Table 1 and Table 2 define the CAV-specific Terms and the general MPAI Terms, respectively.
Table 1 – Terms and Definitions
Note A dash “-” preceding a Term in this Table means the following:
- If the font is normal, the Term in the table without a dash and preceding the one with a dash should be placed before that Term. The notation is used to concentrate in one place all the Terms that are composed of, e.g., the word Audio followed by one of the words Object, Scene, and Scene Descriptors.
- If the font is italic, the Term in the table without a dash and preceding the one with a dash should be placed after that Term. The notation is used to concentrate in one place all the Terms that are composed of, e.g., the word Attitude preceded by one of the words Social or Spatial.
Term | Definition |
Accelerometer Data | A Data Type representing the acceleration forces acting on a CAV. |
Alert | A Data Type representing environment-related elements that should be treated with priority by the Obstacle Avoider AIM. |
AMS-MAS Command | A Data Type representing the command issued by the Autonomous Motion Subsystem instructing the Motion Actuation Subsystem to change the Ego CAV’s Spatial Attitude SAA at time tA to Spatial Attitude SAB at time tB. |
AMS-HCI Response | A Data Type representing the response of the Motion Actuation Subsystem during and after the execution of an HCI-AMS Command. |
Attitude | |
– Social | A Data Type representing an element of the internal status of a human or avatar related to the way they intend to position themselves vis-à-vis the context, e.g., “Confrontational”, “Respectful”. |
– Spatial | A Data Type representing the CAV’s Position, Orientations and their velocities and accelerations at a given time. |
Audio | A Data Type representing analogue signals generated by information perceptible by a human using the sense of sound. |
– Data | A Data Type representing the output of a microphone array capturing the target environment to create the Audio Scene Description used to incorporate Environment Audio information in the Basic and Full Environment Representation. |
– Object | A Data Type representing an audio object and associated metadata. |
– Scene | A Data Type representing an audio scene. |
– Scene Descriptors | A Data Type representing the Audio Data and produced by the Audio Scene Description AIM using previous Basic Environment Representations. |
Audio-Visual | A Data Type representing analogue signals generated by information perceptible by a human using the sense of sound and sight. |
– Object | A Data Type representing Audio-Visual information and associated metadata. |
– Scene | (AV Scene) A Data Type representing an audio-visual scene. |
– Scene Descriptors | A Data Type representing the outdoor and indoor Audio-Visual Scene in terms of Audio-Visual Objects that includes the following features:
1. Having a common time-base. 2. Associating co-located audio and visual objects if both are present. 3. Supporting the physical displacement and interrelation (e.g., occlusion) of Audio and Visual Objects over time. |
Avatar | A Data Type representing a real or fictitious person in a virtual space rendered to a physical space. |
– Model | A Data Type representing the model of a human that a User selects to impersonate the CAV’s HCI as rendered by the Personal Status Display AIM. |
Basic Environment Representation (BER) | A Data Type representing Environment using information provided by a variety of sensors and including:
1. The Audio-Visual Scene Geometry. 2. The Ego CAV’s Spatial Attitude. 3. The Scene Description produced from the available Environment Sensing Technologies. 4. The Road Topology. 5. Other Environment Data. |
Body Descriptors | A Data Type representing the motion and conveying information on the Personal Status of the body of a human or an avatar. |
Brake | |
– Command | A Data Type representing the command issued to the Brakes by the Motion Actuation Subsystem after interpreting an AMS-MAS Command. |
– Response | A Data Type representing the Brakes’ response to the AMS Command Interpreter in response to a Brake Command. |
CAV | See Connected Autonomous Vehicle. |
– Aware | An attribute of physical entities possessing some of the sensing and communication capabilities of a CAV without being a CAV, e.g., Roadside Units and Traffic Lights. |
– Centre | The point in the Ego CAV selected to have coordinates (0,0,0). |
– Ego | The Object in the Environment that the CAV recognises as itself. |
– Identifier | A Data Type uniquely identifying a CAV and carrying information, such as:
1. Country code where the CAV has been registered. 2. Registration number in that country. 3. CAV manufacturer identifier. 4. CAV model identifier. |
Cognitive State | A Data Type representing the internal status of a human or avatar reflecting their understanding of the context, such as “Confused” or “Dubious” or “Convinced”. |
