Robotics has been increasingly relevant over the years. The ever-increasing demand for productivity, the reduction of tedious labor, and safety for the operator and the environment have brought robotics to the forefront of technological innovation. The same principle applies to agricultural robots, where such solutions can aid in making farming easier for the farmers, safer, and with greater margins for profit, while at the same time offering higher quality products with minimal environmental impact. This paper focuses on reviewing the existing state of the art for vision-based perception in agricultural robots across a variety of field operations; specifically: weed detection, crop scouting, phenotyping, disease detection, vision-based navigation, harvesting, and spraying. The review revealed a large interest in the uptake of vision-based solutions in agricultural robotics, with RGB cameras being the most popular sensor of choice. It also outlined that AI can achieve promising results and that there is not a single algorithm that outperforms all others; instead, different artificial intelligence techniques offer their unique advantages to address specific agronomic problems.
This study demonstrates the potential of using low-altitude multispectral imagery data to assess irrigation and fertilization techniques and the relative degree of plant water and nutrient stress. This study aims to create a methodology that can be widely used by vertical farms. Techniques were used for early water and nitrogen stress detection using multispectral reflectance systems in an indoor environment with artificial lighting. The methodology focuses on irrigation and nutrition, that sets schedules, and automatically updates a decision-making system based on crop reflectance data and simplified reflectance indices. The experimental process took place on the premises of CphFarmHouse in Denmark. The results showed that crop reflectance increased due to water and nitrogen deficiencies. The detected reflectance increase was significant on the third day of the experiment when irrigation and fertilization were not applied. It should be noted that during the experimental period, the researchers did not detect water or nitrogen deficiencies visible to the naked eye. More specifically, the Normalized Difference Vegetation Index (NDVI) and the Photochemical Reflectance Index (PRI) showed statistically significant differences between the control treatment and the two stress treatments with limited water and nitrogen. Additionally, based on the reflectance measurements and the measured physiological crop parameters, significant correlations (p < 0.01) were observed mainly between the PRI and the chlorophyll content, the photosynthetic efficiency and the stomatal conductance (r = 0.84/0.90, 0.73/0.66, 0.61/0.66 among the nitrogen and water treatments). The research provides data analysis results on sensors and approaches for crop reflectance measurements as well as spectral indices for remote water and nitrogen detection. Finally, the results provide a feasibility analysis, suggesting that multispectral images could be used as a rapid tool to estimate the physiological status of plants, which is indicative of the spatial variation in the vertical farm.