An efficient and flexible perception pipeline for autonomous agents

Agents in virtual environments require a combination of perception and acti on to behave in an autonomous way. We extend a software architecture for th e management of actions blending, called AGENTlib, with a perception mechan ism. The perception system provides a uniform interface to various techniqu es in the field of virtual perception, including synthetic vision, database access and perception persistency We describe the framework we designed to efficiently filter valuable information from the scene and we address conc erns about computation redundancy and data propagation through multiple fil tering modules.