ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

Agent-Based Approaches for Behavioural Modelling in

Military Simulations
Gaurav Chaudhary
Institute for Systems Studies and Analyses, DRDO, Delhi-110054, India
[email protected]
[email protected]

ABSTRACT
Behavioral modeling of combat entities in given. At the same time, the maturity of ABM in
military simulations by creating synthetic agents agent-based applications has also been
in order to satisfy various battle scenarios is an considered.
important problem. The conventional modeling Keywords: ABM, CGF, Behavior Modeling
tools are not always sufficient to handle complex
situations requiring adaptation. To deal with
this Agent-Based Modeling (ABM) is employed, 1. INTRODUCTION
as the agents exhibit autonomous behavior by
adapting and varying their behavior during the Agent-based modeling comprising of interacting
course of the simulation whilst achieving the autonomous agents have been used to develop
goals. Synthetic agents created by means of models for a wide range of applications.
Computer Generated Force (CGF) is a Applications range from modeling agent
relatively recent approach to model behavior of behavior in voting during elections, to predicting
combat entities for a more realistic training and price variations within stock market trading,
effective military planning. CGFs, are also from modeling the growth and decline of ancient
sometimes referred to as Semi- Automated civilizations to modeling the growth of bacterial
Forces (SAF) and enables to create high-fidelity colonies etc.
simulations. Agents are used to control and The human behavior has been modeled in a very
augment the behavior of CGF entities, hence basic manner in the synthetic battlefield
converting them into Intelligent CGF (ICGF). environment. The latest technological advances
The intelligent agents can be modeled to exhibit made in the agent-based approaches, applied to
cognitive abilities. military wargaming and simulation offers
For this review paper, extensive papers on state- promising advantage in behavioral modeling
of-the-art in agent-based modeling approaches while improving training effectiveness at the
and applications were surveyed. The paper same time. This advantage is driven by
assimilates issues involved in ABM with CGF as emerging trends in learning using agent-based
an important component of it. It reviews modeling and essentials from the field of
modeling aspects with respect to the inter- computer generated forces (CGF), arti ficial
relationship between ABM and CGF, which is intelligence, game-theory etc. The agents are
required to carry out behavioral modeling. autonomous entities which observe through
Important CGFs have been examined and a list sensors and act upon the environment using
with their significant features is given. Another actuators and direct their activity towards
issue that has been reviewed is that how the achieving goals. To be called intelligent, an
synthetic agents having different capabilities are agent also has to be reactive, proactive and
implemented at different battle levels. Brief social; meaning it must be able to react to
mention of state-of-the-art integrated cognitive changes in the environment, pursue goals and be
architectures and a list of significant cognitive able to communicate with other agents
applications based on them with their features is (Wooldridge 2004). Intelligent agents model

IJCTA | Nov-Dec 2015 966

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

both individual human reasoning and team An emergent phenomenon can have properties
behavior, performing tasks without any human that are decoupled from the properties of the
intervention as in constructive simulations. part. The emergent phenomena can be counter-
intuitive and thus it can be difficult to
understand and predict. Eg. In a traffic jam,
taking place due to interactions between
individual car drivers, a car may be moving in
the direction opposite to that of the cars that
cause it.

