A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition

Luan Carlos Klein; João Braun; João Mendes; Vítor H. Pinto; Felipe Martins; André Schneider de Oliveira; Heinrich Wörtche; Paulo Gomes Costa; José Lima

doi:10.3390/s23063128

A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition

Luan Carlos Klein (First author)
, João Braun
, João Mendes
, Vítor H. Pinto
, Felipe Martins
, André Schneider de Oliveira
, Heinrich Wörtche
, Paulo Gomes Costa
, José Lima

Sensors and Smart Systems

The Research Centre in Digitalization and Intelligent Robotics (CeDRI), Polytechnic Institute of Braganca
INESC Technology and Science
Universidade Tecnológica Federal do Paraná (UTFPR), Department of Electronics (DAELN)
Instituto Politécnico de Bragança, Laboratório para a Sustentabilidade e Tecnologia em Regioes de Montanha (SusTEC)
University of Porto (FEUP), Faculty of Engineering
University of Minho, ALGORITMI Center
SYSTEC (DIGI2) Research Center for Systems and Technologies (Digital and Intelligent Industry Lab)
Eindhoven University of Technology, Department of Electrical Engineering

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.

Original language	English
Article number	3128
Journal	Sensors
Volume	23
Issue number	6
DOIs	https://doi.org/10.3390/s23063128 https://doi.org/10.3390/s23063128
Publication status	Published - 15 Mar 2023

Keywords

fiducial markers
indoor localization
industry 4.0
machine learning
robotics competitions

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Healthy Ageing

Research Focus Areas Research Centre or Centre of Expertise * (mandatory by Hanze)

Artificial Intelligence
Cyberfysical systems

Publinova themes

ICT and Media
Health
Technology

Access to Document

10.3390/s23063128Licence: CC BY
10.3390/s23063128

Hanze Impact Event
Wörtche, H. (Speaker) & Manting, F. (Speaker)
31 May 2023
Activity: Talk or presentation › Oral presentation

Cite this

@article{7720acdf4b5b453489938f4d37bd5e40,

title = "A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition",

abstract = "Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.",

keywords = "fiducial markers, indoor localization, industry 4.0, machine learning, robotics competitions, indoor lokalisatie, industrie 4.0, robotica wedstrijden, vaste merktekens",

author = "Klein, \{Luan Carlos\} and Jo{\~a}o Braun and Jo{\~a}o Mendes and Pinto, \{V{\'i}tor H.\} and Felipe Martins and \{Schneider de Oliveira\}, Andr{\'e} and Heinrich W{\"o}rtche and \{Gomes Costa\}, Paulo and Jos{\'e} Lima",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2023",

month = mar,

day = "15",

doi = "10.3390/s23063128",

language = "English",

volume = "23",

journal = "Sensors",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "6",

}

TY - JOUR

T1 - A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition

AU - Klein, Luan Carlos

AU - Braun, João

AU - Mendes, João

AU - Pinto, Vítor H.

AU - Martins, Felipe

AU - Schneider de Oliveira, André

AU - Wörtche, Heinrich

AU - Gomes Costa, Paulo

AU - Lima, José

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2023/3/15

Y1 - 2023/3/15

N2 - Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.

AB - Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.

KW - fiducial markers

KW - indoor localization

KW - industry 4.0

KW - machine learning

KW - robotics competitions

KW - indoor lokalisatie

KW - industrie 4.0

KW - robotica wedstrijden

KW - vaste merktekens

U2 - 10.3390/s23063128

DO - 10.3390/s23063128

M3 - Article

SN - 1424-8220

VL - 23

JO - Sensors

JF - Sensors

IS - 6

M1 - 3128

ER -

A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition

Abstract

Keywords

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Research Focus Areas Research Centre or Centre of Expertise * (mandatory by Hanze)

Publinova themes

Access to Document

Fingerprint

Activities

Hanze Impact Event

Cite this