Robotic map building by fusing ICP and PSO algorithms

This paper proposes the use of Particle Swarm Optimization (PSO) to work with an Enhanced-ICP to effectively filter out outliers and avoid false matching points during the map building of an unknown environment, where PSO is used to solve the local optima problem to obtain better transformation results for two data sets with excessive difference in initial position and direction. Then, we use part of global map as the reference data set with overlapping points for subsequent data matching. Experimental results show that the proposed algorithm not only solves outlier and noise problems but also reduces false matching points so that it has better alignment and smaller accumulated errors for map building.