Magnetic indoor positioning system using deep neural network

Abstract

A magnetic indoor positioning system utilizes distorted geomagnetic fields indoors to estimate locations. However, existing magnetic positioning methods have difficulties in positioning, especially in a wide space because of the ambiguity of magnetic data. Multiple magnetic sensors should work in collaboration to yield a high accuracy, hindering the techniques from being used by mobile devices such as smartphones. To address this problem, we propose a new magnetic indoor positioning method using deep neural network. Features are extracted from magnetic sequences, and then the deep neural network is used for classifying features of magnetic landmarks detected from a dense magnetic map. The magnetic map is constructed by a robot. The proposed method achieved over 80% accuracy in a two-dimensional environment.