Feature-to-Feature based Laser Scan Matching in Polar Coordinates with Application to Pallet Recognition

Abstract

This paper presents a novel method called feature-to-feature based polar scan matching (FFPSM) for pallet recognition. Since FFPSM works in the laser scanner's polar coordinates, the transformation from polar coordinate to Cartesian coordinate is eliminated and some operations are simplified by taking the advantage of the structure of the laser measurements. The method is evaluated in the simulated laser scans. The research results show that the recognition ratio is the same but the recognition velocity is faster than previous works