Ryan McAlinden, Andrew Gordon, H. Chad Lane, David Pynadath: “UrbanSim: A Game-based Simulation for Counterinsurgency and Stability-focused Operations”

July 7, 2009 | Brighton, UK

Speaker: Ryan McAlinden, Andrew Gordon, H. Chad Lane, David Pynadath
Host: Workshop on Intelligent Educational Games, 14th International Conference on Artificial Intelligence in Education

The UrbanSim Learning Package is a simulation-based training application designed for the U.S. Army to develop commanders’ skills for conducting counterinsurgency operations. UrbanSim incorporates multiple artificial intelligence (AI) technologies in order to provide an effective training experience, three of which are described in this paper. First, UrbanSim simulates the mental attitudes and actions of groups and individuals in an urban environment using the PsychSim reasoning engine. Second, UrbanSim interjects narrative elements into the training experience using a case-based story engine, driven by non-fiction stories told by experienced commanders. Third, UrbanSim provides intelligent tutoring using a simulation-based method for eliciting and evaluating learner decisions. UrbanSim represents a confluence of AI techniques that seek to bridge the gap between basic research and deployed AI systems.