Connected Autonomous Vehicle | (CAV) The information technology-related components of a vehicle enabling it to autonomously reach a Pose by:
1. Understanding human utterances in the Subsystem (HCI). 2. Planning a Route (AMS). 3. Sensing and building a Representations of the external Environment (ESS). 4. Exchanging such Representations and other Data with other CAVs and CAV-aware entities (AMS). 5. Making decisions about how to execute the Route (AMS). 6. Acting on the MAS (AMS). |
Data | Information in digital form. |
– Format | The standard digital representation of Data. |
– Semantics | The meaning of Data. |
– Shape | A Data Type representing the volume occupied by a CAV. |
– Type | An instance of Data with a specific Data Format. |
Decision Horizon | The time interval within which a decision is planned to be implemented. |
Descriptor | Coded representation of a text, audio, speech, or visual feature. |
Digital Representation | Data corresponding to and representing a physical entity. |
Emotion | A Data Type representing the internal status of a human or avatar resulting from their interaction with the context or subsets of it, such as “Angry”, and “Sad”. |
Environment | The Digital Representation of the portion of the external world of current interest to a CAV. |
– Representation | A Data Type representing the Environment such as produced by an Environment Sensing Technology or derived from the Basic or Full Environment Representation. |
– Sensing Technology | (EST) One of the technologies used to sense the environment by the Environment Sensing Subsystem, e.g., RADAR, Lidar, Visual, Ultrasound, and Audio. The Offline Map is considered as an EST. |
Face | The portion of a 2D or 3D Digital Representation corresponding to the face of a human. |
– Descriptors | A Data Type representing the motion and conveying information on the Personal Status of the face of a human or an avatar. |
– ID | The Identifier of a human belonging to a group of humans inferred from analysing the face of the human. |
Factor | One of Cognitive State, Emotion, and Social Attitude |
Full Environment Representation | (FER) A Data Type representing the Environment that extends the Basic Environment Representations of the Ego CAV with elements of those of other CAVs in range or Roadside Units. |
– Audio | The ready-to-render Audio component of the Full Environment Representation Viewer. |
– Commands | A Data Type representing the commands issued by a CAV passenger to the HCI to enable navigation in the Full Environment Representation, e.g., select a Point of View, zoom in/out, control sound level. |
– Visual | The ready-to-render Visual component of the Full Environment Representation Viewer. |
Gesture | A Data Type representing the movement of the body or part of it, such as the head, arm, hand, and finger, often a complement to a vocal utterance. |
Global Navigation Satellite System (GNSS) | One of the systems providing global navigation information such as GPS, Galileo, Glonass, BeiDou, Quasi Zenith Satellite System (QZSS) and Indian Regional Navigation Satellite System (IRNSS). |
Goal | The Spatial Attitude planned to be reached at the end of a Decision Horizon. |
HCI-AMS Command | A Data Type representing high-level instructions issued by HCI to AMS to request it to reach a destination. |
Identifier | A Label that is uniquely associated with an Object. |
Inertial Measurement Unit | An inertial positioning device, e.g., odometer, accelerometer, speedometer, gyroscope etc. |
Instance ID | An Instance of a class of Objects and the Group of Objects the Instance belongs to. |
Latitude | A Data Type representing the angular distance of a place north of the earth’s equator measured in degrees [7]. |
LiDAR | A Data Type representing analogue signals generated by information captured by an active time-of-flight sensor operating in the µm range – ultraviolet, visible, or near infrared light (900 to 1550 nm). |
– Data | A Data Type representing Data captured by a LiDAR sensor. |
– Scene Descriptors | A Data Type representing the LiDAR Data and produced by the LiDAR Scene Description AIM using previous Basic Environment Representations. |
Longitude | A Data Type representing the angular distance of a place west of the Greenwich meridian measured in degrees [7]. |
Machine | Synonym with Human-CAV Interaction Subsystem. |
– Avatar | The ready-to-render Avatar produced by the Personal Status Display. |
– Speech | The ready-to-render synthetic speech produced by the Personal Status Display. |
Map Scene Descriptors | A Data Type representing the Offline Map Data complemented by the previous Basic Environment Representations in the common Scene Description Format. |
MAS-AMS Response | A Data Type representing the Response of AMS Command Interpreter integrating the Response from Brakes, Steering Wheel, and Wheel Motors. The MAS-AMS Responses contain the value of the Spatial Attitudes of the Ego CAV at intermediate Poses with the corresponding Times. |
