AGRO: An Autonomous AI Rover for Precision Agriculture
Simar Ghumman, Fabio Di Troia, William Andreopoulos, Mark Stamp, Sanjit Rai
TL;DR
AGRO presents an autonomous ground rover for precision agriculture that integrates LiDAR-based navigation, RTK-GPS positioning, and a YOLO-powered pistachio yield estimation pipeline. The system features a ground-based, real-time detection workflow using a custom 64MP image dataset, a dedicated hardware stack, and a Mission Planner-driven autonomy framework. Key contributions include end-to-end hardware/software integration, a robust pistachio dataset with augmentation, and a YOLOv10 detector achieving $mAP@50=0.9888$ and $89.34\%$ test accuracy, demonstrating practical utility for data-driven orchard management. The work highlights practical implications for real-time decision support and outlines concrete improvements, such as onboard compute, expanded sensing, and alternative ML architectures, to enhance autonomous field performance.
Abstract
Unmanned Ground Vehicles (UGVs) are emerging as a crucial tool in the world of precision agriculture. The combination of UGVs with machine learning allows us to find solutions for a range of complex agricultural problems. This research focuses on developing a UGV capable of autonomously traversing agricultural fields and capturing data. The project, known as AGRO (Autonomous Ground Rover Observer) leverages machine learning, computer vision and other sensor technologies. AGRO uses its capabilities to determine pistachio yields, performing self-localization and real-time environmental mapping while avoiding obstacles. The main objective of this research work is to automate resource-consuming operations so that AGRO can support farmers in making data-driven decisions. Furthermore, AGRO provides a foundation for advanced machine learning techniques as it captures the world around it.