Implementasi Yolo V8 pada Prototipe Autonomous Underwater Robot Berbasis Raspberry Pi 5 Guna Menanggulangi Pencemaran Sampah Plastik di Daerah Perairan.

Plastic waste pollution in the aquatic environment poses a serious threat to marine ecosystems and human health. This research aims to develop a prototype of an Autonomous Underwater Robot (AUR) based on the Raspberry Pi 5 equipped with the YOLO V8 algorithm for real-time detection and classification of plastic waste. This AUR uses a PID control system for precise movement stabilization and navigation. The research methodology includes three stages: analysis, design, and implementation, with a System Development Lifecycle (SDLC) approach. The results show that YOLO V8 achieves an object detection mAP of 0.6772 at the IoU threshold of 0.5, with a detection accuracy of 89.6%. The optimal PID setting (Kp:Ki = 125:12:8) results in an object center accuracy of 96.4%, orientation stability of 90.8%, and a completion time of 2 seconds. These findings show that AUR is effective in dealing with plastic waste in waters in a sustainable manner, with implications for improving waste management solutions in the marine environment. [ABSTRACT FROM AUTHOR]