Particle filter-based heading estimation using magnetic compasses for mobile robot navigation

Abstract

Heading information is critical for the control and/or navigation of mobile devices and robots. To get accurate heading information robustly, we propose a method which combines particle filtering with magnetic compasses. Although magnetic compasses can provide absolute heading angle, they have not been used for indoor applications since serious magnetic interferences are commonly founded in home/office environments. We overcome this difficulty by 1) suggesting statistical calibration of a magnetic compass, 2) deriving necessary conditions of the Earth's magnetic field area, and 3) designing an event-based particle filter based on likelihood calculated from conditional probability. Particle filter is an emerging key technology which can be applied to nonlinear/non-Gaussian model, beyond the limitations of Kalman filter. We take advantage of particle filter to optimally fuse the information from both magnetic compasses and odometry data. Experimental results on mobile robot navigation in indoor environments show reliability and robustness of the proposed method