Search

Global food production depends upon successful pollination, a process that relies on natural and managed pollinators. However, natural pollinators are declining due to different factors, including climate change, habitat loss, and pesticide use. Thus, developing alternative pollination methods is essential for sustainable crop production. This paper introduces a robotic system for precision pollination in apples, which are not self-pollinating and require precise delivery of pollen to the stigmatic surfaces of the flowers. The proposed robotic system consists of a machine vision system to identify target flowers and a mechatronic system with a 6-DOF UR5e robotic manipulator and an electrostatic sprayer. Field trials of this system in 'Honeycrisp' and 'Fuji' apple orchards have shown promising results, with the ability to pollinate flower clusters at an average spray cycle time of 6.5 seconds. The robotic pollination system has achieved encouraging fruit set and quality, comparable to naturally pollinated fruits in terms of color, weight, diameter, firmness, soluble solids, and starch content. However, the results for fruit set and quality varied between different apple cultivars and pollen concentrations. This study demonstrates the potential for a robotic artificial pollination system to be an efficient and sustainable method for commercial apple production. Further research is needed to refine the system and assess its suitability across diverse orchard environments and apple cultivars.

Apple trees, being deciduous, shed leaves each year. This process is preceded by the change in leaf color from green to yellow (also known as senescence) during the fall season. The rate and timing of color change are affected by factors including nitrogen (N) concentration in leaves. The green color of leaves and the speed at which it turns yellow during senescence are highly dependent on chlorophyll content, which in turn depends on nitrogen concentration in the leaves. The assessment of leaf color during this period can therefore provide important information on the nitrogen status of apple trees. This study focused on a machine vision-based system to quantify the timing and change in leaf color during the fall and correlate that information to leaf nitrogen content. The color and 3D image dataset used in this study was collected over five weeks in the fall of 2021 and 2023 at a commercial orchard (tall spindle architecture) using a ground-vehicle-based stereo vision sensor. First, the point cloud obtained from the sensor was used to segment the tree canopies using color and depth thresholding methods in the natural orchard environment. Then, the color information of the segmented canopy area was quantified using a custom-defined metric, \textit{yellowness index} (a normalized ratio of yellow to green foliage in the tree) that varied from $-1$ to $+1$ ($-1$ being completely green and $+1$ being completely yellow), which gives the proportion of yellow leaves on a tree. A K-means-based method and a gradient boosting method were used to estimate the \textit{yellowness index}. The gradient boosting method proposed in this study was found to be superior to the K-means-based method, achieving an $R^2$ of 0.72 in estimating the \textit{yellowness index}. The results showed that the metric was able to capture the gradual color transition from green to yellow over the study period.