Probabilistic, layered and hierarchical animated agents using XML

Abstract

In a previous paper we generated animated agents and their behavior in XML. These agents were specified as FSMs. We make the system more useful by implementing probabilistic FSMs. We show how more interesting behaviors can be generated. Then, we make the system more flexible and structured by implementing layered FSMs and hierarchical FSMs. We show how both of these approaches, used independently or together, allow the user to write more complex behaviors.

Realistic modeling of spectator behavior for soccer videogames with CUDA

“…Ayesh et al have tried fuzzy individual model (FIM) for the behavioral modeling of virtual individuals [16], while also using perceptions to update emotions that trigger different behaviors. Rudomin and Millan used XML scripting to specify behaviors, and employed a Finite State Machine as a processing method [17], further developing this study by implementing probabilistic FSMs, hierarchical FSMs and layered FSMs to produce non-deterministic results [18].…”

Art applications for crowds

“…In Rudomin et al (2005c), we further developed the idea by including probabilistic, hierarchical and layered FSM's to our system. Probabilistic schemas increase the apparent diversity of behaviors, as the behavior for individual characters is not uniquely guided by rigid scripts, but rather modified in unexpected, yet controlled ways, by randomly selecting certain transitions within the FSM.…”