| Yazarlar (4) |
Dr. Öğr. Üyesi Memduh KÖSE
Kırşehir Ahi Evran Üniversitesi, Türkiye |
Bünyamin Mert
Kırşehir Ahi Evran Üniversitesi, Türkiye |
|
Melikhan Kaygusuz
Kırşehir Ahi Evran Üniversitesi, Türkiye |
|
Hakkı Alparslan Ilgın
Kırşehir Ahi Evran Üniversitesi, Türkiye |
| Özet |
| This study focuses on a quadruped robot project where object detection and identification are carried out using a Raspberry Pi 4 Model B and the Raspberry Pi V4 camera module. To achieve this, the YOLO (You Only Look Once) family's YOLOv3 version was chosen, and it was integrated with the Darknet framework, developed by Joseph Redmon, which operates on the CUDA platform, under a single artificial intelligence network. Quadruped robots encounter various natural and artificial obstacles while moving, such as height differences, terrain conditions, distance variations, solid and liquid objects, as well as living beings. In this research, YOLO model and developed AI algorithms were used to recognize and locate these types of obstacles the robot may face during its walking process. The ultimate goal of the study is to develop a system that can detect and position objects and humans and analyze environmental factors. To this end, research on image processing for quadruped robots was conducted, and object detection was successfully achieved using YOLOv3. |
| Anahtar Kelimeler |
| Artificial Intelligence | DarkNET | Quadruped robot | Raspberry Pi 4 Model B | YOLO V3 |
| Bildiri Türü | Tebliğ/Bildiri |
| Bildiri Alt Türü | Tam Metin Olarak Yayınlanan Tebliğ (Uluslararası Kongre/Sempozyum) |
| Bildiri Niteliği | Alanında Hakemli Uluslararası Kongre/Sempozyum |
| Doi Numarası | 10.1109/SIU66497.2025.11111751 |
| Bildiri Dili | İngilizce |
| Kongre Adı | 33rd Signal Processing and Communications Applications Conference (SIU) |
| Kongre Tarihi | 25-06-2025 / |
| Basıldığı Ülke | Türkiye |
| Basıldığı Şehir | İstanbul |
| Atıf Sayıları |
