Event prediction for modeling mental simulation in naturalistic decision making

Abstract

Nearly all armies of the Western Hemisphere use modeling and simulation tools as an essential part of performing analysis and training their leaders and war fighters. Tremendous resources have been applied to increase the level of fidelity and detail with which real combat units are represented in computer simulations. Current models digress from Lanchester equations used for modeling the big Cold War scenarios towards modeling of individual soldier capabilities and behavior in the post Cold War environment and increasingly important asymmetric warfare scenarios. Although improvements in computer technology support more and more detailed representations, human decision making is still far from being automated in a realistic way. Many "decisions" within a simulation are based on overly simple models and hardly at all on cognitive processes. One cognitive model in naturalistic decision making is the Recognition Primed Decision Model developed by Klein and Associates. It describes how the actual process humans use to come up with decisions in certain situations is radically different from the traditional model of rational decision making. Mental simulation is an essential part of this model in order to picture possible outcomes in the future for potential courses of actions. This research provides a computational model for mental simulation in a combat simulation environment. It generates the look into the near future with a finite Markov Chain as one instance of several possible predictive models. The results of the model are compared with preliminary human experimental data. The experiments show that the model developed performs in the human range with respect to prediction and decisions. This research shows that entities in a combat simulation environment having the capability of looking ahead into the near future based on statistical data perform more realistically than those that just use the information of the present, not even including the past.