ATHENS – Say hello to Watson.
A four-wheeled phenotyping robot that operates autonomously or under human control, Watson is taking shape in Changying “Charlie” Li’s lab at the Center for Plant Phenomics and Robotics on the University of Georgia’s Athens campus in collaboration with researchers from the College of Agriculture and Science for the environment.
Watson’s progress underscores UGA’s pioneering role in integrated precision agriculture, an approach that applies automation technology to agriculture. The PPRC advances this role by facilitating interdisciplinary, collaborative research across CAES, the College of Engineering, and other UGA units.
“Watson can carry sensors and data collection tools in the field,” said Li, director of the PPRC and professor of engineering. “We use three color RGB cameras to collect color images of peanut plants. With these images, we can construct 3D models of plants and measure morphological characteristics such as crown height, size and volume.
“Color images can also be used to detect foliar diseases. We plan to add additional sensors, such as a multispectral camera, to measure features that cannot be measured with color images.
Drone images help peanut growers at the UGA Tifton campus measure traits of different hybrid peanut genotypes in the field — crown volume, plant height and plant vigor — that can be seen more easily from above rather than from the ground. But studying finer details requires higher-resolution images, so they collaborated with Li’s group to incorporate Watson into their phenotyping toolset.
“We want to develop algorithms and machine learning techniques to teach robots how to measure disease symptoms to identify susceptibility as well as hybrids with improved disease resistance,” said Nino Braun, assistant researcher at CAES.
A key factor for peanut growers is seedling vigor, a genetically influenced function of seedling size after germination that reveals how quickly they develop into larger, healthier, more resilient plants.
“If we can accurately measure seedling vigor among plants and hybrid populations, our cultivars or cultivars that we release may have some of these traits with high seedling vigor,” Brown explained.
A human can evaluate a few hundred parcels a day, but one or two robots or UAVs could evaluate thousands in the same range.
“The more genotypes we can evaluate, the faster and cheaper we can create genetic gain to make vastly improved new peanut varieties,” Brown added.
In addition, Brown and his colleagues are developing an automated process in which seeds that will produce high-oleic peanuts—which the confectionery industry favors because of their long shelf life—are identified and separated from those with normal oleic acid content. used for peanut butter and similar products.
The new process means breeders can have both high-oleic and normal-oleic breeding pipelines, Brown said.
“This makes it much cheaper for us and provides high productivity for developing high oleic varieties,” he noted.
CAES agricultural engineer and professor Glen Rains leads a research group that modifies an off-the-shelf soil sampling robot to perform agricultural work. ‘Little Red Rover’ uses mobile attachments for seed planting, pest scouting, weed management and harvesting. A multi-functional robotic arm is mounted on the front. Sensory data and artificial intelligence guide the rover’s activities.
Aimed at small and medium farms, the rover is designed to be economical, easy to use, scalable and robust.
“We are looking at applications for peanuts and cotton and expect to expand into vegetables as well,” Raines said. “It’s basically a utility tool like a tractor that can be used all year round, so it doesn’t have to sit in the shed most of the time.”
CAES Assistant Professor and UGA Cooperative Extension Precision Agriculture Specialist Simer Virk rigs and tests various sensors on standard farm machinery that feed performance data to a display in the machine’s cab.
For example, sensors mounted on board a large planter ensure that the desired number of seeds are sown automatically at the prescribed depth and spacing. Other sensors measure properties such as soil moisture, temperature and organic matter.
If the operator sees that the soil isn’t moist enough for the initial depth setting, “he can act on that information in real time and direct the machine to plant seed a little deeper,” Virk said.
Likewise, when a field’s soil texture changes from clay to sand, the machine operator is notified and can change planting settings while in the field “to maximize the planter’s performance in each soil type.”
Automation also allows for precise application of chemicals. Cameras mounted on the sprayer “detect and identify where the weeds are between the rows and where the plants are and turn the nozzles only where they need to spray,” Virk said.
An innovation originally developed at CAES, variable rate irrigation for pivot irrigation systems helps growers conserve water and improve efficiency by irrigating crops where and when needed with the exact amount of water needed, according to university professor George Velidis , head of the Vellidis Research Group at CAES.
“Sandy soil holds less water than clay, for example, so sandy areas in a field require less water application more often than clay areas,” he explained.
This soil texture information, described by field “recipe maps,” is supplemented by evaporation data and daily, detailed weather forecasts to produce estimates of which specific areas of the field will need water at what intervals and how much to be applied. This information is encoded in the prescription card.
Forecasts are sent to an app on the grower’s smartphone or smart device, which relays them to large pivot irrigation systems equipped with a VRI controller and GPS receiver.
“The GPS tells you where you are in the field, so it can translate that position on the map to see how much water needs to be applied at that location,” Velidis said.
Agriculture in the future will be intelligent, precise and more environmentally responsible, Li predicted.
“Being intelligent means that farm and plant management will be done autonomously with robots using artificial intelligence and the process will be self-controlled without human intervention,” he said. “Being precise means that through sensors and automation, crop management can be precisely controlled at the plot or plant level to minimize farming inputs while maintaining maximum productivity. This can reduce the use of water, energy, carbon, pesticides and fertilizers to make agriculture greener.”