Machine Vision and Machine Learning for Intelligent Agrobots: A review

Abstract

An intelligent precise autonomous farming by an agricultural robot achieves the farm duties possibly harvesting, weed detection, disease identification, pruning and fertilizing deals with path planning and mapping of the unstructured and uncertain environment. A machine vision-based Agrobots along with artificial intelligence provides unmanned ground vehicle and unmanned aerial vehicle to navigate the path and to implement the agricultural task for minimizing labour and increasing quality food production. The perception-related work uses a machine learning algorithm to detect the feature and analyze the agricultural tasks for the autonomous machine. The trained data sets create the ability for robots to learn and decide the farm practices. The dawn of autonomous system design gives us the outlook to develop a wide range of flexible agronomic equipment based on multi-robot, smart machines and human-robot systems which lessen waste, progresses economic feasibility also reduces conservational impact and intensifies food sustainability. The multi-tasking Agrobots overcomes the effort of farmers in agricultural husbandry, independent of the climatic conditions. In this paper, a study on Agrobots effective in a diverse environment, its control and action process conjoined with mapping and detection using machine vision and machine learning algorithms are distinguished.