By Blake Jackson
A new autonomous robot, designed to scout for grape diseases in vineyards in near-real time with accuracy comparable to skilled human scouts, promises to help track crop-threatening pathogens while reducing labor demands.
The robot’s development was detailed in a titled “PhytoPatholoBot: Autonomous ground robot for near real‐time disease scouting in the vineyard.” This innovation is critical, as managing diseases like powdery and downy mildew is a top priority for grape growers and viticulturists.
“It is by far ranked as the highest and most potent threat to the sustainability and viability of viticulture in New York, as well as broadly on the East Coast,” said Katie Gold, grape pathologist and senior author of the paper, along with Yu Jiang, applied roboticist at Cornell AgriTech in Geneva, New York.
The challenges of disease management are compounded by climate change, stricter chemical regulations, rising pathogen resistance, and long-standing labor shortages. “That’s been a motivation for us: How we can use robots to do this very skilled job?” Jiang said.
“Disease scouting is not something that just anyone can do, [but now our robot] will be able to identify those critical stresses for our food systems.”
Gold added, “In the past, I have regularly hired teams of scouts four or five people to sweep the vineyards and do the work of one robot. Now the robot can do it on its own, with just one person babysitting it.”
The robot, named PhytoPatholoBot, self-navigates between vineyard rows, capturing side-view canopy images. Its AI model identifies canopy and disease pixels, while data from NASA remote sensing, GPS, and modeling helps infer disease risk.
Growers receive near-real-time updates on disease type, location, and severity, allowing targeted treatment and reducing the use of heavy fungicides.
Tested across 10 Cornell pathology vineyards and commercial sites in several states, PhytoPatholoBot proved efficient, accurate, and low-power.
A California startup, co-founded by first author Ertai Liu, plans to produce the robots commercially. Gold noted the technology could expand to other crops, including apples.
Coauthors include Lance Cadle-Davidson, Kathleen Kanaley, and David Combs, who contributed to robot training and implementation at Cornell AgriTech.
Photo Credit: istock-jimfeng
Categories: New York, Crops, Fruits and Vegetables, Education