Smart Robotic System for Crop Automated Harvesting Using YOLOv8 and Robotics

Robotics and AI-powered crop harvesting are revolutionizing modern farming by enhancing efficiency, reducing manual intervention, and increasing crop yields. This study investigates the implementation of YOLOv8, a smart object detection model, for improved real-time fruit recognition and selective picking. The system combines deep learning, IoT connectivity, and robotic automation to identify and pick fruits efficiently. It utilizes a high-resolution camera, a robot arm that can adjust its grip, and cloud computing for data processing to work more effectively. YOLOv8's advanced architecture allows real-time fruit detection even in complex agricultural settings with obstacles and changing lighting conditions. This paper outlines the process of acquiring the dataset, labeling, training, and testing it to achieve a high detection rate. Additionally, IoT monitoring and voice control make it easy for farm workers to use. Smart farming analytics offer useful insights for better resource allocation and eco-friendly farming. The results show a remarkable improvement in harvesting efficiency, accuracy, and scalability. Future improvements include using groups of robots, AI-based quality checks, and blockchain tracing for supply chain transparency. The research shows how AI-driven automation revolutionizes agriculture, leading to a fully autonomous and smart harvesting system. The use of edge computing minimizes data processing latency, allowing fast decision-making. Additionally, intelligent irrigation systems enable water-conserving farming practices, supporting the autonomous harvesting process. The system can be adjusted to various crops and environmental conditions to work optimally in different farming applications.