Smart Spraying Rover

Abstract

The Smart Spraying Rover is an autonomous agricultural vehicle designed to optimize pesticide and fertilizer application through intelligent sensing and control. Traditional spraying methods often result in excessive chemical use, uneven coverage, and environmental pollution. This project aims to overcome these challenges by integrating IoT, machine vision, and automation technologies into a compact rover system.

Introduction

The Smart Pesticide Spraying Rover is an autonomous agricultural vehicle designed to identify diseased plant leaves and apply pesticides only where needed, reducing chemical usage and promoting sustainable farming. It integrates camera-based disease detection using TinyML, RFID-based indoor positioning for navigation, and an ESP8266 controller for system coordination and wireless communication.

The main objectives include designing the autonomous rover platform, implementing real-time leaf disease detection using Edge Impulse, enabling precise spray activation through the NodeMCU controller, transmitting operational data via Wi-Fi, and demonstrating reduced pesticide consumption compared to conventional spraying.

A brief literature survey highlights advancements in AI-based plant disease detection using embedded systems, drones, and IoT platforms.

Methodology

The system works through five stages: initialization, navigation, image processing, decision-making, and selective spraying.

• Navigation (RFID-based IPS): RFID tags placed along crop rows guide the rover. An RFID reader identifies tag locations, triggering straight movement or programmed turns using an H-bridge motor driver.

• AI Disease Detection (Edge Impulse): A lightweight CNN model is trained on plant images, deployed on an ESP32-CAM, and used for real-time classification of leaves as healthy or diseased.

• Targeted Spraying & IoT: When disease is detected, the main controller activates a small pump to spray only the affected area. The system logs location, time, and detection results and sends them to cloud platforms like Firebase or ThingSpeak. A dashboard displays rover activity for remote monitoring.

System Components

Key components include the NodeMCU (ESP8266) main controller, AI processing camera module, motor driver, DC gear motors, RFID reader, Wi-Fi module, spraying pump, and stable power supply.

Implementation Requirements

• Hardware: ESP32/Arduino, ultrasonic sensor, camera module, Wi-Fi, battery, and power system.

• Software: Arduino IDE, Embedded C/C++, Edge Impulse, and cloud IoT services.

Algorithm (Simplified Steps)

1. Start system

2. Initialize sensors, motor driver, pump, and controller

3. Move rover

4. Capture and preprocess image

5. Classify leaf condition

6. Spray if diseased

7. End

Conclusion

Autonomous Precision Sprayer Rover using RFID and Embedded AI can be achieved successfully. The core components, including the custom RFID-based navigation for indoor positioning, the deployment of a low-latency TinyML model on the ESP32-CAM for real-time disease detection, and the IoT data transmission capabilities, have been analyzed and selected. The resulting system promises to deliver a practical, economical, and precise solution to modern agricultural challenges by minimizing pesticide usage, maximizing operational safety, and providing actionable data to the farmer.

References

[1] https://www.researchgate.net/publication/381030590_Agricultural_Pesticide_Spraying_Robot [2] https://www.hackster.io/538517/embedded-ai-for-real-time-leaf-disease-detection-c9ca46 [3] https://ijariie.com/AdminUploadPdf/Smart_Pesticide_Sprayer_Robot_Using_IOT__In__Agriculture_Field_ijariie26703.pdf [4] https://www.researchgate.net/publication/395019790_Applying_computer_vision_and_predictive_analytics_to_optimize_water_use_reduce_pesticide_application_and_increase_crop_yield_sustainably [5] https://www.researchgate.net/publication/224146356_Working_and_Analysis_of_the_H_Bridge_Motor_Driver_Circuit_Designed_for_Wheeled_Mobile_Robots [6] https://www.researchgate.net/publication/371408123_IOT_Enabled_Pesticide_Sprayer_Robot [7] https://circuitdigest.com/microcontroller-projects/object-recognition-using-esp32-cam-and-edge-impulse

Copyright

Copyright © 2025 Sapna Jadhav, Mayuri Nawale, Rutuja Shelke, Ritu Kadam. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.