Improving the Heading Accuracy in Indoor Pedestrian Navigation Based on a Decision Tree and Kalman Filter

Guanghui Hu,Xinxin Li,Weizhi Zhang,Hong Wan

doi:10.3390/s20061578

Abstract

In pedestrian inertial navigation, multi-sensor fusion is often used to obtain accurate heading estimates. As a widely distributed signal source, the geomagnetic field is convenient to provide sufficiently accurate heading angles. Unfortunately, there is a broad presence of artificial magnetic perturbations in indoor environments, leading to difficulties in geomagnetic correction. In this paper, by analyzing the spatial distribution model of the magnetic interference field on the geomagnetic field, two quantitative features have been found to be crucial in distinguishing normal magnetic data from anomalies. By leveraging these two features and the classification and regression tree (CART) algorithm, we trained a decision tree that is capable of extracting magnetic data from distorted measurements. Furthermore, this well-trained decision tree can be used as a reject gate in a Kalman filter. By combining the decision tree and Kalman filter, a high-precision indoor pedestrian navigation system based on a magnetically assisted inertial system is proposed. This system is then validated in a real indoor environment, and the results show that our system delivers state-of-the-art positioning performance. Compared to other baseline algorithms, an improvement of over 70% in the positioning accuracy is achieved.

Highlights

Indoor navigation refers to the technology that provides positioning and position tracking services in large buildings or other places with certain closed structures
A wearable inertial measurement units (IMUs) device worn on the waist was used to test the navigation algorithm and verify the effectiveness of the magnetic data classification method
The proposed DT+Kalman method has the smallest heading estimation error; The method uses magnetic data to improve the accuracy of heading angle and prevent the errors caused from abnormal magnetic anomalies

Summary

Introduction

Indoor navigation refers to the technology that provides positioning and position tracking services in large buildings or other places with certain closed structures. Due to the loss of satellite signals indoors, the popular Global Navigation Satellite System (GNSS) is ineffective for indoor positioning. A new high-precision indoor positioning technique is urgently needed. Passive wireless signal positioning technology and active inertial navigation technology are the two mainstream solutions [5,6]. A wireless signal-based positioning system relies on specific signal-emitting base stations. The accuracy and range of such positioning systems are heavily reliant on the numbers of base stations, which means that it may be financially costly to achieve a large-scale or high-precision implementation. There are many challenges in obtaining accurate positioning through wireless signals due to the multipath effects and decay in obstacles [7,8,9]. It is worth noting that if Sensors 2020, 20, 1578; doi:10.3390/s20061578 www.mdpi.com/journal/sensors

Methods

Results

Conclusion