Object Detection by Tiny-YOLO on TurtleBot3 as an Educational Robot

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F23%3A00011235" target="_blank" >RIV/46747885:24220/23:00011235 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/46747885:24620/23:00011235

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-981-99-2322-9_47" target="_blank" >https://link.springer.com/chapter/10.1007/978-981-99-2322-9_47</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-99-2322-9_47" target="_blank" >10.1007/978-981-99-2322-9_47</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Object Detection by Tiny-YOLO on TurtleBot3 as an Educational Robot

Popis výsledku v původním jazyce

By the unceasing efforts of many scientists, machine learning algorithms are increasing quickly with an enhanced object detection performance for the explicit applications on specific devices. This paper investigates the operation of TurtleBot3 as an educational wheeled autonomous robot which Tiny-YOLO algorithm has been applied as a novel application on it. At first, the required knowledge about the kinematics and dynamics of a differential drive robot with constraints is studied, and a graph where the robot is working under some specific conditions is plotted. The robot operating system (ROS) and simultaneous localization and mapping (SLAM) of the TurtleBot3 have been explained. The robot is equipped with a LiDAR sensor and a camera embedded onto it as a sensor fusion SLAM for a more precise type of mapping. Finally, Tiny-YOLO as a machine learning algorithm for object detection is implemented based on the fact that Raspberry Pi could not handle the full YOLO due to its memory capacity limitation, and the results are discussed.

Název v anglickém jazyce

Object Detection by Tiny-YOLO on TurtleBot3 as an Educational Robot

Popis výsledku anglicky

By the unceasing efforts of many scientists, machine learning algorithms are increasing quickly with an enhanced object detection performance for the explicit applications on specific devices. This paper investigates the operation of TurtleBot3 as an educational wheeled autonomous robot which Tiny-YOLO algorithm has been applied as a novel application on it. At first, the required knowledge about the kinematics and dynamics of a differential drive robot with constraints is studied, and a graph where the robot is working under some specific conditions is plotted. The robot operating system (ROS) and simultaneous localization and mapping (SLAM) of the TurtleBot3 have been explained. The robot is equipped with a LiDAR sensor and a camera embedded onto it as a sensor fusion SLAM for a more precise type of mapping. Finally, Tiny-YOLO as a machine learning algorithm for object detection is implemented based on the fact that Raspberry Pi could not handle the full YOLO due to its memory capacity limitation, and the results are discussed.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Networks and Systems

ISBN

978-981992321-2

ISSN

2367-3370

e-ISSN

—

Počet stran výsledku

12

Strana od-do

619 - 630

Název nakladatele

Springer

Místo vydání

—

Místo konání akce

New Delhi

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—