A novel framework for simultaneous localization and mapping

Abstract

The six Degrees of freedom (6-Dof) Simultaneous Localization and Mapping (SLAM) aims to build a map of an unknown environment and simultaneously use this map to compute the location with 6-Dof poses. To solve this problem, probabilistic approaches such as Particle Filters (PF) have become dominant methods. PF suffers from certain problems (e.g. the need for large number of particles and so on) which induce high computational complexity. In this paper, an efficient SLAM framework is proposed and new ideas for each module are presented. By combining machine vision and a PF algorithm called the Exponential Natural Particle Filter (xNPF), the predicted results converge close to the true target states. Experimental results validate the potential of the proposed approach.