Hardware Connection and Software Communication in the Application of Deep Reinforcement Learning Algorithm
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24210%2F22%3A00010207" target="_blank" >RIV/46747885:24210/22:00010207 - isvavai.cz</a>
Výsledek na webu
<a href="http://www.biomechanika.cz/attachments/47.pdf" target="_blank" >http://www.biomechanika.cz/attachments/47.pdf</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Hardware Connection and Software Communication in the Application of Deep Reinforcement Learning Algorithm
Popis výsledku v původním jazyce
This paper deals with the application of deep reinforcement learning (DRL) algorithm to dynamic system control. The introductory chapter describes the operation of the selected algorithm in the control of a dynamic system, in our case a bellows air spring, which is a mechanical system with one degree of freedom. The following sections address software and hardware troubleshooting. The procedure of exporting the learned agent of the used DRL algorithm from the MATLAB environment to the Raspberry Pi 4 B microcomputer is shown and then the method of communication of the microcomputer with the sensor and actuator using AD and DA converters is described. One of the main advantages of the presented solution is the low purchase price of individual components.
Název v anglickém jazyce
Hardware Connection and Software Communication in the Application of Deep Reinforcement Learning Algorithm
Popis výsledku anglicky
This paper deals with the application of deep reinforcement learning (DRL) algorithm to dynamic system control. The introductory chapter describes the operation of the selected algorithm in the control of a dynamic system, in our case a bellows air spring, which is a mechanical system with one degree of freedom. The following sections address software and hardware troubleshooting. The procedure of exporting the learned agent of the used DRL algorithm from the MATLAB environment to the Raspberry Pi 4 B microcomputer is shown and then the method of communication of the microcomputer with the sensor and actuator using AD and DA converters is described. One of the main advantages of the presented solution is the low purchase price of individual components.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
21100 - Other engineering and technologies
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů