Route planning using an emergent hierarchical architecture

Abstract

A cognitive map is a representation of an environment that consists of both nodes and connections. How this hierarchical structure might emerge from a computational standpoint is the focus of this research. The system builds a cognitive map by traversing routes in an environment. A hierarchical structure emerges when a certain place has been visited often enough to justify its coming to be representative of an entire region. Places are considered to be connected to one another when there is a traversable route that directly links them. Each time the route is traversed, the cognitive relationship between the two places strengthens. If a place is visited often enough, it will come to symbolize an entire region. Once a region is symbolized, all other places in the region are inhibited, allowing each region to be only symbolized by one place. This process can continue indefinitely, leading to a hierarchy with more and more levels. We explore some of the properties of such a hierarchical model including how it develops and how it affects the quality of a planned route.