Go To CAV-TEC V1.0 Use Cases and Functional Requirements home page


In recent years, Artificial Intelligence (AI) and related technologies have been applied to a broad range of applications, have started affecting the life of millions of people and are expected to do so even more in the future. As digital media standards have positively influenced industry and billions of people, so AI-based data coding standards are expected to have a similar positive impact. Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) has been established to develop standards that promote the efficient use of data especially using Artificial Intelligence technologies.


To establish a framework for the pursuit of its mission, MPAI has developed Technical Specification: Governance of the MPAI Ecosystem (MPAI-GME) [1]. This defines the following elements: Standards, i.e., the ensemble of Technical Specifications, Reference Software, Conformance Testing, and Performance Assessment; Implementers of MPAI Technical Specifications; the MPAI Store in charge of making AIMs and AIWs submitted by Implementers available to Integrators and End-Users; Performance Assessors, independent entities assessing the performance of implementations in terms of Reliability, Replicability, Robustness, and Fairness; and End Users.


To facilitate the development of smaller-scale high-performance components and the availability of solution with improved explainability, MPAI has developed another foundational Technical Specification: Artificial Intelligence Framework (MPAI-AIF) [1] whose Reference Model is depicted in Figure 1.

Figure 1 – The AI Framework (MPAI-AIF) V2 Reference Model

MPAI-AIF specifies an environment enabling initialisation, dynamic configuration, and control of AI Workflows composed of interconnected AI Modules (AIM) in the standard AI Framework environment.. AI Modules can be Composite if they include interconnected AIMs or Basic if they are not Composite.


1          Introduction

MPAI has published Technical Specification: Connected Autonomous Vehicle (MPAI-CAV) – Architecture (CAV-ARC) V1.0. The CAV-ARC Reference Model assumes that the CAV is composed of four Subsystems each of which is specified as an AI Workflow (AIW) composed of AI Modules (AIM) executed in AI Framework implementations. The CAV-ARC Technical Specification, however, does not specify the Functional Requirements of such Data.


This document – Use Cases and Functional Requirements: Connected Autonomous Vehicle (MPAI-CAV) – Technologies – identifies and develops such Functional Requirements for use in a planned new Technical Specification: Connected Autonomous Vehicle (MPAI-CAV) – Technologies (CAV-TEC).


As mandated by the MPAI Statutes [1] and the MPAI Patent Policy [2], this document is published jointly with the CAV-TEC Call for Technologies [4], CAV-TEC Framework Licence [5], and CAV-TEC Template for Responses [6].


In developing Functional Requirements of CAV-TEC Data Types, this document makes reference to some MPAI Technical Specifications, namely MPAI-CAE [7], MPAI-CUI [8], MPAI-HMC [10], MPAI-MMC [11], MPAI-MMM [12], MPAI-OSD [13], and MPAI-PAF [14] and a preliminary version of the JSON Syntax and Semantics of the identified Data Types reported in this document. These references are provided as a background information and as examples of how the Functional Requirements can be fulfilled, not as a foregone conclusion. MPAI welcomes motivated proposals of extension or alternative solutions for use in the planned CAV-TEC Technical Specification.


JSON Syntax and Semantics are believed to be sufficient for a significant portion of the Data Types identified for the planned CAV-TEC Technical Specification. For others, a Data Format is also required. The examples of JSON Syntax and Semantics of this document include reference to “FormatIDs” of Data Types and Attributes. Respondents are encouraged to send comment and proposals to populate a planned Technical Specification: Data Types, Formats, and Attributes (MPAI-TFA).