|
Project Proposals for William Flynn Scholarship: IIndex page Project Number: 11 A virtual environment (VE) provides a computer-based interface representing a three-dimensional physical environment or abstract space. A large and growing number of applications are using VE technology in a variety of areas including manufacturing, business, entertainment, medicine and education. Users of these three-dimensional information spaces require intuitive tools to enable effective navigation and interaction. Navigation is the process of moving (usually sequentially) around an environment, deciding at each step where to go. Users require the ability to move, controlling orientation, direction of movement and speed, in order to get to desired positions within a VE. VE applications often place a high demand on navigation skills, which means that a high level of navigational support is required from the interface. It is important, therefore, that interfaces are designed which provide users with the tools to enable them to exploit the new possibilities offered. Research has shown that current interfaces which supply users with visible tools for navigation within VEs cause user frustration in a variety of ways. Problems encountered relate to support for velocity, getting lost or becoming disoriented in the environment, direction of movement, navigational modes (e.g. walking, flying), the provision of landmarks in the environment itself, and automatic navigation to predefined locations. This research will investigate the use of Natural Language Processing (NLP) as an additional/alternative means of navigation and interaction in these environments. Although there has been much success in developing theories, models and systems in the areas of Natural Language Processing (NLP) and Visual Processing (VP), there has been little progress in integrating these two areas. In the beginning, although the general aim of the field was to build integrated language and visual systems, few were developed, and these two subfields quickly arose. Intelligent MultiMedia (IntelliMedia) focuses on the computer processing and understanding of signal and symbol input from at least speech, text and visual images in terms of semantic representations. There has been very little work on integrating spoken dialogue systems with VEs. Our focus here is to link spoken dialogue processing into VEs so that users can ask questions about entities and objects in the environments and also about navigation within them. For example, users may be asking questions about a 3D VR presentation of a building space and how to get to certain offices, or about how to get to a destination on a VR map display, or about patient medical data. There are a number of research questions in respect of how the semantics of visual and spoken dialogue information can be integrated and how visual data can be mapped into and out of those semantics.
If you are interested in being considered for a studentship please
contact or telephone: +44-(0)28-71375417. See the current research section of this website
for details on research projects pursued by existing PhD students
|