Pengembangan Kursi Roda Otonom Berbasis YOLOV8 Untuk Penghindaran Obstacle

Kusuma, I Gst Ngr Agung Hari Vijaya (2024) Pengembangan Kursi Roda Otonom Berbasis YOLOV8 Untuk Penghindaran Obstacle. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211940000073-Undegraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (41MB) | Request a copy

Abstract

Pengembangan kursi roda otonom telah menjadi semakin penting dalam meningkatkan mobilitas bagi individu dengan mobilitas terbatas. Studi ini mengusulkan pengembangan sistem kursi roda otonom berbasis YOLOv8 untuk menghindari obstacle, khususnya fokus pada deteksi obstacle manusia. Dengan memanfaatkan kemampuan deteksi objek yang canggih dari YOLOv8, sistem yang diusulkan bertujuan untuk mendeteksi dan menghindari obstacle manusia secara efektif. Sistem tersebut mendeteksi manusia melalui video menggunakan Intel NUC dan Kamera. Obstacle yang terdeteksi membuat NUC mengirim perintah ke ESP32 untuk menjalankan motor untuk melakukan manuver penghindaran. Pengujian performa keberhasilan penghindaran dilakukan dengan 30 kali percobaan pada objek manusia yang diam. Hasil pengujian menunjukkan bahwa kursi roda berhasil menghindar sebanyak 30 kali tanpa gagal, memberikan tingkat keberhasilan sebesar 100%. Hal ini menunjukkan bahwa sistem kursi roda otonom yang dirancang mampu melakukan penghindaran rintangan dengan sangat baik.
=========================================================================================================

The development of autonomous wheelchairs has become increasingly important in improving mobility for individuals with limited mobility. This study proposes the development of a YOLOv8-based autonomous wheelchair system for obstacle avoidance, specifically focusing on human obstacle detection. By utilizing the advanced object detection capabilities of YOLOv8, the proposed system aims to effectively detect and avoid human obstacles. The system detects humans through video using an Intel NUC and a camera. When an obstacle is detected, the NUC sends a command to the ESP32 to operate the motor to perform avoidance maneuvers. Performance testing of the avoidance success was conducted with 30 trials on stationary human objects. The test results showed that the wheelchair successfully avoided obstacles 30 times, providing a success rate of 100%. This indicates that the designed autonomous wheelchair system is capable of performing obstacle avoidance without mistake.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Kursi Roda Otonom, YOLOV8, Intel NUC, ESP32, Deteksi Manusia, Bantuan Mobilitas, Autonomous Wheelchair, YOLOv8, Intel NUC, ESP32, Human Detection, Mobility Aid.
Subjects:	R Medicine > R Medicine (General) > R856.2 Medical instruments and apparatus. T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T59.7 Human-machine systems. T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Data Transmission Systems T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	I Gst Ngr Agung Hari Vijaya Kusuma
Date Deposited:	06 Aug 2024 10:01
Last Modified:	06 Aug 2024 10:01
URI:	http://repository.its.ac.id/id/eprint/111406

Actions (login required)

View Item