A hierarchy of cognitive maps from panoramic images

This paper presents a computational model which implements formation of cognitive maps based on panoramic images captured during the exploration phase. The resulting map consists of “place cells” and topological relations between them. The formation of the cognitive map is based on the model introduced by Hafner. The use of panoramic images as inputs would result in high computational complexity of the simulation, therefore we propose to use the PCA (Principal Component Analysis) method to reduce the dimension of the input space. A physical force model is applied to extend the relatively sparse topological map with metric information. Both the computational model and the physical force model try to mimic functions performed in the mammalian brain.