Application of Robotics, Artificial Intelligence and Deep Learning in Modern Agriculture Technology: A Review
Harshad A. Prajapati
Department of Horticulture, Krishi Vigyan Kendra, NAU, Waghai (Dang), India.
D. M. Kadam
Department of Farm Machinery and Power Engineering, College of Agricultural Engineering, JNKVV, Jabalpur, M.P., India.
Shivkanya S. Aitwar
Department of Agricultural Engineering, Maharashtra Institute of Technology, Aurangabad, India.
Prathamesh Dilip Jagtap
Department of Agricultural Engineering, Maharashtra Institute of Technology (An Autonomous Institute), Chh. Sambhajinagar, India.
Debesh Singh
RVSKVV, KVK, MORENA (M.P.), India.
Nirjharnee Nandeha *
SMS, KVK Mahasamund, IGKV, Raipur, India.
Deepanshu Mukherjee
SMS, KVK Mahasamund, IGKV, Raipur, India.
*Author to whom correspondence should be addressed.
Abstract
In order to determine their potential impact in the field of agriculture, the proposed work aims to review the various artificial intelligence (AI) techniques, with a focus on expert systems, robots designed specifically for agriculture, and sensors technology for data collection and transmission. These techniques include fuzzy logic (FL), artificial neural network (ANN), genetic algorithm (GA), particle swarm optimisation (PSO), artificial potential field (APF), simulated annealing (SA), deep learning. The application of AI techniques and robots in cultivation, monitoring, and harvesting is not highlighted in any literature, making it difficult to compare each one simultaneously based on popularity and usefulness while also understanding how each contributes to the agricultural industry. With knowledge of the extent of AI engaged and the robots used, this paper compares three crucial agricultural phases: cultivation, monitoring, and harvesting. The current study offers a comprehensive analysis of over 200 publications that cover the use of automation in agriculture as of 1960 and 2021. It draws attention to the unmet research needs for developing intelligent, self-governing agricultural systems. The frequency of various AI, robotics and deep learning techniques for particular applications in the agriculture industry round out the article.
Keywords: precision agriculture, smart farming, deep learning, CNN, RNN, SVM