The world of Virtual Environments and Immersive Technologies (Sutherland, 1965) (Kalawsky, 1993) are evolving quite rapidly. As the range and complexity of applications increases, so does the requirement for intelligent interaction. The now relatively simple environments of the OZ project (Bates, Loyall & Reilly, 1992) have been superseded by Virtual Theatres (Doyle & Hayes-Roth, 1997) (Giannachi, 2004), Tactical Combat Air (Jones, Tambe, Laird & Rosenbloom, 1993) training prototypes and Air Flight Control Simulators (Wangermann & Stengel, 1998). This article presents a brief summary of present and future technologies and emerging applications that require the use of AI expertise in the area of immersive technologies and virtual environments. The applications are placed within a context of prior research projects.
Visualisation is defined as the use of computer-based, interactive visual representations of data to amplify cognition. The much cited process driven visualisation pipeline proposed by Upson et al (1989) is shown in Figure 1. Upson and his colleagues define three processes consisting of filtering, mapping and rendering the data. The image presented allows the user to draw some inference and gain insight into the data.
Upson et al’s visualisation pipeline
The Filter process is when data of interest are derived from the raw input data; for example, an interpolation of scattered data onto a regular grid. This data is then Mapped into geometric primitives that can be then be Rendered and displayed as an image to the user. The user may then gain an improved understanding and greater insight into the original raw data. The type of data and application area heavily influence the nature of the mapping process. That is, choosing the actual visualisation technique that we are going to use. For example, if the data consisted of 1D scalar data, then a simple line graph can be used to represent the data. If the filtered data consists of 3D scalar data, then some form of 3D isosurfaces or direct volume rendering technique would be more appropriate. Through the various specifications and conceptualisations of the filter-map pipeline above, we would propose an ontology that describes the relationships between data type and mapping processes that facilitates the automatic selection of visualisation techniques based on the raw data type. As the applications become more sophisticated the visualisation process can make use of the data ontology to drive AI controlled characters and agents appropriate for the application and data.
Key Terms in this Chapter
Knowledge Engineering: Knowledge engineering is a field within artificial intelligence that develops knowledge-based systems. Such systems are computer programs that contain large amounts of knowledge, rules and reasoning mechanisms to provide solutions to real-world problems. A major form of knowledge-based system is an expert system, one designed to emulate the reasoning processes of an expert practitioner (i.e. one having performed in a professional role for very many years).
Flocking: A computer model of coordinated animal motion such as bird flocks and fish schools. Typically based on three dimensional computational geometry of the sort normally used in computer animation or computer aided design.
Virtual Theatres: The concept of “Virtual Theatre” is vague and there seems to be no commonly accepted definition of the term. It can be defined as a virtual world inhabited by autonomous agents that are acting and interacting in an independent way. These agents may follow a predetermined manuscript, or act completely on their own initiative.
Virtual and Immersive Environments: Virtual environments coupled with immersive technologies provide the sensory experience of being in a computer generated, simulated space. They have potential uses in applications ranging from education and training to design and prototyping.
Air Flight Control: A service provided by ground-based controllers who direct aircraft on the ground and in the air. A controller’s primary task is to separate certain aircraft — to prevent them from coming too close to each other by use of lateral, vertical and longitudinal separation. Secondary tasks include ensuring orderly and expeditious flow of traffic and providing information to pilots, such as weather, navigation information and NOTAMs (Notices to Airmen)