1.2 Issues in Military Modeling and Simulation

It is imperative to understand that the simulation

leads to the output being a range of predictions,
or a richer learning experience which is
Figure 1. Intelligent Agent facilitated by ABM. Behavioral modeling of
combat entities needs to be done adequately for
The traditional modeling tools are not always
the simulated battle scenarios.
sufficient when complex adaptive systems are to
be designed. To make realistic synthetic C2 • Simulation as a Predictive tool: Due to
forces the ABM approach provides the limited behavioral modeling, trainees
following features: learn the range of the simulated
• To behave in a pro-active manner. behaviors in a short period of time.
• Able to dynamically modify mission Learning the simulated range of
plans in response to a situational behavior results in learning to predict the
contingency. training system's response.
• Able to collaborate in team/group • Simulation as a Learning tool: Using
decision-making and behavior. simulation so as to find out that how
The ABM approach promises to lend an high-level properties and behaviors of a
increased ability to tailor training programs to system emerge out of low-level rules
the specific needs of military personnel as there applied to individual agents results in
is a need to train soldiers across all phases of learning. Again, being able to study the
battle with diverse missions requiring different emerging collective behavior of the
set of skills and competencies. group is important because it enables
commanders and their subordinates to
1.1 The Conceptual Shift test a wide range of individual and
collective behavioral rules and to
The conceptual shift in ABM is due to the fact observe if and how robustly the rules
that rather than finding a mathematical lead to the desired collective level
description of an entire system, the effort here is outcome.
to find a low-level rule based specification of the
behavior of individual agents making up that
1.3 Military Modeling & Simulation Paradigms: A
system (Ilachinski 1997). Casti (1997) argues
Comparison
that agents should contain both base-level rules
for behavior as well as a higher-level set of rules The military modeling and simulation paradigms
to change the rules. The base level rules provide have been broadly classified into SDS (System
responses to the environment while the rules to Dynamics Simulation), DES (Discrete Event
change the rules provide adaptation. Simulation and ABS (Agent-Based Simulation).
Emergent phenomena results from the The agent-based simulation can be further
interactions of individual entities. By definition, classified into Context based reasoning and BDI
it cannot be reduced to the system's parts: the (Belief, Desire, Intention) reasoning. Some of
overall phenomena is more than the sum of its the representative applications are: A system
parts because of interactions among the parts.

IJCTA | Nov-Dec 2015 967

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

dynamics simulation model for a four-rank of a number of agents which interact with one
military workforce [1], Application of RT- another in the same environment (Wooldridge
DEVS in military [2] and Military applications 2002); each of the agents has its own strategy in
of agent-based simulations [3] respectively. order to achieve its objective. Due to the MAS
Jay Forrester, the founder of SDS, defined it as structure, ABS has the ability to be autonomous,
the study of information feedback characteristic responsive, proactive and social (Jennings et al.
of industrial activity to show how organizational 1998). There are two approaches to ABS [6]:
structure, amplification (in policies) and time Context Based Reasoning (CxBR) and BDI
delay (in decision and action) interact to reasoning. CxBR is a reasoning paradigm for
influence the success of enterprise [4]". In other representation of tactical behavior in agents
words, SDS is an approach used to understand (Gonzales and Ahlers 1998; Gallagher et al.
the dynamic behaviour of complex systems over 2000; Gonzales et al. 2008). The motivation
time at aggregate level. The modeling effort is behind CxBR is the realization that people only
usually a set of state equations. DES is a use a fraction of their knowledge at any given
dynamic, stochastic and discrete simulation time. The idea is to divide the knowledge into
technique (Banks et al. 2005). In DES, contexts in order to limit the number of
simulation time plays an important role possibilities for the action selection process. For
(dynamic model) and DES is a stochastic model example, an agent representing a military
as it consists of random input components. In platoon will require a different set of capabilities
addition, DES is discrete because it models a and knowledge when it is performing an attack
system in which the state of entities in the versus when moving along a road. In BDI
system change at a discrete time (Carson 2003). reasoning, set to work, the agent pursues its
The DES model uses a top-down approach to given goals, adopting the appropriate plans,
model system behaviour. One of the advantages according to its current beliefs of the state of the
of using DES [5] compared to other simulation world, so as to perform the role it has been
techniques such as SDS or ABS is it models a given.
system in an ordered queue of events (Siebers et
al. 2010). Another advantage of DES is that it Top-Down/ Discrete/ Reactive,
Bottom-Up Continuous Pro-Active
has the ability to be combined with other
simulation methods, such as continuous
simulation (Zaigler et al. 2000) and agent-based SDS Top-Down Continuous Reactive
simulation for studying complex systems DES Top-Down Discrete Reactive
(Parunak et al. 1998; Darley et al. 2004). Note: Can be
combined with
Entities in DES are not autonomous. This issue Continuous and
of autonomy (Bakken 2006) which relies upon Agent-Based
the capability to make independent decisions has Simulations
made DES a less preferred choice to represent ABS Bottom-Up Discrete Reactive,
Note: AnyLogic Pro-Active
complex human behaviour such as proactive s/w package
behaviour (Borshchev and Filippov 2004). In supports hybrid
DES, people are usually implemented as continuous/discrete
logic
resources or passive entities. Passive entities are
unable to initiate events in order to perform
Table 1: Modeling and simulation paradigms
proactive behaviour. Therefore, a proactive comparison
event that requires self-initiated behaviour by an
individual entity is difficult to implement in Reactive behaviour is a response to the
DES (Borshchev and Filippov 2004). This is environment i.e. the employees respond to
where agent-based simulations have a decisive requests from their customers when they are
edge in modeling proactive entities. These available. Proactive behaviour relates to
systems have many interacting entities and non- personal initiative in identifying and solving a
linear interactions among them. The problem. Many agent-based software and
corresponding computational technique is called toolkits have been developed and are widely
multi-agent simulation (MAS). A MAS consists used. Packages such as Repast, SWARM,

