Evaluation of an indoor localization system for a mobile robot

TL;DR

This paper evaluates the performance of the Marvelmind Indoor GPS system for indoor and outdoor localization of a mobile robot, highlighting its accuracy and potential improvements for automated driving applications.

Contribution

It provides a comprehensive assessment of Marvelmind Indoor GPS in various scenarios and integrates it within a ROS-based robot for practical localization testing.

Findings

Effective indoor localization with static and moving objects

Comparable outdoor localization performance to GPS

Identifies areas for accuracy improvements

Abstract

Although indoor localization has been a wide researched topic, obtained results may not fit the requirements that some domains need. Most approaches are not able to precisely localize a fast moving object even with a complex installation, which makes their implementation in the automated driving domain complicated. In this publication, common technologies were analyzed and a commercial product, called Marvelmind Indoor GPS, was chosen for our use case in which both ultrasound and radio frequency communications are used. The evaluation is given in a first moment on small indoor scenarios with static and moving objects. Further tests were done on wider areas, where the system is integrated within our Robotics Operating System (ROS)-based self-developed 'Smart PhysIcal Demonstration and evaluation Robot (SPIDER)' and the results of these outdoor tests are compared with the obtained localization by the installed GPS on the robot. Finally, the next steps to improve the results in further developments are discussed.