Creating an Artificially Intelligent Director (AID) for Theatre and Virtual Environments

BACKGROUND Historically, most virtual character research focuses on realism, interaction with humans, and discourse. The majority of the spatial positioning of characters has focused on oneon-one conversations with humans or placing virtual characters side-by-side when talking. These rely on conversational space as the main driver (if any) for character placement. Robotics is more of a physical representation of characters and by its nature relies on spatial positioning of objects. Research in this area has involved providing directions to robots or robots providing directions to humans. The main concern is how to describe the spatial positioning of objects with respect to other items in the environment [5, 16]. Some robotics research has worked on incorporating robotics into the theatre, but its purpose has been around pre-recording humanistic movements for replaying in other scenarios [9]. Psychologists have spent a lot of time digging into the meanings behind key prepositions that describe spatial concepts, such as in, on, near, and far [4, 7]. This is useful in helping us to understand spatial instructions given by humans or within play-scripts for characters in theatre. Research has also been performed around comfortable conversational space, grouping of people in conversation, and what may trigger someone to change position or move [6, 10]. Movies and games rely on motion capture (mocap) files and hardcoded functions to perform spatial movements. These require extensive technical knowledge just to have a character move from one place to another. Other methods involve the use of Behavior Markup Language (BML), a form of XML which describes character behaviors. BML Realizers take this BML and performs the requested behavior(s) on