IJCTA | Nov-Dec 2015 968

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

NetLogo, SDML, Jade, MASON, and AnyLogic Battle Synthetic Features

level Forces
are quite extensive and have been well used by
the agent- based modeling community for years. Tactical IFOR Efficient and responsive to dynamic
changes.
Strategic CFOR Extends the IFOR capabilities to
higher echelons and incorporates
2. TYPES OF SYNTHETIC AGENTS IN A the communication and command
BATTLEFIELD SIMULATION functions necessary to operate at
these levels. Reasoning about
interactions and changes in the
The types of synthetic agents with different planning/replanning.
functional capabilities required in a battlefield
simulation are as follows: Table 2: Battle Levels and Applicable Intelligent Agents
• Semi-automated forces (SAF) provide
relatively simple computer-generated 3. AGENT-BASED SIMULATION
entity behaviors, and then depend on ENVIRONMENT WITH CGF COMPONENT
human operators to provide higher level
guidance. ABM provides a natural description of a system.
• Intelligent Forces (IFORs) attempt to It is flexible as it is easy to add more agents to
provide intelligent autonomous entity an agent-based model. The CGF component
behavior without human controllers. provides the basic synthetic agents which
• Command Forces (CFORs) attempt to interact among themselves to meet the desired
automate the commanders that sit above goals while operating in the synthetic
the entity level providing automated environment. The physical aspects [9] represent
models of command decision makers the movement and state of platforms (objects) in
and automated tasking for entities. the simulation, including such aspects as
maximum speed and the actions that can be
SAF systems provide the simulation of performed in the world. The behavioral aspects
individual platforms and small units. IFOR of a synthetic force platform determine where,
entities, though they do have deliberation when and how it performs the physical actions,
capabilities, are more focused on reaction than that is, its behavior (ritter et. al, 2002). There are
planning. CFOR extends this to incorporate lot of constructive simulation agent-based
explicit, virtual representation of command environments with a CGF component.
nodes, command and control (C2) information U.S. Department of Defense Modeling and
exchange, and command decision-making. The Simulation defines CGF as "A generic term used
responsibilities of a command entity (CE) differ to refer to computer representations of entities in
markedly from those of lower echelon units [7]. simulations which attempts to model human
In contrast to the issues faced by vehicle or behaviour suffciently so that the forces will take
platoon level units, CFORs must model the some actions automatically (without requiring
decision making from a broader perspective and man-in-the-loop interaction)". Whereas a
over longer time scales. Whereas vehicle level synthetic environment as given by Dompke
decision making tends to be more reactive in (2001) [10] is "Internetted simulations that
nature, higher echelon units must deliberate represent activities at an appropriate level of
about alternative courses of action and detect realism. These environments may be created by
harmful (or beneficial) interactions between within a single computer or over a distributed
subordinate units and enemy forces. network connected by local and wide area
Eg. Soar/CFOR [8] extends the Soar/IFOR networks and augmented by realistic special
capabilities to higher echelons and incorporates effects and accurate behavioural models."
the communication and command functions
necessary to operate at these levels. Soar/IFOR 3.1 Modeling of CGFs
is an implemented system for controlling
intelligent pilot agents for participation in Modeling of CGFs for implementing an
simulated battlefield exercises. intended behavior, requires a force aggregating
or deagregating process. Force Aggregating [11]

