Interoperable human behavior models for simulations

摘要: Modern simulations and games have limited capabilities for simulated characters to interact with each other humans in rich, meaningful ways. Although significant achievements been made developing human behavior models (HBMs) that are able control a single entity (or group of entities), limiting factor is the inability HBMs developed by different groups other. We present an architecture multi-level message framework enabling communicate about their actions intents, describe results our crowd demonstration system which applied it allow three distinct interoperate within training-oriented simulation. Our hope this will encourage development standards interoperability among lead richer training and analysis simulations.