Kursi Roda Otonom Berbasis Sensor Fusi Menggunakan YOLOv8 dan Lidar 2 Dimensi

Azzam, Muhammad Khaeral (2024) Kursi Roda Otonom Berbasis Sensor Fusi Menggunakan YOLOv8 dan Lidar 2 Dimensi. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5024201074-Undergraduate_Thesis.pdf] Text
5024201074-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2026.

Download (6MB) | Request a copy

Abstract

Kursi roda adalah alat penting yang membantu mobilitas bagi individu dengan disabilitas, agar dapat melakukan berbagai aktivitas. Kemajuan terbaru dalam teknologi kursi roda berfokus pada peningkatan komponen struktural dan fungsionalitas, termasuk motor listrik, pengontrol, dan sistem penghindaran objek yang lebih baik. Penelitian ini memperkenalkan kursi roda otonom canggih untuk penggunaan dalam ruangan yang dirancang untuk meningkatkan mobilitas dan keselamatan individu dengan keterbatasan fisik. Kursi roda ini menggunakan teknik fusi sensor, mengintergrasikan framework YOLOv8 dengan A1 RPLIDAR untuk sensor 2 dimensi, dan didukung oleh Intel NUC untuk memastikan navigasi real time yang kuat dalam lingkungan dalam ruangan yang kompleks. Hasil penelitian menunjukkan bahwa kursi roda ini memiliki respons yang sangat cepat, dengan uji delay sistem menunjukkan waktu respons rata-rata di bawah 500 milidetik untuk semua perintah navigasi. Namun, tes akurasi berhenti menunjukkan bahwa meskipun sistem ini efektif mendeteksi rintangan, terdapat error jarak stop rata-rata sebesar 211,5 mm karena inersia kursi roda, yang memerlukan penyempurnaan lebih lanjut untuk meningkatkan presisi. Hasil ini menunjukkan potensi integrasi teknologi sensor dan pemrosesan yang lebih baik dalam kursi roda untuk meningkatkan keselamatan dan mobilitas, serta menekankan area untuk pengembangan lebih lanjut guna mengoptimalkan respons real-time dan akurasi dalam navigasi.
=================================================================================================================================
wheelchair is an essential device that aids mobility for individuals with disabilities, al-lowing them to perform various activities. Recent advancements in wheelchair technology focus on enhancing structural components and functionality, including electric motors, controllers, and improved object avoidance systems. This research introduces an advanced autonomous indoor wheelchair designed to improve mobility and safety for individuals with physical limitations. The wheelchair uses sensor fusion techniques, integrating the YOLOv8 framework with A1 RPLIDAR for 2-dimensional sensing, and is powered by Intel NUC to ensure robust real-time navigation in complex indoor environments. The research findings show that this wheelchair has a very fast response, with system delay tests indicating an average response time of under 500 milliseconds for all navigation commands. However, the stop accuracy tests reveal that while the system effectively detects obstacles, there is an average stop distance error of 211.5 mm due to the wheelchair’s inertia, requiring further refinement to improve precision. These results highlight the potential for better integration of sensor technology and processing in wheelchairs to enhance safety and mobility, and emphasize areas for further development to optimize real-time response and accuracy in navigation.

Item Type: Thesis (Other)
Uncontrolled Keywords: Dalam Ruangan, Kursi Roda, Otonom, Autonomous, Indoor, NUC, LIDAR, Wheelchair, YOLOv8.
Subjects: R Medicine > R Medicine (General) > R856.2 Medical instruments and apparatus.
T Technology > T Technology (General) > T57.84 Heuristic algorithms.
T Technology > T Technology (General) > T59.7 Human-machine systems.
T Technology > TA Engineering (General). Civil engineering (General) > TA1573 Detectors. Sensors
T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3070 Automatic control
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Data Transmission Systems
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Muhammad Khaeral Azzam
Date Deposited: 25 Jul 2024 02:46
Last Modified: 25 Jul 2024 02:46
URI: http://repository.its.ac.id/id/eprint/108834

Actions (login required)

View Item View Item