Meaning | A Data Type representing an input text such as syntactic and semantic information. |
Microphone Array Geometry | A Data Type representing the position of each microphone comprising a microphone array and characteristics such as microphone type, look directions, and array type. |
Modality | One of Text, Speech, Face, or Gesture. |
Model | A Data Type representing:
1) A ready-to-be animated object with its features, or 2) An Artificial Neural Network. |
Object | A Data Type representing an object sensed by an EST and produced by an EST-specific Scene Description including the following elements:
1. Timestamp. 2. Identifier of the Scene Description AIM that has generated the Object. 3. Alerts. 4. Spatial Attitude of the Object and its estimated accuracy referred to the CAV Centre. 5. Bounding box. 6. Object type (2D, 2.5D, and 3D). |
– ID | The Identifier uniquely associated with a particular class of Objects, e.g., hammer, screwdriver, etc. |
Odometer Data | A Data Type representing the distance from the start up to the current Pose measured by the number of wheel rotations times the tire circumference (π x tire diameter). |
Offline | |
– Map | A previously created digital map of an Environment and associated metadata. |
– Map Data | A Data Type representing the Data provided by an Offline Map in response to a given set of coordinate values. |
Orientation | A Data Type representing the set of the 3 roll, pitch, yaw angles indicating the rotation around the axes of a CAV obtained from the CAV’s sensors:
– Roll: around the principal axis X. – Pitch: around the Y axis. Y has an angle of 90˚ counterclockwise (right-to-left) with the x axis. – Yaw: around the Z axis perpendicular to and out of the ground. |
Other Environment Data | Data Types representing information acquired by the Motion Actuation Subsystem and complementing the spatial data such as weather, temperature, air pressure, humidity, ice and water on the road, wind, fog etc. |
Path | A Data Type representing a sequence of Poses. |
Personal Status | A Data Type representing the ensemble of information internal to a person expressed by 3 Factors (Cognitive State, Emotion, Social Attitude) conveyed by one or more Modalities (Text, Speech, Face, and Gesture). |
Point of View | The Spatial Attitude of a user looking at the Environment. |
Portable Avatar | A Data Type providing context information and allowing the rendering of an Avatar as intended by the Portable Avatar producer. |
Pose | A Data Type representing Position and Orientation of the CAV as captured by the CAV sensors. |
Position | A Data Type representing the current coordinates of a CAV as captured by the CAV sensors. |
RADAR | A Data Type representing analogue signals generated by information captured by an active time-of-flight sensor operating in the operating in the 24-81 GHz range. |
– Data | A Data Type representing the Visual Data captured by a RADAR sensor. |
– Scene Descriptors | A Data Type representing the Visual Data captured by RADAR and produced by the RADAR Scene Description AIM using previous Basic Environment Representations. |
Remote AMS | AMS of a CAV or CAV-Aware entity in range. |
Remote HCI | HCI of a CAV or CAV-aware entity in range. |
Road State | A Data Type representing the state of the road the CAV is traversing such as detours and road conditions. Road State may be inferred by the AMS from internally available information or received from an external source via a communication channel. |
Road Topology | A Data Type representing the Position of the Road Signs (Traffic Poles, Road Signs, Traffic Lights) and the Taxonomy-based semantics of the Road Signs. |
Roadside Unit | A wireless communicating device located on the roadside providing information to CAVs in range. |
Route | A Data Type representing a sequence of Waypoints. |
Scene Descriptors | A Data Type representing the combination of EST-specific 2D, 2.5D, or 3D Scene Descriptors used by an EST Scene Description in an EST-specific time window. |
Speaker ID | The Identifier of a human belonging to a group of humans inferred from analysing the speech of the human. |
Speech | A Data Type representing analogue speech sampled at a frequency between 8 kHz and 96 kHz with 8, 16 and 24 bits/sample, and linear quantisation. |
Speech Model | A Data Type representing the Speech Descriptors characteristic of a speaker used to generate the Personal Status Display’s synthetic speech. |
Speedometer Data | A Data Type representing the speed of a CAV as measured by the sensor. |
Steering Wheel | |
– Command | A Data Type representing the command issued to the Steering Wheel by the Motion Actuation Subsystem after interpreting an AMS-MAS Command. |
– Feedback | A Data Type representing the Steering Wheel’s response to the AMS Command Interpreter in response to a Steering Direction Command. |
