Auxiliary Particle Filter Localization for Intelligent Wheelchair Systems in Urban Environments

Abstract

We propose the robust 2D localization applies an Auxiliary Particle Filter (APF) to Monte Carlo Localization (MCL). Urban environments have fewer landmarks than two-dimensional (2D) indoor maps for efficiently finding a unique location. Localization using MCL have the problem that few landmarks pose divergence of the particles of MCL. We use APF for MCL, because APF continues resampling until convergence particle occurs in one localization step. Another problem with 2D urban mapping is that of data association posed by three-dimensional (3D) surfaces. Pitching and rolling may, for example, adversely affect 2D scan-data metrics due to 3D surfaces, causing mismatching data association in 2D maps. We therefore use a Laplacian filter for 2D grid maps. Experimental results show that our localization method is more highly stable in urban environments than MCL.