Agribot: Plant Disease Detection and Spraying Robot

The proposed Agribot system demonstrates the effective use of artificial intelligence and robotics in modern agriculture. By combining image processing, deep learning, and automated spraying, the system is capable of identifying plant diseases at an early stage and providing timely treatment. The Raspberry Pi and camera module work together to capture and analyze leaf images, while the CNN model accurately classifies plant health conditions. Upon detecting an infected plant, the spraying mechanism applies pesticide only where required, reducing unnecessary chemical usage.   The implementation of this system offers several advantages, including reduced pesticide consumption, lower environmental impact, decreased labor requirements, and improved crop protection. The results show that intelligent image-based disease detection can enhance farming efficiency and support better decision-making in crop management. The system also provides a practical and affordable solution for precision agriculture.   In conclusion, Agribot represents an important step toward automated and sustainable farming practices. The successful integration of embedded systems, machine learning, and robotic technology highlights its potential for real-world agricultural applications. With future improvements such as advanced navigation, IoT connectivity, and support for multiple crop varieties, the system can become a more versatile and effective tool for smart agriculture.

1.                 A. O. Santhosh, A. Sagar, M. Govindaswamy, S. Anees, and M. K. M., “Agni – A Plant  Disease Detection Robot,” International Journal of Engineering Research & Technology (IJERT), vol. 12, no. 5, pp. 266–274, May 2023. 2.                 N. R. Dhumale and P. C. Bhaskar, “Smart Agricultural Robot for Spraying Pesticide with Image Processing based Disease Classification Technique,” Proceedings of the International Conference on Emerging Smart Computing and Informatics (ESCI), AISSMS Institute of Information Technology, Pune, India, 2021. 3.                 F. G. Destreza, R. Concepcion Jr., J. A. Alano, J. J. De Padua, and K. J. Butiong, “Smart Agribot: Advanced CNN-Based Disease Detection in Green Beans with EfficientDet & Auto-Spraying,” International Journal of Integrated Engineering (IJIE), vol. 17, no. 2, pp. 230–240, Batangas State University, Philippines, 2025.  4.                 S. Shetty, R. Bhosale, R. Naik, R. Lokare, R. Mane, and S. Patil, “Agribot – System for Plant Disease Detection and Pesticide Sprinkling,” SSRN Electronic Journal, K. J. Somaiya Institute of Engineering and Information Technology, University of Mumbai, India, 2021.  5.                 Amrita, S. K. Nayak, R. Kumar, and S. Tomar, “Plant Disease Detection Using Deep Learning,” Journal of Mechanics of Continua and Mathematical Sciences, Vol. 20, No. 5, pp. 134–149, May 2025.  6.                 G. U. Shinde, R. C. Agrawal, I. Mani, A. Agrawal, U. M. Khokde, S. V. Muley, D. D. Tekale, S. R. Bhalerao, and O. D. Kakade, “Digital Farming Solution by Automation Using Agri-Bot, Agri-Drone, and Agri-AGV for Organic Farming Practices,” in Agriculture Digitalization and Organic Production, Smart Innovation, Systems and Technologies, A. Rounhin et al., Springer Nature Singapore, 2024.  7.                 M. Wyawhare, J. Madake, A. Sarkar, A. Parkhe, A. Khaspe, and T. Gaikwad, “Crop-Weed Detection, Depth Estimation and Disease Diagnosis Using YOLO and Darknet for Agribot: A Precision Farming Robot,” in Proceedings of International Conference on Principles of Computing, Computing and Data Analytics: Algorithms for Intelligent Systems, Springer Nature Singapore, 2023.  8.                 S. K. P. M., S. J., V. Savitha, B. U. Sharan, and A. Suresh, “Automatic Detection of Diseased Plant Using Robotics and Image Processing,” International Journal of Creative Research Thoughts (IJCRT), vol. 6, issue 2, DSCE, Bengaluru, India, Apr. 2018.