Modeling Culturally Accurate Behavior via Multiplayer Game Environments

Military simulations involving non-player characters (NPCs) representing non-US cultures are becoming increasingly important for training and mission rehearsal. However, creating culturally-realistic behaviors for these characters remains a technical challenge due to the lack of a clear standard or process for creating behaviors that are consistent with a given culture. This effort proposes a solution to the problem via a set of tools, called CulturePad, that allow cultural behaviors to be captured and empirically abstracted and modeled in such a way that the resulting abstraction can be used to efficiently create more accurate models of the cultural behaviors of non-US NPCs. The Phase II effort centers around four primary objectives: Design and implement CulturePad system for behavioral recording, analysis, and modeling; conduct experiments to evaluate role-play features with regard to key risks identified in Phase I; Conduct empirical assessments of CulturePad usability and life-cycle costs, and training effectiveness; and plan and promote transition to Army training users and other transition opportunities. The CulturePad concept is based on a generative narrative representation which has been shown to hold validity as a method of capturing cultural knowledge and a feasible way of generating realistic behaviors for computer-generated synthetic agents.