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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |