Automating the Acquisition of Tactical Knowledge for Military Missions (original) (raw)
Related papers
Modelling battle command with context-based reasoning
2013
An important aspect of simulation based training is the need for realistic computer generated forces. In typical systems for computer generated forces the entities can be instructed to perform simple tasks like "move along route" and "move into formation". Our objective is to make a simulation system that is capable of simulating the execution of a higher level operational order autonomously. In order to do this, the simulation system will have to understand and plan how to execute higher level commands like "seize area x" or "support unit y by fire", and be able to react to unplanned events according to doctrine. Such a system can be used both for training purposes and as a support tool when planning military operations.
Design and Implementation of CITKA, a Context Based Tactical Knowledge Acquisition System
2000
The CITKA system has been developed to facilitate the acquisition of the knowledge for military tactics; this is known to be one of the limiting factors in the development of computer generated forces. This acquisition is achieved via a query session between a subject matter expert (SME) and an intelligent system. Such a system has several advantages. The most important
Reasoning, Planning, and Goal Seeking for Small Combat Unit Modeling and Simulation
The current state of Modeling and Simulation (M&S) scenario creation is difficult, requiring too much time and effort on the part of Subject Matter Experts (SMEs) and analysts to produce scenarios that are sufficiently realistic for valid analysis, as well as a need for more realistic M&S agent behavior and decision making in simulation. Additionally, there also is a critical need for decision support tools to support Soldier and Small Unit (SU) decision making in the field. TSE is currently developing algorithms for the automation of combat operation simulation behaviors on the individual Soldier and SU level that may also be leveraged for Soldier and SU decision support tools to meet these critical Computer-Human Interaction (CHI) domain problems. TSE is researching and developing the Reasoning, Planning, and Goal-Seeking (RPGS) architecture , which is targeted at the next generation of constructive simulations requiring autonomous and intelligent agents that are capable of problem solving ; considering multiple courses of action; coordinating with friendly forces; following chain of command; and using Tactics, Techniques, and Procedures (TTPs) to guide operations. Intelligent agents guided by RPGS methodologies and algorithms will be able to execute complex tasks given mission goals, ini-tial/boundary conditions, constraints, and access to a battlespace knowledge base. TSE is creating a formal model of the Soldier and SU battlespace on which reasoning can be conducted. TSE will integrate two technical standards into the battlespace knowledge model; the Joint Consultation, Command, and Control Information Exchange Data Model (JC3IEDM) and the Coalition Battle Management Language (C-BML). This paper discusses the application of these standards and the design and development of a battlespace knowledge base and new RPGStechnologies.
Automated Reasoning across Tactical Stories
The Military Analogical Reasoning System (MARS) is a performance support system and decision aid for commanders in Tactical Operations Centers. MARS enhances and supports the innate human ability for using stories to reason about tactical goals, plans, situations, and outcomes. The system operates by comparing many instances of stored tactical stories, determining which have analogous situations and lessons learned, and then returning a description of the lessons learned. The description of the lessons learned is at a level of abstraction that can be generalized to an appropriate range of tactical situations. The machine-understandable story representation is based on a military operations data model and associated tactical situation ontology. Thus each story can be thought of, and reasoned about, as an instance of an unfolding tactical situation. The analogical reasoning algorithm is based on Gentner's Structure Mapping Theory. Consider the following two stories. In the first, a U.S. platoon in Viet Nam diverts around a minefield and subsequently comes under ambush from a large hill overlooking their new position. In the second, a U.S. task force in Iraq diverts around a biochemical hazard and subsequently comes under ambush from the roof of an abandoned building. MARS recognizes these stories as analogical, and derives the following abstraction: When enemy- placed obstacles force us into an unplanned route, beware of ambush from elevation or concealment. In this paper we describe the MARS interface, military operations data model, tactical situation ontology, and analogical reasoning algorithm.
