Paper Contents
Abstract
Plastic waste accumulation on water surfaces is a critical environmental issue, necessitating automated solutions for effective waste removal. This paper presents the design and implementation of an autonomous robotic system, AQUACLEANBOT, for efficiently detecting and collecting plastic waste from water surfaces. The system integrates computer vision-based object detection using the YOLOv8 Nano model, which accurately identifies floating plastic bottles in real time. A Raspberry Pi 5-controlled vision-based navigation mechanism enables precise movement toward detected waste, utilizing a dual-motor propulsion system with a 3D-modeled shaft for efficient maneuverability. The robot employs PVC pontoons for stability and buoyancy, ensuring smooth operation in varying aquatic environments. A labeled dataset of plastic bottles was compiled and annotated using Roboflow, allowing the YOLOv8 model to achieve high detection accuracy in real-world conditions. The AQUACLEANBOT project contributes to sustainable water conservation efforts, offering a low-cost, scalable, and environmentally friendly solution for mitigating plastic pollution in aquatic ecosystems.
Copyright
Copyright © 2025 HANNAH RAIHAANAH. This is an open access article distributed under the Creative Commons Attribution License.