IJCTA | Nov-Dec 2015 969

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

could be described as forming a new CGF entity 3.1.2 CGF as a Simulation and Wargame
from two or more existing CGF units all of
whose numeric parameters are redefined by the The application Close Action ENvironment
Commander of the new CGF entity. Similarly, (CAEN) [16] can be run as either a simulation
Force Deagregating is described as forming two and wargame. It is both a means of simulation of
or more new CGF entities from a single one. weapons effects and an interactive wargame
The parameters of the new CGF entities should (operational analysis) between opposing forces
be defined by the old CGF Commander before of up to platoon level strength. It can operate
the deagregating takes place. In the case of either as an automatically replicated constructive
Force Aggregating, the military hierarchy simulation with no user intervention, or as an
coherence is maintained by comparing the old interactive game in which two or more
CGF units Commanders level and assigning the independent players control the actions of their
command to the highest in rank; in case of own forces. Thus a combination of wargame and
deagregating, the old CGF unit Commander simulation is more amenable to cater to the
chooses the new CGF unit Commanders changing requirements for one-on-one to
assigning to each of them a Command position. divisional and corps battles.
The aggregation /deaggregation process enables
to simulate the desired effects. Eg. The paper 3.2 Examples of CGFs
[12] describes the ABM approach used to
simulate strategic effects at the operational level Some of the significant CGFs developed so far,
of war. CGFs have also been modeled in a with their features have been listed in the
Synthetic Theatre Of War (STOW) where CGFs following table.
and intelligent synthetic agents are brought to
theater-level exercises [13]. STOW [14] is a S. Architecture Features
no
program to construct synthetic environments for
1. JointSAF U.S. Tri-service simulation system,
numerous defence functions. Its primary (JSAF) including detailed modeling of air, land,
objective is to integrate virtual simulation and sea assets. JSAF lacks a
(troops in simulators fighting on a synthetic comprehensive dismounted infantry
model.
battlefield), constructive simulation (war 2. MOD-SAF ModSAF simulates an extensive list of
games), and live maneuvers to provide a training [17] entities. For fixed wing aircraft, it
environment for various levels of exercise. simulates the F-14D, MIG-29, A-10
and SU-25. For rotary wing aircraft, it
simulates the AH-64, OH-58D, Mi-24,
3.1.1 CGF as Battle Force Representation and and Mi-28. For its ground forces,
Simulation Modeling ModSAF can simulate tanks (M-I and
T-72), infantry fighting vehicles (M-2
Current and planned CGF capabilities were and BMP), ADA (ZSU-23/4), &
dismounted infantry. Enhancements
evaluated [15] on the basis of two evaluation could result in the support of additional
criteria: Battle Force representation and physical models such as Cavalry,
Simulation Modeling features. Howitzers, Mortars, Mine- fields, CSS,
Scud Patriot.
Battle force representation assesses the ability of 3. OTB-SAF OTB primarily caters for land-based
the CGF to represent different types of weapon [18] behaviors and interactions, however it
systems/military equipment for all services (Air does include the representation of air
Force, Army, Navy); levels of military and sea assets. In addition, OTB
includes specialized Dismounted
organizations (platoon through Division); Infantry SAF (DISAF) extensions and
Command, Control, Communications, and behaviors developed to support US
Intelligence (C3I); behaviors of entities and Army simulations.
units; tactics and doctrine. Simulation modeling 4. ONESAF A composable, next generation
[19] simulation architecture supporting both
features characterize simulation models and data Computer Generated Forces (CGF) and
bases used to represent system performance and SAF operations. Capable of replacing
the environment. US Army legacy entity-based
simulations: BBS, OTB/ ModSAF,
CCTT /AVCATT SAF, Janus (A&T),
JCATS MOUT.

IJCTA | Nov-Dec 2015 970

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

5. VR-Forces VR-Forces is MAK's complete include procedural reasoning system (PRS),

(COTS) simulation solution a powerful and
flexible Computer Generated Forces
dMARS, JACK, 3APL, Jason, JADE, JADEX,
(CGF) platform to fill your synthetic JAM, AgentSpeak(L),and UM-PRS. BDI is
environments with urban, battlefield, designed to be situated, goal directed, reactive,
maritime, and airspace activity. It can and social. This means a BDI agent is able to
be used as a threat generator for
training and mission rehearsal systems, react to changes and communicate in their
a synthetic environment for embedded environment, as it attempts to achieve
experimentation, or an engine to its goals.
stimulate C4I systems.

