Combat Simulator Research Articles

Empowering Military in Tactical and Warfare Area with Virtual Reality Technology: A Systematic Literature Review

The rapid advancement of virtual reality technology offers numerous real-world benefits across various sectors worldwide, including the military. As early adopters of this technology, the military has found multiple medical and practical applications. However, the research contributions of virtual reality technology, particularly in practical military applications, remain limited. This is primarily due to limited data availability and a lack of interest from researchers and military institutions. To investigate this issue, the authors are conducting a systematic literature study focused on practical military virtual reality, specifically tactical and combat operations. Following the PRISMA framework and employing searching and inclusion-exclusion techniques, the authors identified twenty-five relevant research outputs that extensively discuss these topics, both qualitatively and quantitatively. Notably, fifteen of these studies focus on combat and weapon training simulators, and interestingly, researchers are beginning to integrate other technologies such as robotics, big data, haptics, body area networks, and signal processing. The majority of the quantitative research conducted in this area has demonstrated success, with eight out of ten papers showing positive outcomes. To improve research quality, the authors propose two main solutions: implementing combat and weapon training within the military system and encouraging innovative and in-depth research in this domain. In conclusion, the analyzed virtual reality products can serve as a platform for military forces to support personnel in enhancing and maintaining their personal development and skills.

Comparing Team Performance Constructs Involved in Ground Combat and a Ground Combat Simulator

This paper aims at exploring whether a single team performance management system could effectively monitor team communication within active firefights in both real and simulated environments. While individual skills training in military settings has undergone extensive research, work focused on contrasting team constructs within real and simulated combat has seen comparatively little development. One hour of firefight footage taken from US Army engagements and one hour of firefight footage taken from groups using the ground combat simulator ARMA 3 were reviewed. Analysis revealed that the team metrics recorded by team performance measurement system are similar in quality and quantity. While this was an early exploratory study, these preliminary results support the proposition that teamwork in real and simulated ground combat environments is similar enough to use common metrics between them. These results may indicate a potential for more effective cross-training of military teams in simulated environments.

Hierarchical Adversarial Search Applied to Real-Time Strategy Games

Real-Time Strategy (RTS) video games have proven to be a very challenging application area for artificial intelligence research. Existing AI solutionsare limited by vast state and action spaces and real-time constraints. Most implementations efficiently tackle various tactical or strategic sub-problems, but there is no single algorithm fast enough to be successfully applied to big problem sets (such as a complete instance of the StarCraft RTS game). This paper presents a hierarchical adversarial search framework which more closely models the human way of thinking --- much like the chain of command employed by the military. Each level implements a different abstraction --- from deciding how to win the game at the top of the hierarchy to individual unit orders at the bottom. We apply a 3-layer version of our model to SparCraft ---a StarCraft combat simulator --- and show that it outperforms state of the art algorithms such as Alpha-Beta, UCT, and Portfolio Search in large combat scenarios featuring multiple bases and up to 72 mobile units per player under real-time constraints of 40 ms per search episode.

Building Placement Optimization in Real-Time Strategy Games

In this paper we propose using a Genetic Algorithm to optimize the placement of buildings in Real-Time Strategy games. Candidate solutions are evaluated by running base assault simulations. We present experimental results in SparCraft — a StarCraft combat simulator --- using battle setups extracted from human and bot StarCraft games. We show that our system is able to turn base assaults that are losses for the defenders into wins, as well as reduce the number of surviving attackers. Performance is heavily dependent on the quality of the prediction of the attacker army composition used for training, and its similarity to the army used for evaluation. These results apply to both human and bot games.

An Analysis of Model-Based Heuristic Search Techniques for StarCraft Combat Scenarios

Real-Time Strategy games have become a popular test-bed for modern AI system due to their real-time computational constraints, complex multi-unit control problems, and imperfect information. One of the most important aspects of any RTS AI system is the efficient control of units in complex combat scenarios, also known as micromanagement. Recently, a model-based heuristic search technique called Portfolio Greedy Search (PGS) has shown promisingpaper we present the first integration of PGS into the StarCraft game engine, and compare its performance to the current state-of-the-art deep reinforcement learning method in several benchmark combat scenarios. We then perform theperformance for providing real-time decision making in RTS combat scenarios, but has so far only been tested in SparCraft: an RTS combat simulator. In this same experiments within the SparCraft simulator in order to investigate any differences between PGS performance in the simulator and in the actual game. Lastly, we investigate how varying parameters of the SparCraft simulator affect the performance of PGS in the StarCraft game engine. We demonstrate that the performance of PGS relies heavily on the accuracy of the underlying model, outperforming other techniques only for scenarios where the SparCraft simulation model more accurately matches the StarCraft game engine.

