Multi-actor Planning for Directable Simulations

There has been growing academic and industry interest in the behavioral animation of autonomous actors in virtual worlds. However, it remains a considerable challenge to automatically generate complicated interactions between multiple actors in a customizable way with minimal user specification. In this paper, we propose a behavior authoring framework which provides the user with complete control over the domain of the system: the state space, action space and cost of executing actions. Actors are specialized using effect and cost modifiers -- which modify existing action definitions, and constraints which prune action choices in a state-dependent manner. Behaviors are used to define goals and objective functions for an actor. Actors having common or conflicting goals are grouped together to form a composite domain, and a multi-agent planner is used to generate complicated interactions between multiple actors. We demonstrate the effectiveness of our framework by authoring and generating a city simulation involving multiple pedestrians and vehicles that interact with one another to produce complex multi-actor behaviors.