Table 3: Some of the notable CGFs

4.2 Examples of Cognitive Architecture Based
Applications
4. COGNITIVE ARCHITECTURE
Some of the implementations based on the
This section talks briefly about the cognitive various architectures are listed in the table
architecture, which is the blueprint for below:
intelligent agents. A cognitive architecture
S. Archi- Application Features
proposes (artificial) computational processes no Tecture
that act like cognitive systems (human). It is an 1. SOAR Soar-RWA (1) Models pilot
approach that attempts to model behavioral as [23]: Planning, agents for a company
well as structural properties of the modeled teamwork, and of helicopters.
intelligent (2) A command agent
system. In military simulation, relatively little behavior for that makes decisions
attention has been given to modeling human synthetic rotary and plans for the
cognition, and how this affects human behavior wing aircraft helicopter company.
(3) An approach to
and thereby affecting tactical decision making. teamwork that enables
Modeling cognitive behavior, includes the pilot agents to
variations like (timing, errors, physiological coordinate their activ-
biases) of the human behavior. ities in accomplishing
the goals of the
A detailed account of the state of the art company.
research in the field of integrated cognitive TacAir-Soar (1) An intelligent,
architectures [20] is given as a review of six System [24]: rule-based system that
cognitive architectures, namely Soar, ACT-R, Automated generates believable
Intelligent Pilots human like behavior
ICARUS, BDI, the Subsumption architecture for Combat for largescale, distrib-
and CLARION. Another detailed chronology Flight uted military simula-
and evaluation for development of the cognitive Simulation tions.
(2) It accomplishes its
architectures is given in [21] & [22] mission b y integrating
respectively. a wide variety of
intelligent capabilities,
4.1 BDI Agents including real-time
hierarchical execution
of complex goals and
Current research in behavior modeling is plans, communication
directed towards BDI (Belief, Desire, Intention) and coordination with
humans and simulated
agents in command and control. The BDI entities, maintenance
intelligent agent as described here is an of situational aware-
autonomous piece of software, which has ness, and the ability to
explicit goals or desires to achieve, and is pre- accept and respond to
new orders while in
programmed with plans or behaviours to achieve flight.
these goals under varying circumstances. Such 2. ACT-R Steering Control A model of a take-off
an intelligent agent model is generally referred in a Flight in simulated single-
to as a BDI agent. Under the BDI model, agents Simulator Using engine propeller air-
ACT-R [25] craft, using ACT-R.
may be given pre-compiled behaviours, or they The paper explores the
may plan or learn new plans at execution time. use of iterative model
The implementations of the BDI architecture stress-testing to explo-

IJCTA | Nov-Dec 2015 971

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

re the minimally • How much confidence we have about

sufficient productions
and modules for the
modeling people's behavior credibly ?
take-off task. • To what extent we know about modeling
BDI Using Agent (1) The use of BDI social interaction among people ?
(JADE- Technology to agents in training a
X) Build a complex real-world
Real-World task: on-board fire As compared to system dynamics modeling,
Training fighting. Agent-based modeling does not as of yet have a
Application [26] (2)The trainee controls mature set of standard formalisms or procedures
the virtual character of
the commanding
for model development and agent representation.
officer. BDI-agents The absence due to the lack of models that were
are developed to gene- completely validated, the lack of references to
rate the behavior of all the
other officers involved
(3) Describe the complete model and what can be accepted as
design of the publishable results. Despite use in many fields,
application, the functi- agent-based simulations are criticised for having
onal and technical
requirements, and our
too many parameters. In other words,
experiences during understanding of the scope and sensitivities of
implementaion. model outputs for varying parameter choices is
BDI Modeling and Demonstrates the use limited. ABMS is more than having stochastic
(JACK) Simulation of of intelligent agent-
Tactical Team based team behaviour
modeling elements only. Classical mathematical
[27] modeling concepts in programming techniques such as linear and
simulating the armou- integer programming cannot be applied to
red tanks in a tactical optimize the settings for agent-based models,
masking scenario.
BDI Modeling Rules (1) A human behavior which are highly nonlinear and stochastic. It is a
(CoJA- of Engagement modeling tool that challenge that there is no data source against
CK) in supports tactics indep- which the model can be calibrated. For this
Computer endent representation model simulations are run hundreds or
Generated of ROE.
Forces [28] (2) ROE are defined as thousands of times to generate a distribution of
meta-knowledge that behavior, and behavior is compared with
act as a constraint on historical data to ensure that the model is
the tactical choices
selected by the
correctly calibrated.
synthetic entity.
6 CONCLUSIONS
Table 4: Cognitive Architectures and Applications
based on them. Intelligent CGFs helps in representation and
simulation of realistic military tactical
More interesting applications of the BDI behaviour, without the requirement of
intelligent agent concept is given in [29] namely, involvement of life of humans. More
the OASIS air traffic management system importantly, representing aggregated entities
prototype [30], the SWARMM air mission using CGF inclusive agent-based technology
simulation system [31], the IRTNMS network enables modeling of the required behaviour at a
management system [32] etc. fairly abstract level. At the time of execution,
these abstract specifications map to quite
5. AGENT-BASED MODELING: HOW complex behaviours which "emerge" during the
MATURE IT IS? running of the simulation.