A Behavior Optimization Method for Unmanned Combat Aerial Vehicles Using Matrix Factorization

One of the fundamental technologies for unmanned combat aerial vehicles and combat simulators is behavior optimization, which finds a behavior that maximizes the probability of winning a battle. With the advent of military science, combat logs became available, allowing machine learning algorithms to be used for the behavior optimization. Due to implicit attributes such as the experience of an operator that are not explicitly presented in log data, existing methods for behavior optimization have limitations in performance improvement. Furthermore, specific behaviors occur with low frequency, resulting in a dataset with imbalanced and empty values. Therefore, we apply a matrix factorization (MF) method, which is one of latent factor models and known for sophisticated imputation of empty values, to the behavior optimization problem of unmanned combat aerial vehicles. A situation-behavior matrix, whose elements are ratings indicating the optimality of behaviors in situations, is defined to implement the MF based method. Experiments for performance comparison were conducted on combat logs, in which the proposed method yielded satisfactory results.

A Hierarchical SVM Based Behavior Inference of Human Operators Using a Hybrid Sequence Kernel

To train skilled unmanned combat aerial vehicle (UCAV) operators, it is important to establish a real-time training environment where an enemy appropriately responds to the action performed by a trainee. This can be addressed by constructing the inference method for the behavior of a UCAV operator from given simulation log data. Through this method, the virtual enemy is capable of performing actions that are highly likely to be made by an actual operator. To achieve this, we propose a hybrid sequence (HS) kernel-based hierarchical support vector machine (HSVM) for the behavior inference of a UCAV operator. Specifically, the HS kernel is designed to resolve the heterogeneity in simulation log data, and HSVM performs the behavior inference in a sequential manner considering the hierarchical structure of the behaviors of a UCAV operator. The effectiveness of the proposed method is demonstrated with the log data collected from the air-to-air combat simulator.

Airborne Sensor Model Position Fidelity Determination for Combat Aircraft Simulators

Airborne sensors become a primary system in any combat program and the effectiveness depends on the coverage spectrum of the sensors and also the ability of flying machine. However evaluating the mission functionalities using sensors in flight involves tasks namely, Man Machine interface evaluation, Sensor function capability evaluation, System interface evaluation, Performance evaluation, pilot work load etc needs to carried out and the issues observed during the flight test needs to be cleared before accepting the system. It is one of the challenging task for any combat aircraft development program and proving require time, effort and also may lead to time and cost overrun. To minimize the effort one of the method adopted in recent flight development programs are using high fidelity sensor model to evaluate the mission function in the simulator which will reduce the actual test required in flight. Flight simulators during development of combat aircraft program have increased drastically in recent times with new technologies, possible to bring realism in a close room environment. However the success of any simulators depends on the fidelity of each subsystem integrated with in the simulator. Simulator contains simulation model which represents system in the aircraft world and the system which represents the outside world in a simulated manner. Mathematical based Avionics and weapon system Sensor simulation models is one of the major sub systems in any combat simulator and its level of usage depends on its fidelity. This paper proposes a unique and new methodology for evaluating the fidelity of simulated sensors used in the combat simulators. System identification technique allows generating mathematical model for dynamic systems having multiple input and output parameters. The developed model using System Identification Technique is a referent model through which the sensor model fidelity is evaluated.

This systems architect builds the most advanced F-16 combat simulators

Flying combat missions in a jet fighter requires reflexes that can respond to challenging terrain, shifting mission objectives, and hostile forces. Danny Jones is helping U.S. Air Force pilots develop those reflexes by building perhaps the most advanced military flight simulator in the world.

