IEEE - Aerospace and Electronic Systems - July 2021 - 67

Munir et al.
Figure 3.
CPCG architecture.
Level 5-User Refinement. An element of knowledge
management and provides adaptive determination of
access control and display of information to support decision
making via human-machine interface.
Level 6-Mission Management. An element ofsystems
management and enables spatial-temporal control of
assets (e.g., airspace operations), route planning, and goal
determination to support decision making while considering
social, economic, and political constraints.
CYBER-PHYSICAL COMMAND-GUIDED (CPCG)
ARCHITECTURE
As the name implies, the CPCG architecture combines the
elements of the static (DFD) and dynamic (DIG) methods
from the late 1990s with the user-focused updates from
the JDl/DFIG in the 2000s for " command guided " systems,
such as swarm of unmanned domain systems (UxS)
(where x can be space, air, ground, surface, or undersea).
The CPCG architecture seeks to not only utilize the distributed
data fusion but also the distributed diffusion of
command to cyber-physical elements. Hence, the CPCG
architecture leverages the cloud and edge processing to be
able to collect data for IF, affords consumption and analytics
by operator infusion (OI), and then direct needs for
control diffusion (CD). The CPCG architecture takes
advantage of centralized command with distributed execution
by expressing goals and having the contextual agents
develop the sensing and action strategy.
The AI agents in CPCG architecture mine data, process
and fuse information, and store the results in a
JULY 2021
distributed space. The AI agents ofCPCG architecture are
assisted with three different types of data fusion, viz., IF,
OI, and CD. Organization of these three data fusion agents
induces different AI architectures as depicted in Figure 3.
These fusion techniques can be characterized based on the
data they provide and/or operate on.
(1) Information Fusion (IF). The IF agent mines and
processes physical data/information that originates in
the external environment. The IF can be assisted with
different AI/ML approaches, such as symbolic, probabilistic,
connectionist, analogistic, evolutionary, and
possibilistic (please refer to Section " Alignment of
Multilevel Fusion and AI " for types ofAI and ML).
(2) Operator Infusion (OI). The OI agent assimilates
human-in-the-loop within CPCG architecture for
interpreting and assessing processed information/
data, specifying mission objectives, interacting with
CPCG agents for ML and fusion/diffusion augmentation
and refinement with social knowledge, and
decision making. The UDOP enables the human
operator to direct his/her decision making at the
highest level of establishing or updating mission
objective, or to expand his/her decision making to
involve details of instantaneous coordination among
engagement groups within CPCG architecture, or
even to decision making at the level of individual
sensors, weapons, actuators, and platform management.
This rich human operator access and interaction
with CPCG architecture at different levels
suggest that the human operator is infused into the
CPCG architecture.
IEEE A&E SYSTEMS MAGAZINE
67
IEEE - Aerospace and Electronic Systems - July 2021

Table of Contents for the Digital Edition of IEEE - Aerospace and Electronic Systems - July 2021
