Image-based memory of environment

This paper describes how an intelligent agent can locate itself from iconic memory of scenes. Omnidirectional images of the environment at a number of reference points are memorized as signs of the local areas. Similarity of the omnidirectional views at different locations in a small area decreases with their distance. The agent can thereby nds the current local area by examining the similarities of the current view with those memorized already. Since the omnidirectional view are represented by their Fourier coe cients, cost for memorizing and matching a large number of the views is inexpensive. When the agent explores a new environment, it wanders around, memorizes the views at di erent locations and organizes them into the iconic memory so as to re ect the environment geometry, which is e ective to guide navigation. Results of experiments in an o ce cluttered with much furniture and objects indicate the agent can reliably locate itself in it from the memorized views.