The goal of the current research was to design and imple- ment a system able to extract high-level representations of 3D building models for the purpose of developing cognitive mod- els. We present an intermediate representation scheme that supports modeling at different levels of detail. A cognitive model could easily use our representation scheme to perceive and navigate a 3D building. The overall goal of the project was to develop an implementation-independent representation scheme, sufficient to support high-level symbolic cognitive models. Our node-based representation supports high-level vi- sual perception (which can be used in a spatial representation internal to the agent) or a complete semantically labelled topo- logical map. Our representation scheme identifies structural features of the 3D building environments: “floor”, “ceiling”, “wall”, “door”, and “corner”, which are useful for agents pro- grammed in symbolic cognitive architectures and navigating simulated environments. Our evaluation shows that this rep- resentation is sufficient for agents to do simple navigation in virtual environments.