Implementasi YOLOv8-DeepSORT Dan ESP32 Untuk Deteksi Objek Pada Robot Penghindar Rintangan

Rasjid, Azka Avicenna (2024) Implementasi YOLOv8-DeepSORT Dan ESP32 Untuk Deteksi Objek Pada Robot Penghindar Rintangan. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) Cover.pdf Download (873kB)
	Text (Bab 1) Bab 1.pdf Download (390kB)
	Text (Bab 2) BAB 2.pdf Restricted to Repository staff only until 17 July 2026. Download (1MB)
	Text (Bab 3) BAB 3.pdf Restricted to Repository staff only until 17 July 2026. Download (649kB)
	Text (Bab 4) BAB 4.pdf Restricted to Repository staff only until 17 July 2026. Download (1MB)
	Text (Bab 5) BAB 5.pdf Download (191kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf Download (415kB)

Abstract

In the era of rapid technological development, the role of robots is increasingly popular and can have a significant impact on human life. Increasing the intelligence and independence of robots has become a major focus in the development of robotics technology. Robots are not only developing in the academic or industrial world, but several fields have applied advances in robot technology. This research aims to implement YOLOv8-DeepSORT and Arduino on an obstacle avoidance robot. You Only Look Once (YOLO) is an algorithm with Convolutional Neural Network to perform object detection which is then connected with Deep Association Metric Simple Online and Realtime Tracking (DeepSORT). The implementation of YOLOv8-DeepSORT aims to test the robot's navigation capabilities in detecting obstacles such as chairs, humans, and garbage cans in front of the robot. This intelligent robot is designed cost-effectively configured with an arduino as well as a motor protector and a laptop running the operating system. From the results of this study obtained in YOLOv8 training using 100 epochs which resulted in precision 0.97, recall 0.95, and mAP50 0.99. The system is designed using the Python programming language.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Rahmat, Basuki	NIDN0023076907	basukirahmat.if@upnjatim.ac.id
Thesis advisor	Sihananto, Andreas Nugroho	NIDN0012049005	andreas.nugroho.jarkom@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Azka Avicenna Rasjid

Date Deposited:

17 Jul 2024 06:09

Last Modified:

17 Jul 2024 06:09

URI:

https://repository.upnjatim.ac.id/id/eprint/25915