Based on the survey paper [33] in the year 2009,

the challenges with respect to ABM have been
described as follows. Some important questions
become immediately apparent.

IJCTA | Nov-Dec 2015 972

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

REFERENCES [14] Timothy Lenoir. Programming theatres of war:

Gamemakers as soldiers. Latham, R. Bombs and
[1] Jun Wang. A system dynamics simulation model for Bandwidth: The emerging relationship between
a four-rank military workforce. 2007. information technology and security. New York: The
[2] Mohammad Moallemi, Gabriel Wainer, Antoine New Press. Draft chapter accessed on January, 14:2006,
Awad, et al. Application of rt-devs in military. In 2003.
Proceedings of the 2010 Spring Simulation [15] Wilbert J Brooks and Marguerite M Dymond.
Multiconference, page 29. Society for Computer Computer generated forces (cgf) assessment. In
Simulation International, 2010. SUMMER COMPUTER SIMULATION
[3] Thomas M Cioppa, Thomas W Lucas, and Susan M CONFERENCE, pages 315{319, 1996}.
Sanchez. Military applications of agent-based [16] J Adamson. The caen wargame for ootw
simulations. In Simulation Conference, 2004. applications. In 6th Conference on Computer Generated
Proceedings of the 2004 Winter, volume 1. IEEE, 2004. Forces and Behavioral Representation, 1996.
[4] Jay W Forrester. Industrial dynamics: a major [17] RB Calder, JE Smith, AJ Courtemanche, JMF Mar,
breakthrough for decision makers. Harvard business and Andy Z Ceranowicz. Modsaf behavior simulation
review, 36(4):37{66, 1958}. and control. In Proceedings of the Conference on
[5] Mazlina Abdul Majid. Human behaviour modelling: Computer Generated Forces and Behavioral
an investigation using traditional discrete event and Representation, 1993.
combined discrete event and agent-based simulation. [18] Ronald D Anderson and My V Baranoski. Onesaf
PhD thesis, University of Nottingham, 2011. test bed (otbsaf) automation. Technical report, DTIC
[6] Rikke Amilde Levlid, Anders Alstad, Ole Martin Document, 2005.
Mevassvik, Nico de Reus, Henk Henderson, Bob [19] Robert L Wittman Jr and Cynthia T Harrison.
vander Vecht, and Torec Luik. Two approaches to Onesaf: a product line approach to simulation
developing a multi-agent system for battle command development. Technical report, DTIC Document, 2001.
simulation. In Winter Simulation Conference, pages [20] Hui-Qing Chong, Ah-Hwee Tan, and Gee-Wah
1491{1502, 2013. Ng. Integrated cognitive architectures: a survey.
[7] R Calder, R Carreiro, J Panagos, G Vrablik, B Wise, Artificial Intelligence Review, 28(2):103{130, 2007}.
FL Chamberlain, and DP Glasson. Architecture of a [21] Vidar Engmo. Representation of human behavior
command forces command entity. In Proceedings of the in military simulations. 2008.
Sixth Conference on Computer Generated Forces and [22] Hui-Qing Chong, Ah-Hwee Tan, and Gee-Wah
Behavioral Representation. Orlando, FL, 1996. Ng. Integrated cognitive architectures: a survey.
[8] Jonathan Gratch. Task-decomposition planning for Artificial Intelligence Review, 28(2):103{130, 2007}.
command decision making. In Proceedings of the Sixth [23] Randall Hill, Johnny Chen, Jonathan Gratch, Paul
Conference on Computer Generated Forces and Rosenbloom, and Milind Tambe. Soar-rwa: Planning,
Behavioral Representation, STRICOM- DMSO, pages teamwork, and intelligent behavior for synthetic rotary
37{45, 1996}. wing aircraft. In Proceedings of the 7th Conference on
[9] John C Giordano, Paul F Reynolds Jr, and David C Computer Generated Forces & Behavioral
Brogan. Exploring the constraints of human behavior Representation, pages 12{14, 1998}.
representation. In Proceedings of the 36th conference [24] Randolph M Jones, John E Laird, Paul E Nielsen,
on Winter simulation, pages 912{920. Winter Karen J Coulter, Patrick Kenny, and Frank V Koss.
Simulation Conference, 2004. Automated intelligent pilots for combat flight
[10] Uwe Dompke. Computer generated forces- simulation. AI magazine, 20(1):27, 1999.
background, definition and basic technologies. [25] Sterling Somers and Robert L West. Steering
Technical report, DTIC Document, 2003. control in a flight simulator using act-r. In Proceedings
[11] Matteo Brandolini, Attilio Rocca, Agostino G of the international conference for cognitive modeling,
Bruzzone, Chiara Briano, and Petranka Petrova. Poly- 2013.
functional intelligent agents for computer generated [26] Michal Cap, Annerieke Heuvelink, Karel Van Den
forces. In Simulation Conference, 2004. Proceedings of Bosch, and Willem Van Doesburg. Using agent
the 2004 Winter, volume 1. IEEE, 2004. technology to build a real-world training application. In
[12] Richard K Bullock, Gregory A McIntyre, and Agents for games and simulations II, pages 132{147.
Raymond R Hill. Using agent-based modeling to Springer, 2011}.
capture airpower strategic effects. In Proceedings of the [27] Sanjay Bisht, Aparna Malhotra, and SB Taneja.
32nd conference on Winter simulation, pages 1739- Modelling and simulation of tactical team behaviour.
1746. Society for Computer Simulation International, Defence Science Journal, 57(6):853{864, 2007}.
2000. [28] Rick Evertsz, Frank E Ritter, Simon Russell, and
[13] RM Jones, JE Laird, and PE Nielsen. Moving David Shepherdson. Modeling rules of engagement in
intelligent automated forces into theater-level scenarios. computer generated forces. In Proceedings of the 16th
In Proceedings of the Sixth Conference on Computer Conference on Behavior Representation in Modeling
Generated Forces and Behavioral Representation, and Simulation, volume 7, 2007.
STRICOM-DMSO, pages 113{117, 1996}.