Self-Regulation and Performance in High-Fidelity Simulations: An Extension of Ego-Depletion Research

This article extends the research literature related to “ego-depletion.” Although numerous studies have focused on the self-regulatory failure associated with ego-depletion, the extant literature is generally characterized by relatively simple behavioral manipulations and dependent measures. Two studies are described that extend previous ego-depletion findings by employing a high-fidelity, customer service simulation as an ego-depleting manipulation (Study 1) and by using performance on a cognitively demanding naval combat simulator as a dependent measure (Study 2). Results of both studies show the generalizability of the effects of ego-depletion; the implications for self-regulatory failure in more naturalistic settings are discussed.

Speech acts, communication problems, and fighter pilot team performance

Two aspects of team communication, speech acts and communication problems, and their relation to team performance in a team air combat simulator were studied. The purpose was to enhance the understanding of how team performance is related to team communication. Ten Swedish fighter pilots and four fighter controllers of varying experience participated. Data were collected during fighter simulator training involving four pilots and one fighter controller in each of two teams. Speech acts were collapsed over seven categories and communication problems over five categories. Communication was studied from two perspectives: critical situation outcome and mission outcome. Some problems were closely related to particular speech acts. Speech act frequency, especially meta-communications and tactics, was highest when winning. However, the timing of tactics in critical situations needs further research. Communication problem frequency was highest for runs which ended equally. The most common problem was simultaneous speech, possibly because of the simulator radio system. The number of speech acts was related to enhanced performance but in a complex manner. Thus in order to work efficiently team members need to communicate, but to communicate sufficiently and at appropriate times. This work has applications for fighter pilot and controller team training and the development of communication standards.

Evaluation of Symptoms and Effects of Virtual Reality Based Flight Simulation and Enhanced Sensitivity of Postural Stability Measueres

In order to investigate level of experienced sickness symptoms in a VR based air combat simulator, a combined methodology was used. Before, during, and after simulation the participants repeatedly answered a VR sickness symptoms questionnaire (VRSQ). In addition, before and after simulation their postural stability was measured. In order to investigate if measurements of postural stability can be made more sensitive to changes in postural stability, during the measurements a sideways rolling wide angular visual flow was presented to half of the participants. Only low levels of VR-sickness symptoms and effects on postural stability were found. However, headache caused by the Head Mounted Display was a major concern for most participants. The presentation of a visual flow during the measurements of postural stability led to generally higher levels of postural instability, but did not increase the sensitivity of the measurements.

Modeling Air Combat by a Moving Horizon Influence Diagram Game

Thepaperdescribesamultistageinfluencediagramgameformodelingthemaneuveringdecisionsofpilotsinoneon-one air combat. The game graphically describes the elements of the decision process, contains a model for the dynamics of the aircraft, and takes into account the pilots’ preferences under conditions of uncertainty. The pilots’ game optimal control sequences with respect to their preference models are obtained by solving the influence diagram game with a moving horizon control approach. In this approach, the time horizon of the original game is truncated, and a feedback Nash equilibrium of the dynamic game lasting only a limited planning horizon is determined and implemented at each decision stage. To demonstrate the influence diagram game and its aspects, exampleswithapointmassaircraftmodelarecomputedandanalyzed.Thegamemodelpresentedinthepaperoffers a new way to analyze optimal air combat maneuvering and to develop an automated decision making system for selecting combat maneuvers in air combat simulators.

Training and Assessing Complex Decision-Making in a Virtual Environment

The current report describes a procedure for training and assessing complex decision-making in a virtual environment. Focusing on small unit leaders, 7 experienced and 7 inexperienced Army platoon leaders performed missions in a combat simulator, where they were required to direct the activities of 3 subordinate leaders and computer-generated forces in 4 different operations in a virtual urban setting. Objective and subjective assessments of the training value of the simulations showed that both experienced an inexperienced platoon leaders improved their decision-making across the four missions, and both groups rated this "virtual environment" training procedure as useful and positive. Lessons learned and implications for designing similar training protocols for other domains are discussed.

TRAINING AND ASSESSING COMPLEX DECISION-MAKING IN A VIRTUAL ENVIRONMENT

The current report describes a procedure for training and assessing complex decision-making in a virtual environment. Focusing on small unit leaders, 7 experienced and 7 inexperienced Army platoon leaders performed missions in a combat simulator, where they were required to direct the activities of 3 subordinate leaders and computer-generated forces in 4 different operations in a virtual urban setting. Objective and subjective assessments of the training value of the simulations showed that both experienced an inexperienced platoon leaders improved their decision-making across the four missions, and both groups rated this “virtual environment” training procedure as useful and positive. Lessons learned and implications for designing similar training protocols for other domains are discussed.

