The application of Al techniques for automatic generation of crowd scenes

摘要

Generation of animated human figures especially in crowd scenes has many applications in such domains as the special effects industry, computer games or for the simulation of the evacuation from crowded areas. Currently such scenes have to be created by human animators using dedicated software packages. This is both expensive and time-consuming. Our "FreeWill" prototype proposes and implements a cognitive architecture designed for easy creation of animated scenes with many autonomous agents interacting in various ways. Agents maintain an internal model of the world and fulfil their goals. The design allows for easy co-operation of different software packages (geometry engine Al engine, sensing/actuating modules, simulation managing unit and a visualisation environment). The implementation language is Java and the graphics package is ID Studio Max. The requirements capture process and design is being conducted and documented in the Unified Modelling Language (UML).