Subsystem | A high-level subdivision of a CAV. |
Text | A series of characters drawn from a finite alphabet represented using a Character Set. |
– Recognised | The Text produced by a speech recogniser. |
– Refined | Text resulting from the Language Understanding AIM’s refinement of Recognised Text produced by a Speech Recognition AIM. |
Traffic | |
– Rules | A Data Type representing the traffic rules applying to an Environment as extracted from the local Traffic Signals based on the local traffic rules. |
– Signals | A Data Type representing the traffic signals on a road and around it, their Spatial Attributes, and the semantics of the traffic signals. |
Trajectory | A Data Type representing a sequence of Spatial Attitudes and the expected time each Spatial Attitude will be reached. |
Ultrasound | A Data Type representing analogue signals generated by information captured by an ultrasonic sensor, an active time-of-flight sensor typically operating in the 40 kHz to 250 kHz range. |
– Data | A Data Type representing the Data provided by an ultrasonic sensor. |
– Scene Descriptors | A Data Type representing the Visual Data captured by Ultrasound and produced by the Ultrasound Scene Description AIM using previous Basic Environment Representations. |
Visual | A Data Type representing analogue signals generated by information perceptible by a human using the sense of sight. |
– Data | A Data Type representing the Visual Data captured by a Visual sensor. |
– Object | A Data Type representing a visual object and associated metadata. |
– Scene | A Data Type representing a visual scene. |
– Scene Descriptors | A Data Type representing the Visual Objects of an Environment, their Spatial Attitudes, and associated Visual Scene Geometry. |
Waypoint | The coordinates of a point on an Offline Map. |
Wheel Motor | |
– Command | A Data Type representing the command issued to the Wheel Motors by the Motion Actuation Subsystem after interpreting an AMS-MAS Command. |
– Response | A Data Type representing the Wheel Motors’ response to AMS Command Interpreter in response to a Wheel Motor Command. |
Table 2defines the Terms used in this Technical Specification with a capitalised first letter that are not already included in Table 1.
Note: To concentrate in one place all the Terms that are composed of a common name followed by other words (e.g., the word Data followed by one of the words Format, Type, or Semantics), the definition given to a Terms preceded by a dash “-” applies to a Term composed by that Term without the dash preceded by the Term that precedes it in the column without a dash.
Table 18 – MPAI-wide Terms
Term | Definition |
Access | Static or slowly changing data that are required by an application such as domain knowledge data, data models, etc. |
AI Framework (AIF) | The environment where AIWs are executed. |
AI Model (AIM) | A data processing element receiving AIM-specific Inputs and producing AIM-specific Outputs according to according to its Function. An AIM may be an aggregation of AIMs. |
AI Workflow (AIW) | A structured aggregation of AIMs implementing a Use Case receiving AIW-specific inputs and producing AIW-specific outputs according to the AIW Function. |
Application Standard | An MPAI Standard designed to enable a particular application domain. |
Channel | A connection between an output port of an AIM and an input port of an AIM. The term “connection” is also used as synonymous. |
Communication | The infrastructure that implements message passing between AIMs. |
Component | One of the 7 AIF elements: Access, Communication, Controller, Internal Storage, Global Storage, MPAI Store, and User Agent |
Composite AIM | An AIM aggregating more than one AIM. |
Component | One of the 7 AIF elements: Access, Communication, Controller, Internal Storage, Global Storage, MPAI Store, and User Agent |
Conformance | The attribute of an Implementation of being a correct technical Implementation of a Technical Specification. |
– Testing | The normative document specifying the Means to Test the Conformance of an Implementation. |
– Testing Means | Procedures, tools, data sets and/or data set characteristics to Test the Conformance of an Implementation. |
Connection | A channel connecting an output port of an AIM and an input port of an AIM. |
Controller | A Component that manages and controls the AIMs in the AIF, so that they execute in the correct order and at the time when they are needed |
Data | Information in digital form. |
– Format | The standard digital representation of Data. |
– Type | An instance of Data with a specific Data Format. |
– Semantics | The meaning of Data. |
Descriptor | Coded representation of a text, audio, speech, or visual feature. |
Digital Representation | Data corresponding to and representing a physical entity. |
Ecosystem | The ensemble of actors making it possible for a User to execute an application composed of an AIF, one or more AIWs, each with one or more AIMs potentially sourced from independent implementers. |
