Global agriculture has been significantly impacted by the 21st century’s rapid technological advancement. In order to solve issues like labor shortages, decreased productivity, and ecological concerns, automation and robotics have become crucial. In this study, our team’s prototype for precision and sustainable farming the Ground Autonomous Agricultural Vehicle (GAAV)—is conceptualized, designed, built, and tested. The GAAV combines computer vision, LiDAR and ultrasonic sensors, navigation based on the Global Navigation Satellite System (GNSS/RTK), and a dual-layer control architecture for self-operation. In order to create an affordable and scalable agricultural robot, the project blends traditional engineering with cutting-edge computer, drawing inspiration from historical prototypes like the BOPS-1960 and contemporary systems like DEDALO.With little assistance from humans, the system can carry out a variety of tasks, such as field navigation, precision watering, and pesticide spraying. Stable motion, precise trajectory tracking, and a 25% reduction in chemical use compared to manual approaches were all demonstrated in field tests. The results demonstrate how efficient, safe, and environmentally friendly autonomous ground vehicles have the potential to completely transform agriculture.
Keywords: GNSS/RTK navigation, autonomous agriculture, robotics, precision farming, sustainable mechanization, and smart farming
1. Introduction
There is increasing pressure on the world’s agriculture industry to meet sustainability and environmental goals while producing more food with less resources. Despite its ability to boost production, conventional mechanization is frequently linked to labor intensity, operator fatigue, and inefficient input usage. Automation, digitization, and Industry 4.0 have made the incorporation of robotics into agriculture both necessary and unavoidable.
Unmanned Ground Vehicles (UGVs), another name for autonomous agricultural vehicles, are designed to carry out farming tasks without direct human supervision. They use AI algorithms, machine vision, and GPS-based positioning to carry out precise operations including sowing, spraying, plowing, and monitoring.The design and development of a Ground Autonomous Agricultural Vehicle (GAAV) that combines sustainability and precision farming is the main goal of our project. The GAAV is a small, clever, and flexible system that can carry out routine field tasks on its own. Additionally, the system is adaptable to many crop types and terrains due to its scalability.
The 2022 study by Rondelli, Franceschetti, and Mengoli, which examined the historical and contemporary developments in autonomous farm vehicle development and was published in Sustainability, serves as conceptual guide for the project.
2. Literature Review and Historical Context
2.1 Agricultural Automation’s Development
Agriculture automation is not a novel concept. In the 1950s, both the United States and England started experimenting with cable-guided and radio-controlled tractors. Researchers from the University of Bologna in Italy created the first programmable unmanned tractor, the BOPS-1960, in 1960. It used gyroscopic steering and electromechanical logic to operate in a fully autonomous mode.
Even while early prototypes’ mechanical complexity and lack of computational power hindered them, they set the stage for today’s sophisticated robotic systems. By the late 20th century, robotic platforms and precision-guided tractors had become possible thanks to developments in sensors, GPS, and embedded computing.
2.2 Contributions to Modern Research
Globally, academic institutions and research facilities have created customized UGVs for use in agriculture in recent decades:
HortiBot (Denmark): Vision-based weeding robot capable of navigating between crop rows.
Shrimp (Australia): A field robot designed for fruit detection and environmental mapping.
Armadillo (Denmark): A modular, ROS-based robotic platform for variable field tasks.
DEDALO (Italy): A hybrid electric-petrol tracked vehicle for spraying and mowing in vineyards and orchards.
d for mowing and spraying in orchards and vineyards in Italy.
The combination of automation, robotics, and sustainable agriculture is reflected in these systems. However, access for small and medium farms is restricted by expensive costs and intricate designs; our GAAV seeks to close this gap.
3. Problem Statement and Research Objectives
3.1 Description of the Problem
The issues of accessibility, price, and flexibility still exist in agricultural robots, despite advancements. Manual methods of irrigation and pesticide application not only raise expenses but also put farmers at risk for health problems and uneven harvests.
3.2 Intentions
The goal of this study is to:
Create and build a multipurpose, inexpensive autonomous vehicle for use in agriculture.
LiDAR, IMU, and GNSS/RTK sensors should be integrated for accurate obstacle avoidance and navigation.
Design and implement a reliable two-layer motion and decision-making control system.
Exhibit self-sufficient weeding, irrigation, and pesticide application in controlled field tests.
Assess how well the GAAV performs in terms of accuracy, effectiveness, and sustainability.
4. Methodology
4.1 The Concept of Design
The foundation of our design is a four-wheeled platform (small tractor frame) furnished with:
Chassis: Four-wheel platform with adjustable ground clearance.
Power System: DC motor drive powered by rechargeable Li-ion batteries.
Navigation Module: GNSS/RTK antenna and IMU for localization and heading control.
