A Decision Network Framework for the Behavioral Animation of Virtual Humans

Abstract

We introduce a framework for advanced behavioral animation in virtual humans, which addresses the challenging open problem of simulating social interactions between pedestrians in urban settings. Based on hierarchical decision networks, our novel framework combines probability, decision, and graph theories for complex behavior modeling and intelligent action selection subject to manifold internal and external factors in the presence of uncertain knowledge. It yields autonomous characters that can make nontrivial interpretations and arrive at rational decisions dependent on multiple considerations. We demonstrate our framework in behavioral animation scenarios involving interacting autonomous pedestrians, including an elaborate emergency response animation.