Tactile robot shape recognition using geometrical angle/length sequences

Abstract

A novel technique of building an angle/length representation of planar polygons is introduced. The object's positional data are slowly acquired by robotic tactile sensors and a neural network is then used to recognize the shape. The method proposed is straightforward, and seems to work well on simple shapes. It is rotational and shift invariant and can also be made scale invariant.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>