Vision and Sensing Unit: LiDAR and ultrasonic sensors for environmental awareness.
Control Module: Raspberry Pi as the master processor and Arduino Mega as a low-level motor controller.
4.2 Control System Design
There are two levels at which the control system functions:
Low-Level Control: Uses PID controllers to manage wheel encoders, motor driving, and speed regulating.
High-Level Control: Plans the route, analyzes GPS and LiDAR data, and gives commands for navigational actions (such as turning, halting, and avoiding obstacles).
We used Python and ROS (Robot Operating System) to program the system, enabling autonomous decision-making and real-time sensor fusion.
4.3 Navigation and Path Planning
The GAAV follows paths based on waypoints. The system uses a software interface to upload predefined coordinates. The IMU maintains motion stability in the event of signal dropouts, while the GNSS/RTK module attains sub-meter precision. Rerouting and dynamic obstacle identification are made possible by LiDAR data.
4.4 Field Testing
Tests were carried out on level farmland. The parameters that were noted include:
Path accuracy: a deviation of 8–12 cm on the side.
Spray coverage: Tests using dyes confirm uniform distribution.
Runtime of the battery: 90 to 120 minutes straight.
Velocity: 1-3 km/h, contingent on the load on the terrain.
Logs of the data were kept for further performance analysis.
5. Results and Discussion
5.1 Assessment of Performance
With little deviance from predetermined paths, the GAAV showed reliable and accurate navigation. Safe movement was made possible by the integrated LiDAR’s successful obstacle detection up to a 5-meter range.
Tests of pesticide application showed that targeted spraying reduced chemical use by 25%. During short-term tests, the control system operated steadily without drift or communication failure.
5.2 Efficiency in Energy Use
Eco-friendly use was encouraged by the electric powertrain’s low energy consumption and quiet operation. Integration of solar charging was shown to be a feasible future improvement.
5.3 The Effect on the Economy
It is appropriate for smallholders because its estimated fabrication costs are substantially cheaper than those of commercial agricultural robots.
According to market research, the Chinese market for autonomous agricultural robots is expected to expand at a compound annual growth rate (CAGR) of 32.92%, from USD 1.5 billion in 2024 to USD 10.97 billion by 2032, indicating significant economic potential.
5.4 A Comparative Analysis
In contrast to previous systems like DEDALO and HortiBot, the GAAV prioritizes cost-effectiveness, simplicity, and adaptability while attaining acceptable field performance. It is more adaptable to changing field circumstances thanks to its hybrid sensing technique.
6. Applications
There are other uses for the GAAV platform outside of conventional agriculture, including:
Precision irrigation – based on soil moisture mapping.
Targeted pesticide application – using AI-based weed detection.
Plant health monitoring – through camera-based NDVI analysis.
Logistics and warehousing automation – within agricultural supply chains.
Non-agricultural uses – such as industrial inspection, healthcare logistics, and firefighting robots.
7. Sustainability Factors
Sustainability in agriculture refers to maximizing input usage while preserving the environment. In order to promote sustainability, the GAAV:
Reducing the amount of pesticide and water waste.
Electric operation reduces reliance on gasoline.
avoiding soil compaction by the use of lightweight architecture.
encouraging data-driven farming choices to allocate resources effectively.
These traits are in line with the Sustainable Development Goals (SDGs) of the UN, especially Goals 12 (Responsible Consumption and Production) and 2 (Zero Hunger).
8. Future Outlook And Beyond Agriculture
The project’s next stage seeks to:
Use object recognition powered by AI to detect crops and pests in real time.
To increase runtime, incorporate solar charging modules.
Allow several GAAV units to coordinate as a swarm for collaborative fieldwork.
Create a dashboard in the cloud for remote data analytics and logging.
Look for patent and economic potential for deployment on a rural scale. Logistics and Warehousing, Construction, Healthcare, Manufacturing, Retail, Fire Suppression so on…
Agriculture will become a completely data-driven, autonomous system where machines carry out tasks safely, sustainably, and intelligently as a result of the convergence of robotics.
9. Conclusion
In order to improve farming operations’ efficiency, safety, and sustainability, this study effectively illustrates the design and implementation of a Ground Autonomous Agricultural Vehicle (GAAV).
LiDAR sensing, GNSS/RTK navigation, and intelligent control were all combined to enable the prototype to successfully complete autonomous watering and spraying duties.
Motivated by both historical and contemporary research, the GAAV connects the dots between scholarly innovation and real-world field application. It could develop into a scalable approach to sustainable agricultural mechanization with more work.
By: MD FOKHRUL ISLAM
Write and Win: Participate in Creative writing Contest & International Essay Contest and win fabulous prizes.
About the Author
