A developing sensory mapping for robots

A sensory mapping method, called staggered hierarchical mapping (SHM), and its developmental algorithm are described in this paper SHM is a model motivated by human early, visual pathways including processing performed by the retina, lateral geniculate nucleus (LGN) and the primary visual cortex. The work reported here concerns not only the design of such a series of processors but also their autonomous development. A new incremental principal component analysis (IPCA) method is used to automatically develop orientation sensitive and other needed filters. A set of staggered receptive fields model the pattern of positioning of processing cells. From sequentially sensed video frames, the proposed algorithm develops a hierarch, of filters, whose outputs are uncorrelated within each layer but with increasing scale of receptive fields from low to high layers. To study, the completeness of the representation generated by, the SHM, we experimentally, show that the response produced at any layer is sufficient to reconstruct the corresponding "retinal" image to a great degree. In our experiment, we show that SHM can be used to perform local analysis.