USDA awards Cornell $7.5 million to develop autonomous orchard robots for apple and cherry farming operations

Cornell University just landed a four-year, $7.5 million grant from the USDA’s Specialty Crop Research Initiative to build a Center of Excellence for Orchard Robotics inside its Department of Biological and Environmental Engineering. Professor Manoj Karkee is leading the project, which pulls together nine organizations — Washington State University, Oregon State University, Penn State, Michigan State, Carnegie Mellon, Stanford, and Israel-based Fresh Fruit Robotics, among others — to build autonomous robots that can handle the hardest, most labor-intensive tasks in apple and cherry farming.

Cornell receives $7.5 million USDA grant to build orchard robotics center

The USDA’s Specialty Crop Research Initiative put up this money as part of a broader effort to tackle labor shortages and rising costs in specialty crop farming. The funding creates a new Center of Excellence for Orchard Robotics at Cornell — a hub meant to push orchard automation out of the lab and into real commercial fields.

Karkee co-leads the project with Matthew Whiting, a professor of tree fruit horticulture at Washington State University. Nine collaborating organizations span academia, industry, and the grower community — a deliberate mix to keep the research honest about real farming constraints. Washington Fruit and Produce Co., a fourth-generation family operation farming 10,000 acres of apples and cherries in Yakima, Washington, is one of the grower partners at the table.

Sociologists and economists are also involved, tasked with understanding the cultural and financial factors that shape whether farmers actually adopt new technology.

Rising labor costs and worker safety concerns drive demand for automation

The economic pressure behind this project isn’t complicated. At Washington Fruit and Produce Co., labor used to make up about 45% of total costs. Now it’s over 60%. Apple prices, meanwhile, haven’t moved in two decades. “Who gets squeezed at that point? It’s not the warehouse, and it’s not the grocery store. It’s the farmers,” said Gilbert Plath, the company’s technology director.

The financial pressure is only part of it. Harvesting apples means 12-hour days for months — work that leads to repetitive motion injuries, ladder falls, and machinery accidents. “Some of these farming operations are not just labor-intensive, they’re risky for human health and safety,” Karkee said.

Most U.S. agricultural crops are already machine-harvested. Corn, cotton, soybeans — nobody’s picking those by hand anymore. Specialty fruit orchards have been the stubborn exception, because delicate fruit and complex tree canopies have made automation genuinely hard to crack.

One key insight shaping the whole project: a robot that only harvests isn’t worth the investment. Growers need machines capable of handling multiple tasks across the calendar year — pruning in winter, pollinating and thinning in spring, harvesting in fall — to actually justify the cost.

Project scope: AI-powered robots designed to handle multiple orchard tasks year-round

The technical ambition here is real. Robots will be trained using AI and neural networks to read fruit tree canopies, identify individual fruitlets, and make autonomous calls about which ones to thin early in the season — so the fruit that stays on the tree can grow to marketable size, according to the Cornell Chronicle.

“Where it is safe to go, where the fruits are located, how fruits are located in relation to a branch, a trellis, a wire, leaves, other fruits — all those things are being perceived and understood by robots using an AI model running behind the scenes,” Karkee said.

The team will also build digital twins of real orchards to support horticultural analysis and robot training. Getting a robot to navigate a working orchard safely and autonomously is its own engineering challenge — one that requires mapping physical spaces precisely enough that machines can operate without someone watching over them constantly.

Fresh Fruit Robotics, an Israeli company whose founder Avi Kahani spent years managing an orchard at a kibbutz in northern Israel, is the industry partner. Kahani has been working on orchard automation for over a decade and brings a practical filter to the collaboration. “Turning innovation into reality is still one of the major challenges for an industrial company like us,” he said. Cornell Cooperative Extension fruit specialist Mario Miranda Sazo will lead outreach directly to New York apple growers, whose feedback will help ensure the technology fits how orchards actually work — not just how researchers think they work.

Apple farming’s economic scale underscores the urgency of a technological solution

Apples aren’t a niche crop. They’re the most-consumed fruit in the United States, contributing $21 billion annually to the national economy. New York ranks second in total apple production behind Washington State and first in the diversity of apple varieties grown — which makes it a natural testing ground for new orchard technology.

Karkee has spent more than two decades developing soft robotic hands that can handle fruit without bruising it and training agricultural robots to move through complex environments on their own. Recent advances in machine learning have sharply accelerated that work. Neural network-based models have transformed what’s possible in image processing, letting robots distinguish leaves from stems from fruit and make real-time decisions out in the field.

The project team is broader than you’d expect from an engineering grant. Sociologists and economists are also involved, tasked with understanding the cultural and financial factors that shape whether farmers actually adopt new technology. A robot that works in a lab but doesn’t fit a grower’s budget or workflow won’t change anything on the ground.

The short version: Cornell is leading a nine-organization, four-year effort funded at $7.5 million to build autonomous robots for apple and cherry orchards. The work covers pollination, thinning, harvesting, and weeding. It’s driven by rising labor costs, worker safety concerns, and the fact that specialty fruit farming is one of the last major agricultural sectors without viable machine automation. Engineers, AI researchers, horticulturalists, social scientists, and working growers are all part of the team — because the goal isn’t just technology that works. It’s technology growers will actually use.

Kelly Lippke

Kelly is an experienced writer with 15 years of experience exploring the big stories that shape our world, from tech breakthroughs and space exploration to climate, energy, and the fascinating quirks of science. She has a talent for turning complex ideas into sharp, memorable insights that stay with readers long after they’ve finished reading.