Orchard vision system turns farm equipment into AI-powered data collectors

Agricultural robots are not a new phenomenon. We’ve seen systems for picking apples and berries, weeding, planting trees, transporting produce, and more. While these capabilities are considered core capabilities of automation systems, this holds true across technology areas as well: it’s all about the data. One of the value props for these products is the amount of actionable information collected by their onboard sensors.

In a sense, Orchard Robotics’ system is eliminating the middleman. That’s not to say there isn’t still a lot of potential value in automating these tasks amid labor shortages, but the young startup’s system is bringing down the challenge with sensing modules connected to exciting hardware like tractors and other farm vehicles. Barriers to entry.

While many farmers are open to technology that might boost yields and fill positions where it’s hard to retain employees, the cost of fully autonomous robotic systems may be too high to warrant a first step.

As the name suggests, Orchard’s focus is on the apple crop. The system’s camera can take up to 100 images per second, recording information about every tree it passes. Orchard OS software then uses artificial intelligence to build maps from the collected data. This includes every bud/fruit found on each tree, their distribution, and even the hue of the apples.

“Our cameras image trees from sprout to bloom to harvest and use advanced computer vision and machine learning models we developed to collect precise data on hundreds of millions of fruits,” said Charlie, Founder and CEO Wu said. “This is a huge improvement compared to traditional methods, which relied on manually collecting samples of around 100 fruit species.”

With in-vehicle GPS mapping, farmers can get a more complete picture of crop success, down to tree location and size within a few inches. The company was founded in 2022 at Cornell University. Although only young, it has already begun testing the technology with farmers. Last season’s field tests were apparently successful enough to spark real investor interest.

This week, the Seattle-based company announced the completion of a $3.2 million seed round led by General Catalyst. Humba Ventures, Soma Capital, Correlation Ventures, VU Venture Partners and Genius Ventures also participated in the funding, as well as a previously unannounced $600,000 pre-seed round.

The funds will be used to increase headcount, research and development and accelerate Orchard’s launch.