Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study

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

doi:10.1109/ICARSC58346.2023.10129619

Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study

Luan C. Klein, João Braun, Felipe N. Martins, Heinrich Wörtche, André Schneider de Oliveira, João Mendes, Vítor H. Pinto, Paulo Costa, José Lima

Sensors and Smart Systems

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

92 Downloads (Pure)

Abstract

The use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.

Original language	English
Title of host publication	IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)
Pages	69-74
Number of pages	6
DOIs	https://doi.org/10.1109/ICARSC58346.2023.10129619
Publication status	Published - 26 Apr 2023

Keywords

embedded systems
machine learning

Access to Document

10.1109/ICARSC58346.2023.10129619

ICARSC_2023_pre-printSubmitted manuscript, 8.13 MB

Cite this

Klein, L. C., Braun, J., Martins, F. N., Wörtche, H., Oliveira, A. S. D., Mendes, J., Pinto, V. H., Costa, P., & Lima, J. (2023). Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study. In IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC) (pp. 69-74) https://doi.org/10.1109/ICARSC58346.2023.10129619

@inproceedings{031ac401a57e4a4180c2570bbefd77b3,

title = "Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study",

abstract = "The use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.",

keywords = "embedded systems, machine learning, embedded systems, machine learning",

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

day = "26",

doi = "10.1109/ICARSC58346.2023.10129619",

language = "English",

pages = "69--74",

booktitle = "IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)",

}

Klein, LC, Braun, J, Martins, FN , Wörtche, H, Oliveira, ASD, Mendes, J, Pinto, VH, Costa, P & Lima, J 2023, Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study. in IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC). pp. 69-74. https://doi.org/10.1109/ICARSC58346.2023.10129619

Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study. / Klein, Luan C.; Braun, João; Martins, Felipe N. et al.
IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC). 2023. p. 69-74.

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

TY - GEN

T1 - Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study

AU - Klein, Luan C.

AU - Braun, João

AU - Martins, Felipe N.

AU - Wörtche, Heinrich

AU - Oliveira, André Schneider de

AU - Mendes, João

AU - Pinto, Vítor H.

AU - 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 - 2023/4/26

Y1 - 2023/4/26

N2 - The use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.

AB - The use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.

KW - embedded systems

KW - machine learning

KW - embedded systems

KW - machine learning

U2 - 10.1109/ICARSC58346.2023.10129619

DO - 10.1109/ICARSC58346.2023.10129619

M3 - Contribution to conference proceeding

SP - 69

EP - 74

BT - IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

ER -

Using Machine Learning Approaches to Localization in an Embedded System on RobotAtFactory 4.0 Competition: A Case Study

Abstract

Keywords

Access to Document

Fingerprint

Cite this