AGRISCOUT

SMART AGRICULTURE ROVER FOR REAL-TIME CROP MONITORING AND ENVIRONMENTAL SENSING WITH 2D MAPPING AND BIRD REPELLENT SYSTEM

Abstract

Agriculture is a major contributor to the economic growth of countries like India, where a large portion of the population depends on farming. Rising food demand and climate variability require more efficient and automated agricultural monitoring techniques. Traditional farming relies heavily on manual observation and delayed responses, often resulting in reduced productivity and inefficient resource usage.

To address these challenges, this project presents a Smart Agriculture Rover equipped with IoT-based environmental sensing, automated navigation, 2D mapping, and an intelligent bird-repellent mechanism. The rover integrates an ESP32 microcontroller, soil moisture sensor, DHT22 temperature–humidity sensor, and an LDR for light intensity measurement. Data collected from multiple field locations is transmitted to the cloud in real time via Wi-Fi. The rover’s 2D mapping enables systematic movement and obstacle awareness, enhancing coverage and automation. Experimental results show improved data accuracy, reduced manual effort, and enhanced crop protection. Future enhancements include GPS-based navigation, AI-driven crop analysis, and automated irrigation.

1. Introduction

Smart agriculture is rapidly transforming traditional farming practices by merging IoT, automation, and intelligent sensing technologies. Farmers require real-time analytics to make informed decisions about irrigation, crop health, and environmental changes. Manual monitoring of large fields is time-consuming, labour-intensive, and often inaccurate.

This project introduces an autonomous mobile rover designed to assist farmers by performing continuous environmental monitoring, mapping, and crop protection tasks. The system leverages ESP32-driven IoT communication and sensor fusion techniques to gather crucial field data, detect conditions early, and enable cloud-based decision-making. In addition, the rover integrates a bird-repellent audio system to reduce crop damage. The combination of automation and environmental intelligence provides a low-cost, scalable, and efficient solution for modern agriculture.

1. System Overview

The Smart Agriculture Rover consists of four major functional modules:

a. Environmental Monitoring Subsystem
Soil moisture sensor
DHT22 temperature & humidity sensor
LDR for sunlight intensity

These sensors gather real-time data essential for crop health analysis.

b. Navigation and 2D Mapping
ESP32 microcontroller
Motor driver and DC motors
Ultrasonic obstacle detection
Mapping logic for structured field traversal

This enables systematic rover movement across defined field areas.

c. IoT Communication Subsystem
Wi-Fi-enabled telemetry
Cloud storage for long-term monitoring
Smartphone/PC access to data
d. Bird Repellent System
High-frequency sound emitter
Automated triggering based on rover position or schedule
Block Representation
Smart Rover (ESP32)
│
├── Environmental Sensors: Soil Moisture, DHT22, LDR
├── Motor Driver + DC Motors
├── Ultrasonic Sensor for Obstacle Detection
├── Wi-Fi Cloud Communication
└── Bird Repellent System

1. System Operation

Initialization Phase
The ESP32 boots, initializes sensors, motor drivers, and Wi-Fi, and establishes cloud connectivity.

Data Acquisition
As the rover moves, environmental sensors continuously capture moisture, temperature, humidity, and light intensity.

2D Mapping & Navigation
Based on predefined movement algorithms, the rover:
Traverses the field in rows/columns
Avoids obstacles using ultrasonic feedback
Logs its approximate position

Bird Repellent Activation
The system triggers sound waves periodically or when the rover enters designated zones.

Cloud Upload
Collected data is uploaded to the cloud for real-time monitoring and further analysis.

Completion
After covering the target area, the rover stops and waits for the next command.

1. Methodology

Step 1: Hardware Integration
ESP32 as central microcontroller
Sensors connected to ADC and digital pins
Motor driver (L298N/L293D) for rover movement
Battery and power distribution module
High-frequency buzzer for bird repellent

Step 2: 2D Mapping Logic Development
Grid-based mapping representation
Rover moves in systematic rows (like a lawn mower pattern)
Distance measured using wheel rotation timing / predefined speed
Obstacles detected via ultrasonic sensor

Step 3: IoT Data Transmission
MQTT/HTTP communication to cloud
Database logging
Dashboard for online viewing

Step 4: Bird Repellent Strategy
Emits sound frequencies known to deter birds
Triggered periodically or based on time-of-day

Step 5: System Testing
Indoor testing for navigation accuracy
Field testing for sensor accuracy and wireless performance
Evaluation of coverage efficiency

1. Key Design Considerations
   Sensor Accuracy: Environmental sensors must be calibrated for field conditions.
   Power Management: Stable voltage supply for motors and ESP32 is crucial.
   Obstacle Avoidance: Ensures uninterrupted motion and prevents damage.
   Mapping Precision: Accurate timing and motor control improve path coverage.
   Weather Conditions: Components must withstand outdoor temperature and humidity.
   Bird Repellent Safety: Frequency chosen to avoid harm to livestock or humans.
   Cloud Reliability: Ensures consistent data logging for long-term monitoring.

2. Applications

This rover can be used in:

Small and medium-scale farms
Research in precision agriculture
Remote monitoring of greenhouse environments
Automation studies for agricultural robotics
Pest and bird control experiments
Educational demonstrations in IoT and robotics

1. Conclusion

The Smart Agriculture Rover provides an effective, modern solution to key agricultural challenges by integrating automation, IoT, environmental monitoring, 2D mapping, and crop protection mechanisms. The system reduces manual labour, enhances data-driven decisions, and improves field productivity. Its modular and scalable design makes it suitable for both academic research and practical field deployment. Future advancements—such as GPS-based navigation, AI-powered prediction models, and automated irrigation—can further elevate the impact of this system in sustainable smart farming.