Designing and development of agricultural rovers for vegetable harvesting and soil analysis.

Abstract

To address the growing demand for sustainable agriculture practices, new technologies to boost crop productivity and soil health must be developed. In this research, we propose designing and building an agricultural rover capable of autonomous vegetable harvesting and soil analysis utilizing cutting-edge deep learning algorithms (YOLOv5). The precision and recall score of the model was 0.8518% and 0.7624% respectively. The rover uses robotics, computer vision, and soil sensing technology to perform accurate and efficient agricultural tasks. We go over the rover's hardware and software, as well as the soil analysis system and the tomato ripeness detection system using deep learning models. Field experiments indicate that this agricultural rover is effective and promising for improving crop management and soil monitoring in modern agriculture, hence achieving the UN's SDG 2 Zero Hunger goals.

Plant phenotyping relevance

トマトの成熟度という植物器官の状態を深層学習で推定する画像ベース手法を、農業ローバーの主要機能として開発しているため。

Code and data availability

The paper's Data Availability statement points to a public Figshare repository containing the authors' tomato image dataset (500 field images with ripe/unripe annotations) used to train the YOLOv5 ripeness-detection model, which is a paper-specific, publicly actionable asset. The other allowed URLs are generic external