Virtual Environments as a Multi-Modal “Real World” Laboratory for Training

This panel focuses on applied R & D that seeks to employ and extend theory in VE-system development while maintaining a clear focus on end-user requirements. The efforts described in this panel will demonstrate the power and effectiveness of applying Virtual Technologies and Environments (VIRTE) to training. VIRTE will focus on developing two basic elements of VE training technology: (1) improving the quality of interaction provided by VE, and (2) applying advanced training aids and methodologies. Quality interaction is essential for making VE usable for extended training and for applying VE technology to build combat simulators. Advanced training aids and methodologies will be developed to derive full benefit from the flexible new medium provided by VE technologies.

Decision Theoretical Approach to Pilot Simulation

We simulate and analyze pilot decision making in one-on-one air combat by using an ine uence diagram. Unlike most of the existing approaches, an ine uence diagram graphically describes the factors of a decision process and explicitly handles the decision maker’ s preferences under conditions of uncertainty. In the pilot decision model, the possible combat situations related to each maneuver alternative are associated with a probability and a utility. Ine uence diagram analysis produces a probability distribution of the overall utility that represents the successfulness of a maneuver and gives information to make rational maneuvering decisions. Sensitivity analysis determines the impacts of different factors on the outcome of the maneuvering decision. The effects of sensor information that will reduce the uncertainty of the model are evaluated with Bayesian reasoning. The model can be utilized in the analysis of a single decision situation or as an automated decision-making system that selects combat maneuvers in air combat simulators.

Integration of manned simulation and flight test into operational testing and evaluation

A basic outline is presented for integration of a manned simulation test program with a flight-test program to accomplish the operational testing and evaluation of a fighter aircraft or a specific fighter weapon subsystem. A description of and the requirements for an operational test are given. The intrinsic advantages and disadvantages of operational flight testing and manned simulation are explained. The McDonnell Aircraft Company's manned aerial combat simulator is briefly described along with the benefits of using a simulation to support an operational test. A method of integrating flight test and manned simulation to compensate for their inherent limitations is also presented. This integration provides for a better overall test program than would be possible using either method alone. Issues addressed include the use of a manned simulator for training test participants and as a method of significantly expanding the analytical data base. A sample test matrix and scenario are presented. Validation between simulation and flight test results is discussed. Analytical issues addressed include possible measures of effectiveness to be collected and analyzed during both simulation and flight test.

Highly parallel processors in military systems

Parallelism has found its way into programmable processors as well as dedicated engines such as FFT and digital filters. However, choices of machine architecture are still open. We have evaluated two contrasting types to test their versatility and to compare their performance on algorithms related to military applications. Fine-grain SIMD, and coarse-grain MIMD machines (Mil-DAP and Transputer arrays) have been applied to a spectrum of problems including FFT, two-dimensional operators, associative processing, linear assignment, sorting, dynamic programming and ray tracing. These relate to military needs in spectrum analysis and image correlation, feature extraction from images, ESM, tracking with netted radars, speech recognition and terrain intervisibility. Possibilities for parallelism in combat simulators are also being examined. Each type of processor has been proved versatile and much more powerful than conventional sequential machines. DAP has the advantage on regular low precision algorithms, and on assignment and sorting operations where scatter, gather and shift operations are important. Transputer arrays will (when the T800 version is available) offer a better capability for floating point arithmetic and less regular tasks. The chief conclusion is that both architectures are extremely versatile and VLSIcompatible, and that choices between them will more often hinge on the cost of a minimal system, the quality of the development software and the portability of code, rather than on the fundamental properties of the machine topology.

An Application of Manned Simulation in Crew Station Conceptual Development

The McDonnell Aircraft Company's Manned Air Combat Simulator is being used in the early design and evaluation phases of an advanced real-time reconnaissance aircraft. The cockpit arrangement and control logic have been implemented in the engineering development simulator. To date there have been two formal human factors evaluations of the system under simulated operational conditions. This presentation outlines the procedures used, the results, and their impact upon the design.