Sugarcane diseases are major concern for the global sugarcane market, as they can significantly impact crop yield and quality. This can result in economic losses for farmers and reduced supplies for the sugar industry. In this research, we propose a solution for detecting three classes of sugarcane diseases using the YOLO algorithm. The YOLO version 8 model got a maximum accuracy of 96.67% after being trained and evaluated on a dataset of sugarcane disease images. This high accuracy demonstrates the potential of our proposed method for the early diagnosis and treatment of affected plants. By using the YOLO algorithm, a deep learning technique, our proposed solution can improve the efficiency and effectiveness of disease management in sugarcane. Additionally, the proposed solution can be integrated with robotics technology to enable real-time monitoring and treatment of sugarcane fields. The use of robotics technology can enable the automated monitoring of large sugarcane fields, providing real-time data on the health of the crop, which can help farmers and agronomists make informed decisions on disease management. In conclusion, our proposed solution can help mitigate the impact of sugarcane diseases on the global sugarcane market by providing early diagnosis, efficient treatment, and real-time monitoring of crop health.