A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications

The evolution of low-cost embedded systems is growing exponentially; likewise, their use in robotics applications aims to achieve critical task execution by implementing sophisticated control and computer vision algorithms. We review the state-of-the-art strategies available for Tiny Machine Learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel Beltrán-Escobar, Teresa E. Alarcón, Jesse Y. Rumbo-Morales, Sonia López, Gerardo Ortiz-Torres, Felipe D. J. Sorcia-Vázquez
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/11/476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267672805113856
author Miguel Beltrán-Escobar
Teresa E. Alarcón
Jesse Y. Rumbo-Morales
Sonia López
Gerardo Ortiz-Torres
Felipe D. J. Sorcia-Vázquez
author_facet Miguel Beltrán-Escobar
Teresa E. Alarcón
Jesse Y. Rumbo-Morales
Sonia López
Gerardo Ortiz-Torres
Felipe D. J. Sorcia-Vázquez
author_sort Miguel Beltrán-Escobar
collection DOAJ
description The evolution of low-cost embedded systems is growing exponentially; likewise, their use in robotics applications aims to achieve critical task execution by implementing sophisticated control and computer vision algorithms. We review the state-of-the-art strategies available for Tiny Machine Learning (TinyML) implementation to provide a complete overview using various existing embedded vision and control systems. Our discussion divides the article into four critical aspects that high-cost and low-cost embedded systems must include to execute real-time control and image processing tasks, applying TinyML techniques: Hardware Architecture, Vision System, Power Consumption, and Embedded Software Platform development environment. The advantages and disadvantages of the reviewed systems are presented. Subsequently, the perspectives of them for the next ten years are present. A basic TinyML implementation for embedded vision application using three low-cost embedded systems, Raspberry Pi Pico, ESP32, and Arduino Nano 33 BLE Sense, is presented for performance analysis.
format Article
id doaj-art-c4ca6ccdd9584466b9507f7ae19ed9bd
institution OA Journals
issn 1999-4893
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-c4ca6ccdd9584466b9507f7ae19ed9bd2025-08-20T01:53:42ZengMDPI AGAlgorithms1999-48932024-10-01171147610.3390/a17110476A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic ApplicationsMiguel Beltrán-Escobar0Teresa E. Alarcón1Jesse Y. Rumbo-Morales2Sonia López3Gerardo Ortiz-Torres4Felipe D. J. Sorcia-Vázquez5Academic Division of Industrial Mechanics, Emiliano Zapata Technological University of the State of Morelos, Emiliano Zapata 62760, MexicoComputer Science and Engineering Department, University of Guadalajara, Ameca 46600, MexicoComputer Science and Engineering Department, University of Guadalajara, Ameca 46600, MexicoComputer Science and Engineering Department, University of Guadalajara, Ameca 46600, MexicoComputer Science and Engineering Department, University of Guadalajara, Ameca 46600, MexicoComputer Science and Engineering Department, University of Guadalajara, Ameca 46600, MexicoThe evolution of low-cost embedded systems is growing exponentially; likewise, their use in robotics applications aims to achieve critical task execution by implementing sophisticated control and computer vision algorithms. We review the state-of-the-art strategies available for Tiny Machine Learning (TinyML) implementation to provide a complete overview using various existing embedded vision and control systems. Our discussion divides the article into four critical aspects that high-cost and low-cost embedded systems must include to execute real-time control and image processing tasks, applying TinyML techniques: Hardware Architecture, Vision System, Power Consumption, and Embedded Software Platform development environment. The advantages and disadvantages of the reviewed systems are presented. Subsequently, the perspectives of them for the next ten years are present. A basic TinyML implementation for embedded vision application using three low-cost embedded systems, Raspberry Pi Pico, ESP32, and Arduino Nano 33 BLE Sense, is presented for performance analysis.https://www.mdpi.com/1999-4893/17/11/476embedded systemimage processingmobile roboticTinyML
spellingShingle Miguel Beltrán-Escobar
Teresa E. Alarcón
Jesse Y. Rumbo-Morales
Sonia López
Gerardo Ortiz-Torres
Felipe D. J. Sorcia-Vázquez
A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
Algorithms
embedded system
image processing
mobile robotic
TinyML
title A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
title_full A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
title_fullStr A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
title_full_unstemmed A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
title_short A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
title_sort review on resource constrained embedded vision systems based tiny machine learning for robotic applications
topic embedded system
image processing
mobile robotic
TinyML
url https://www.mdpi.com/1999-4893/17/11/476
work_keys_str_mv AT miguelbeltranescobar areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT teresaealarcon areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT jesseyrumbomorales areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT sonialopez areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT gerardoortiztorres areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT felipedjsorciavazquez areviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT miguelbeltranescobar reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT teresaealarcon reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT jesseyrumbomorales reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT sonialopez reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT gerardoortiztorres reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications
AT felipedjsorciavazquez reviewonresourceconstrainedembeddedvisionsystemsbasedtinymachinelearningforroboticapplications