Explainability | The ability to trace the output of an Implementation back to the inputs that have produced it. |
Fairness | The attribute of an Implementation whose extent of applicability can be assessed by making the training set and/or network open to testing for bias and unanticipated results. |
Function | The operations effected by an AIW or an AIM on input data. |
Global Storage | A Component to MPAI Store data shared by AIMs. |
AIM/AIW Storage | A Component to MPAI Store data of the individual AIMs. |
Identifier | A name that uniquely identifies an Implementation. |
Implementation | 1. An embodiment of the MPAI-AIF Technical Specification, or
2. An AIW or AIM of a particular Level (1-2-3) conforming with a Use Case of an MPAI Application Standard. |
Implementer | A legal entity implementing MPAI Technical Specifications. |
ImplementerID (IID) | A unique name assigned by the ImplementerID Registration Authority to an Implementer. |
ImplementerID Registration Authority (IIDRA) | The entity appointed by MPAI to assign ImplementerID’s to Implementers. |
Instance ID | Instance of a class of Objects and the Group of Objects the Instance belongs to. |
Interoperability | The ability to functionally replace an AIM with another AIW having the same Interoperability Level |
– Level | The attribute of an AIW and its AIMs to be executable in an AIF Implementation and to:
1. Be proprietary (Level 1) 2. Pass the Conformance Testing (Level 2) of an Application Standard 3. Pass the Performance Testing (Level 3) of an Application Standard. |
Knowledge Base | Structured and/or unstructured information made accessible to AIMs via MPAI-specified interfaces |
Message | A sequence of Records transported by Communication through Channels. |
Normativity | The set of attributes of a technology or a set of technologies specified by the applicable parts of an MPAI standard. |
Performance | The attribute of an Implementation of being Reliable, Robust, Fair and Replicable. |
– Assessment | The normative document specifying the Means to Assess the Grade of Performance of an Implementation. |
– Assessment Means | Procedures, tools, data sets and/or data set characteristics to Assess the Performance of an Implementation. |
– Assessor | An entity Assessing the Performance of an Implementation. |
Profile | A particular subset of the technologies used in MPAI-AIF or an AIW of an Application Standard and, where applicable, the classes, other subsets, options and parameters relevant to that subset. |
Record | A data structure with a specified structure |
Reference Model | The AIMs and theirs Connections in an AIW. |
Reference Software | A technically correct software implementation of a Technical Specification containing source code, or source and compiled code. |
Reliability | The attribute of an Implementation that performs as specified by the Application Standard, profile, and version the Implementation refers to, e.g., within the application scope, stated limitations, and for the period of time specified by the Implementer. |
Replicability | The attribute of an Implementation whose Performance, as Assessed by a Performance Assessor, can be replicated, within an agreed level, by another Performance Assessor. |
Robustness | The attribute of an Implementation that copes with data outside of the stated application scope with an estimated degree of confidence. |
Scope | The domain of applicability of an MPAI Application Standard |
Service Provider | An entrepreneur who offers an Implementation as a service (e.g., a recommendation service) to Users. |
Standard | A set of Technical Specification, Reference Software, Conformance Testing, Performance Assessment, and Technical Report of an MPAI application Standard. |
Technical Specification | (Framework) the normative specification of the AIF.
(Application) the normative specification of the set of AIWs belonging to an application domain along with the AIMs required to Implement the AIWs that includes: 1. The formats of the Input/Output data of the AIWs implementing the AIWs. 2. The Connections of the AIMs of the AIW. 3. The formats of the Input/Output data of the AIMs belonging to the AIW. |
Testing Laboratory | A laboratory accredited to Assess the Grade of Performance of Implementations. |
Time Base | The protocol specifying how Components can access timing information |
Topology | The set of AIM Connections of an AIW. |
Use Case | A particular instance of the Application domain target of an Application Standard. |
User | A user of an Implementation. |
User Agent | The Component interfacing the user with an AIF through the Controller |
Version | A revision or extension of a Standard or of one of its elements. |
Zero Trust | A cybersecurity model primarily focused on data and service protection that assumes no implicit trust. |