IJCTA | Nov-Dec 2015 973

Available [email protected]
 ISSN:2229-6093

Gaurav Chaudhary, Int.J.Computer Technology & Applications,Vol 6 (6),966-974

[29] Andrew Lucas and Simon Goss. The potential for

intelligent software agents in defence simulation. In
Information, Decision and Control, 1999. IDC 99.
Proceedings. 1999, pages 579{583. IEEE, 1999}.
[30] Magnus Ljungberg and Andrew Lucas. The oasis
air traffic management system. 1992.
[31] David McIlroy and Clinton Heinze. Air combat
tactics implementation in the smart whole air mission
model (swarmm). In Proceedings of the First
International SimTecT Conference. Citeseer, 1996.
[32] Anand S Rao and Michael P Georgeff. Intelligent
real-time network management. In Proceedings of the
Tenth International Conference on AI, Expert Systems
and Natural Language. Citeseer, 1990.
[33] Raymond Hill brian Heath and Frank
Ciarallo(2009). A survey of agent-based modeling
practices (january 1998 to july 2008). Technical report,
Journal of Artificial societies and Social Simulation,
2009.

CONTRIBUTOR

Mr. Gaurav Chaudhary received his M.E. in Computer

Science and Engineering from Indian Institute of
Science, Bangalore. He is working as Scientist in
Defence Research & Development Organisation
(DRDO) and his current interests includes agent-
based applications and rule-based systems.

IJCTA | Nov-Dec 2015 974

Available [email protected]