Representation and Learning of Spatial Maps
Rushi Bhatt, Karthik Balakrishnan, Vasant Honavar · 2000
How animals acquire, store, update, and use spatial representations of their environments for localization and navigation is one of the central questions in Cognitive Science and Neuroscience. Design of robust algorithms for spatial learning for mobile robots for exploring a-priori unknown environments is one of the key problems in robotics and artificial intelligence. This paper describes some approaches to acquiring, representing, retrieving, and updating spatial maps using sensory as well as motor measurements in a biologically inspired model of spatial learning. Introduction The computational strategies used by animals to acquire and use spatial knowledge (e.g., maps) for navigation have been the subject of study in Neuroscience, Cognitive Science, and related areas. Based on lesion and pharmacological studies performed by numerous experimenters O'Keefe and Nadel (1978) suggested that hippocampus is critically involved in the formation of a "cognitive map". The cogniti...