Abstract

An important aspect of all robotic systems is sensing and there are many sensing modalities used including vision, tactile, olfactory and acoustics to name a few. This paper presents a robotic system for sensing in acoustics, specifically in elevation localization. The model presented is a two-stage model incorporating spectral analysis using artificial pinna and an artificial neural network for classification and elevation estimation. The spectral classifier uses notch filters to analyze changes in attenuation of certain frequencies with elevation. This paper shows how using the spectral output of a signal generated by an artificial pinna can be classified by a feed-forward backpropagation neural network to estimate the elevation of a sound-source.