High-level interpretation in virtual environments

As virtual environments applications become mole complex, there is a need t o interpret user interaction in terms of high-level concepts. In this paper , the relations between conceptual representations of actions and their phy sical simulation in virtual worlds is investigated. A model inspired from n atural language processing (NLP) research in the linguistic interpretation of dynamic scenes has been developed. The experiments are based on real-tim e animation software, which has been enhanced with a symbolic information p rocessing layer, originally developed for NLP-based animation. We report th e implementation of a high-level interpretation module that is able to reco gnize complex actions from low-level physical events in the virtual world a nd discuss its performance as well as directions for further developments.