Context-based representation of intelligent behavior in training simulations
Transactions of the Society for Computer …, 1998
This article presents, describes and evaluates a novel behavior representation paradigm that can effectively and efficiently be used to model the behavior of intelligent entities in a simulation. Called Context-based Reasoning (CxBR), this paradigm is designed to be applicable whenever simulation of human behavior is required. However, it is especially well suited to representing tactical behavior of opponents and teammates in simulation-based tactical training systems. Representing human behavior in a simulation is a complex and difficult task that generally requires significant investment in human effort as well as in computing resources. Conciseness and simplicity of representation and efficiency of computation, therefore, are important issues when developing models of intelligent opponents. We believe that this paradigm is an improvement over the rule-based approach, currently a common technique used in representing human behavior. We have preliminarily tested CxBR in two different prototype systems. Evaluation of the prototype shows that the context-based paradigm promises to meet the desired levels of simplicity, conciseness and efficiency required for the task.
Comparing two context-driven approaches for representation of human tactical behavior
The Knowledge Engineering Review, 2008
Contextual Graphs (CxG), two well-known context-driven approaches used to represent human intelligence and decision making. The specific objective of this investigation was to compare and contrast both approaches to increase the readers' understanding of each approach. We also identify which, if any, excels in a particular area, and to look for potential synergism between them. This comparison is presented according to ten different criteria, with some indication of which one excels at each particular facet of performance. We focus the comparison on how each would represent human tactical behavior, either in a simulation or in the real world. Conceptually, these two context-driven approaches are not at the same representational level. This could provide an opportunity in the future to combine them synergistically.
2011 - MILCOM 2011 Military Communications Conference, 2011
This paper discusses a novel approach that addresses the problem of supporting the Commanderʼs dynamic information requirements through automation of the Military Decision-Making Process (MDMP) for time-constrained environments and training purposes, as part of the Tactical Human Integration of Networked Knowledge (THINK) Army Technology Objective-Research (ATO-R) initiative. We demonstrate this capability with automated user support for the execution of battle drills. Our approach is based on adapting the R-CAST cognitively-inspired agent architecture towards a context-aware anticipation of information requirements. R-CAST is a computational model of the Recognition-Primed Decision (RPD) model, which models human decision making under time stress. R-CAST agents support and collaborate with human decision making teams as both "smart aids" and "effective teammates" by anticipating, investigating, seeking, and interpreting information relevant to decision making. A key feature of R-CAST is that the proactive sharing of information relevant to decision making is automatically generated by the computational RPD model. The fundamental research question being addressed is whether the inclusion of R-CAST in Army staff processes improves said staff understanding and execution of battle tasks. We adapted R-CAST to Battle Drill #26 (i.e., responding to an IED event) as a proof of concept for team decision making under stress and constant switching of modalities. We demonstrate that the use of R-CAST cognitive agents effectively assists the Battle Manager in the S3 cell with auto-filling certain forms required by doctrine in response to the dynamism of the current state of the environment, improving cognitive performance in this task. Our novel approach integrates relevant context in communication, information, and socio-cognitive networks, coupled with cognitive modeling. We report initial findings that we can use the R-CAST cognitive framework to effectively and efficiently develop individual intelligent training tools that understand and support the dynamic information requirements of Commanders.
Rehearsing Naval Tactical Situations Using Simulated Teammates and an Automated Tutor
IEEE Transactions on Learning Technologies, 2000
This paper describes a deployed simulation-based Intelligent Tutoring System (ITS) for training of Tactical Action Officers (TAOs). The TAO on board a Navy ship is responsible for the operation of the entire watch team manning the ship's command center. The ITS goal is to train the TAO in "command by negation," in which watchstanders perform their duties autonomously, while the TAO supervises, intervening in order to correct mistakes and rectify omissions. The ITS uses artificial intelligence (AI) techniques to provide Automated Role Players (ARPs) representing the watchstanders in the ship, and to provide a Natural Language interface to communicate with these automated teammates. An adaptive coaching strategy is used to provide coaching and feedback during an exercise. The paper presents a discussion of the ITS instructional design, its architecture, and the AI techniques it employs.