and their Position Attributes, depending on the available bandwidth.

3   Syntax

4   Semantics

5   Data Formats

6   To Respondents

Respondents are requested to:

  1. Explore the use of the MPAI Audio-Visual Scene Descriptors to support the Basic Environment Representation by adding the missing functionalities.
  2. Comment on the Functional Requirements.