Leveraging YOLO Deep Learning for Real-Time Weed Detection with a Mini Rover

Agriculture was the most modified and developing industry, and it needed to be more developed. Weed infestation is a serious problem in agriculture as it reduces crop yield and increases costs through competition for vital resources. Weeds compete with crops for essential resources such as nutrients, water, and sunlight, leading to reduced productivity and increased costs for farmers. The growth of weeds in agricultural fields is influenced by several factors, including soil conditions, climate, and farming practices. Traditional weed control methods include manual removal and herbicides, which are time-consuming and harmful to the environment. Efficient solutions are being developed with advancements in artificial intelligence, computer vision, and robotics. We aim to develop an efficient, eco-friendly, and automated weed control system that minimizes manual labor, reduces chemical usage, and improves overall crop yield. The proposed system has the potential to transform traditional farming practices, paving the way for a more sustainable and technologically advanced agricultural landscape. This paper suggests an AI-driven weed detection system that integrates the YOLO deep learning model with a mini rover. The rover captures images in real time, distinguishes weeds from crops, and takes the initiative to shoot targeted miniweeds. The method increases productivity in agriculture without increasing environmental harm and labor work, thus promoting sustainable agriculture.