Artificial intelligence-controlled pole balancing using an Arduino board

Automation Process (AP) is an important issue in the current digitized world and, in general, represents an increase in the quality of productivity when compared with manual control. Balance is a natural human capacity as it relates to complex operations and intelligence. Balance Control presents a...

Full description

Saved in:
Bibliographic Details
Main Authors: José Luis Revelo Orellana, Oscar Chang
Format: Article
Language:English
Published: Escuela Superior Politécnica del Litoral 2021-11-01
Series:Revista Tecnológica
Subjects:
Online Access:https://rte.espol.edu.ec/index.php/tecnologica/article/view/852
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849697759918030848
author José Luis Revelo Orellana
Oscar Chang
author_facet José Luis Revelo Orellana
Oscar Chang
author_sort José Luis Revelo Orellana
collection DOAJ
description Automation Process (AP) is an important issue in the current digitized world and, in general, represents an increase in the quality of productivity when compared with manual control. Balance is a natural human capacity as it relates to complex operations and intelligence. Balance Control presents an extra challenge in automation processes, due to the many variables that may be involved.  This work presents a physical balancing pole where a Reinforcement Learning (RL) agent can explore the environment, sense its position through accelerometers, and wirelessly communicate and eventually learns by itself how to keep the pole balanced under noise disturbance. The agent uses RL principles to explore and learn new positions and corrections that lead toward more significant rewards in terms of pole equilibrium. By using a Q-matrix, the agent explores future conditions and acquires policy information that makes it possible to maintain stability. An Arduino microcontroller processes all training and testing. With the help of sensors, servo motors, wireless communications, and artificial intelligence, components merge into a system that consistently recovers equilibrium under random position changes. The obtained results prove that through RL, an agent can learn by itself to use generic sensors, actuators and solve balancing problems even under the limitations that a microcontroller presents.
format Article
id doaj-art-4cecef01e7544fe6b6c518426ed118cb
institution DOAJ
issn 0257-1749
1390-3659
language English
publishDate 2021-11-01
publisher Escuela Superior Politécnica del Litoral
record_format Article
series Revista Tecnológica
spelling doaj-art-4cecef01e7544fe6b6c518426ed118cb2025-08-20T03:19:07ZengEscuela Superior Politécnica del LitoralRevista Tecnológica0257-17491390-36592021-11-0133210.37815/rte.v33n2.852Artificial intelligence-controlled pole balancing using an Arduino boardJosé Luis Revelo Orellana0Oscar Chang1Yachay TechYachay Tech Automation Process (AP) is an important issue in the current digitized world and, in general, represents an increase in the quality of productivity when compared with manual control. Balance is a natural human capacity as it relates to complex operations and intelligence. Balance Control presents an extra challenge in automation processes, due to the many variables that may be involved.  This work presents a physical balancing pole where a Reinforcement Learning (RL) agent can explore the environment, sense its position through accelerometers, and wirelessly communicate and eventually learns by itself how to keep the pole balanced under noise disturbance. The agent uses RL principles to explore and learn new positions and corrections that lead toward more significant rewards in terms of pole equilibrium. By using a Q-matrix, the agent explores future conditions and acquires policy information that makes it possible to maintain stability. An Arduino microcontroller processes all training and testing. With the help of sensors, servo motors, wireless communications, and artificial intelligence, components merge into a system that consistently recovers equilibrium under random position changes. The obtained results prove that through RL, an agent can learn by itself to use generic sensors, actuators and solve balancing problems even under the limitations that a microcontroller presents. https://rte.espol.edu.ec/index.php/tecnologica/article/view/852reinforcement learningintelligent agentQ-learningmicrocontrollerIndustry 4.0
spellingShingle José Luis Revelo Orellana
Oscar Chang
Artificial intelligence-controlled pole balancing using an Arduino board
Revista Tecnológica
reinforcement learning
intelligent agent
Q-learning
microcontroller
Industry 4.0
title Artificial intelligence-controlled pole balancing using an Arduino board
title_full Artificial intelligence-controlled pole balancing using an Arduino board
title_fullStr Artificial intelligence-controlled pole balancing using an Arduino board
title_full_unstemmed Artificial intelligence-controlled pole balancing using an Arduino board
title_short Artificial intelligence-controlled pole balancing using an Arduino board
title_sort artificial intelligence controlled pole balancing using an arduino board
topic reinforcement learning
intelligent agent
Q-learning
microcontroller
Industry 4.0
url https://rte.espol.edu.ec/index.php/tecnologica/article/view/852
work_keys_str_mv AT joseluisreveloorellana artificialintelligencecontrolledpolebalancingusinganarduinoboard
AT oscarchang artificialintelligencecontrolledpolebalancingusinganarduinoboard