Hierarchical model for real time simulation of virtual human crowds

This paper describes a model for simulating crowds of humans in real time. We deal with a hierarchy composed of virtual crowds, groups, and individual s. The groups are the most complex structure that can be controlled in diff erent degrees of autonomy. This autonomy refers to the extent to which the virtual agents are independent of user intervention and also the amount of information needed to simulate crowds. Thus, depending on the complexity of the simulation, simple behaviors can be sufficient to simulate crowds. Oth erwise, more complicated behavioral rules can be necessary and, in this cas e, it can be included in the simulation data in order to improve the realis m of the animation. We present three different ways for controlling crowd b ehaviors: 1) by using innate and scripted behaviors, 2) by defining behavio ral rules, using events and reactions, and 3) by providing an external cont rol to guide crowd behaviors in real time. The two main contributions of ou r approach are: the possibility of increasing the complexity of group/agent behaviors according to the problem to be simulated and the hierarchical st ructure based on groups to compose a crowd.