Comparing two context-driven approaches for representation of human tactical behavior (original) (raw)

Context-based representation of intelligent behavior in simulated opponents

1995

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.

Context-based representation of intelligent behavior in training simulations

Transactions of the Society for Computer …, 1998

Composing tactical agents through contextual storyboards

2010

This paper presents the novel use of storyboards for composing, organizing and visualizing tactical agents designed to serve as computer generated forces. These tactical agents represent enemy forces that act and react to trainee actions and are specifically used here to populate military training scenarios. The tactical agents are based on the Context-based Reasoning human behavior representation paradigm. This application of storyboards facilitates the use and visualization of the contextual elements that make up the composed agents. The use of the approach is described and an informal qualitative evaluation is conducted.

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 Reasoning: A Revised Specification

The Florida AI Research Society Conference, 2004

This paper is an extension to and revision of Gonzalez and Ahlers' (6) definition of the Context-Based Reasoning Paradigm. Included are rigorous definitions of all terms and components applicable to CxBR models along with a discussion on how and where these models store and execute tactical knowledge. In addition, new terms and concepts are introduced that justify the need for

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.

Understanding the Role of Context in the Interpretation of Complex Battlespace Intelligence

2006 9th International Conference on Information Fusion, 2006

A key challenge presented by the increasing volume and complexity of information collectable from battlespace situations is the development of intelligent applications able to automatically analyze the information and identify critical enemy activities in a timely manner. What makes this information fusion problem particularly difficult is the strong contextual dependency of the interpretation of complex battlespace information. This paper examines the dimensions of intelligence information, establishes a framework for exploring the effects of contextual information and provides an illustration of its use. The paper concludes with a discussion of the ramifications of context on the development of intelligent applications intended to aid in the interpretation of complex battlespace intelligence.

Tale of Two Context-Based Formalisms for Representing Human Knowledge

Lecture Notes in Computer Science, 2006

This paper describes an investigation that compared and contrasted Context-based Reasoning (CxBR) and Contextual Graphs (CxG), two paradigms used to represent human intelligence. The specific objectives were to increase understanding of both paradigms, identifying which, if either, excels at a particular function, and to look for potential synergism amongst them. We study these paradigms through ten different aspects, with some indication of which one excels at this particular facet of performance. We point out how they are complementary and finishes with a recommendation for a new synergistic approach, followed by an example of an application of the new approach to tactical

Improving Computational Efficiency in Context-Based Reasoning Simulations

The current application of the competing context approach to solve ambiguities in context-based reasoning (CxBR) simulations has limitations. This paper describes several improvements to the current competing context approach that allow a more dynamic and and preemptive evaluation of the simulation environment. In their previous work, Saeki and Gonzalez developed the idea of the competing context as a method to choose a course of action from among two or more possibilities in CxBR simulations. Essentially, the concept is that the simulation halts while the intelligent agent generates a list of possible context transitions and, if necessary, enters a "time-warp simulation," selects each context in a "what if" approach to see what will happen, and then makes a selection based on the "best" outcome. The major drawbacks to this approach are the lack of realism introduced by relying on random simulated events as part of the decision making process and the computational burden as the number of choices grows. To effectively cope with a large number of possible choices while still exhibiting realistic tactical decision making, the CxBR framework can be improved. The generation of situation interpretation metrics (SIMs) is made more robust by incorporating degraded states, resulting in a much richer representation of the simulation environment. The more robust representation of the simulation environment allows the agents to be more proactive in decision-making, thus improving the computational efficiency of the simulation and increasing the realism by more closely reflecting actual human tactical behavior.

Representing the Human Decision Making Process in Simulation Models of Combat

2003

Across NATO, there is a growing realisation that the proper representation of Command and Control (C2) within combat models is very important, in the context of major Defence topics such as Digitization of the Battlespace. In addition to the use of current OA models and tools to address immediate requirements, there is thus a need for longer term research to develop methods of properly representing these effects. In consequence, research has been instigated in the UK to investigate ways in which the effects of C2 can be incorporated successfully into constructive simulation models of combat i.e. models which can run in closed form on a computer, and represent the effects of C2, without the need for human intervention during the simulation run. wider span of scenarios in studies, reflecting increased uncertainty in the post-Cold War world. Another reflection of this uncertainty is the need to consider a wide range of sensitivity analysis. These point to the need for constructive simu...

Comparing two context-driven approaches for representation of human tactical behavior (original) (raw)

Related papers