Revolutionizing agriculture: a comprehensive review of agribots, machine learning, and deep learning in meeting global food demands

Abstract

Abstract Agriculture is quickly transforming into a high-tech industry, which is drawing new professionals, investors, and firms. Technology is constantly improving, allowing farmers to increase their output capacity. This growth, modernization, and automation over time have led to a substantial increase in agricultural output. The United Nations is projecting that the population of our world will reach 9.7 billion by the year 2050. Hence, the world needs considerably more food, putting farmers under tremendous pressure to satisfy that need. The one of best solutions for this problem is using Agribots. Agribots assist farmers in a number of ways to enhance output yields. An Agribot, or agricultural robot, is a robot that is used for agricultural applications. Agribots utilize Machine Learning (ML) and Deep Learning (DL) techniques to improve agricultural production and output. ML and DL advancements have enabled agribots to locate, localize, and recognize objects in images and videos. This paper analyzes the three primary research areas in agriculture: The first area is Agricultural Operations, focusing on recent research findings regarding operations such as crop and weed detection, fruit detection, area detection, and disease detection. The next research area discusses the various hardware setups and types of agribots, and finally the machine vision systems of the Agribots. Comparative analyses of machine learning and deep learning approaches have been conducted, along with an exploration of the limitations and future research focus on Agribots.