AI-Assisted Vision for Agricultural Robots

Abstract

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.

Integrated Management of Pathogens and Microbes on <em>Cannabis sativa</em> L. (Cannabis) under Greenhouse Conditions

“…The location of the diseased plants should be recorded, and if the causal pathogen is unclear, diagnostic testing should be performed, typically through the submission of samples to a diagnostic laboratory [4,7]. In addition to visualization of these areas with the naked eye, the utility of infrared (IR) and artificial intelligence (AI)-powered scouting technologies could be of value as they have been used in a range of other crops [53][54][55][56][57], but further evaluation of how these technologies could be modified for application to cannabis is needed. A discussion of these technologies is presented in Sections 2.10.5 and 2.10.6 of this article.…”

Agricultural Robotics and Automation [TC Spotlight]

“…Stateoftheart progress in research and future challenges is docu mented in a wide range of review papers and book chapters addressing agriculture in general [1], [3], [4], [5] and specific application domains, including phenotyping [6], [7], [8] ara ble farming [9], livestock farming [10], greenhouse horticulture [2], orchard management [11], forestry [12], and food processing [13]. Review papers also address specific technologies in the context of agricultural robotics, such as computer vision [14], [15], active perception [16], unmanned aer ial vehicle technologies [17], [18], cov erage path planning in arable farming [19], and grasping and soft grasping [20], [21]. Some illustrative examples of agrifood robotics are documented in Figure 2.…”

A Synthetic Review of Various Dimensions of Non-Destructive Plant Stress Phenotyping

“…Although plant stress phenotyping can be carried out using either destructive (biochemical analysis) or non-destructive (optical sensing) techniques [9,10], it is almost a consensus that non-invasive optical sensing technologies are highly suitable for seeing and examining plants under stress, as these methods are rapid, reliable, and repeatable [3,11]. Optical sensing utilizes optical waves (electromagnetic radiation) to interact with the object and feedback spectral characteristics.…”