Repetitive, physically demanding, and, in many cases, exhausting — it’s unsurprising that crop picking is unattractive to many workers in North America. Imported seasonal labor has long been the solution to the shortage, but with labor costs skyrocketing, many growers are now looking to automation and robotics for an answer.
For Walt Duflock, senior vice president for innovation at Irvine, CA-headquartered Western Growers, a large industry association, the driving force behind this phenomenon can be easily identified by looking at the United States’ H-2A program first established in 1986 for seasonal agricultural workers. In 2005, there were 48,000 workers documented using the program. By 2022, that number had increased to more than 371,000.
“It’s a massive lift,” says Duflock. “But the crazy part people forget is if you bring in immigrant labor, you’ve got two big expenses that occur all of a sudden — you’ve got to house these folks in complexes costing millions of dollars, and then you have to transport them from the H-2A housing location to and from the work site.”
Representing more than 2,400 grower members who account for over half of all conventional and organic production of specialty crops (fruits, nuts and vegetables) in the U.S., Western Growers’ innovation arm works with robotics start-ups, helping them understand the problems and needs of growers.
“My team’s job is to sit between the grower and the start-up and help them scale without Western Growers making an investment,” explains Duflock. “It’s expensive to make ag-robots, so we’ve built some standard components and open-source tools to allow startups to build robots faster.”
To enable this process, Western Growers supplies image libraries to developers of specific crops, allowing them to save initial research time and costs, as well as a “Startup Toolkit.” The association has also produced two editions of its Specialty Crop Automation Report, which Duflock says focuses on robotics start-ups that are “really hitting the mark” to help give venture capital firms the context and confidence to make investments.
But for Duflock the reason behind the growing interest in robotic solutions is simple: labor. “It’s always getting more expensive, it’s always getting harder to find,” he explains.
And the problem is not just limited to North America — there is a similar situation becoming apparent in Europe. “Both are having to pull further south to get ag-workers to come to the country,” Duflock says.
He notes this combination of the two factors — the decrease in the availability of domestic workers and the increasing cost of immigrant labor — is forcing farmers to look at alternatives, with the top of the list being automation. “Labor is getting worse and automation is getting better at about the same time,” he says.
Progress Being Achieved
So, how advanced are the technologies currently? Duflock says great progress has been made on solutions for weeding and thinning, as well as some progress in planting and so-called harvest assist solutions (robots that support crews in moving pallets or crates to and from packinghouses).
But while robotics are now widely used to harvest products for further processing, such as bagged salads, Duflock admits the place where the least progress has been made is in harvesting fresh produce. “It’s so hard to pick strawberries or apples with a robot when it cannot be damaged — it’s a high bar for fresh harvest,” he says.
“There’s going to be hundreds of weeding robots out there in the next couple of years doing hundreds of thousands of acres and something similar with planting over the next five to ten years. The last mile is harvesting fresh product via automation, and it’s hard to put a timeframe on that. We’re able to produce machines that harvest strawberries but not with economics that work for the grower. Not yet.”
One of the start-ups working to complete that last mile is Davis, CA-based Advanced Farm, which was established in 2018 with the aim of using robotics to build a better future for farming, according to the company’s director of business development, Peter Ferguson.
“Labor is tight and expensive, and we identified agriculture as being a really good place to bring robotics and automation,” he says. “Traditionally, robotics has been used in factories for very specific tasks, and as technology has improved, the ability to use robotics in environments like farming has become more realistic.”
To date, Advanced Farm has built robotic harvesters for strawberries and apples, as well as automation equipment for packing. “These have all been built on the premise of helping farmers reduce their labor burden,” notes Ferguson.
At the same time, he admits that some tasks remain challenging for robotic harvesters to perform, namely handling delicate fruits and being able to judge the optimum moment of ripeness and color. “These are difficult tasks for robots,” says Ferguson. “Certainly our robots are still under development, but we’re getting closer to a point where we can fully commercialize the technology.”
The reason Ferguson says Advanced Farm decided to focus on strawberries and apples is that they are “two of the biggest produce categories.” Apples, in particular, are conducive to automation thanks to innovations in growing practices such as trellises, which open up the tree canopy and make the fruit more accessible.
“Our goal is to get to the point where cost is cheaper than traditional human crews. That really comes down to being able to pick fruit fast enough and at a high enough quality that it can justify the cost of the machine,” he adds.
To date, the company’s robots have picked over 5 million strawberries and over 200,000 apples.
Turning Concepts Into a Reality
Across the Atlantic, U.K.-based Cambridge Consultants is another company close to the origin of agricultural robotics development. “Start-ups come to us, and we turn their ideas into reality,” says Chris Roberts, the engineering design company’s head of industrial robotics. “Everything we work on has a commercial goal. We help our clients get out into the field.”
To this end, Cambridge Consultants has worked on solutions such as grippers that pick fruit without damaging it and vision systems that can detect where fruit is located and whether it is ripe or not. “For a long time robotics and automation were about dull, repetitive motions, but that doesn’t work in agri-tech,” explains Roberts. “There’s so much natural variation — you have different lighting conditions in the field, so therefore you need to make your robots much smarter and much more sensitive, and that typically takes the form of some combination of vision and touch, and then some form of AI to extract the data from those sensors.”
At the same time, Roberts says a key objective for companies such as Cambridge Consultants is understanding what tasks people don’t want to do on farms and identifying those that can be automated.
“Around the world, there’s more and more pressure on labor and fewer and fewer people willing to work on farms,” he says. “However, the farm environment is complex and difficult, and you’re never going to be able to automate everything. Combining humans with automation is how we succeed, but we can’t just do a like-for-like replacement.”
One example Roberts cites is a Cambridge Consultants project where a client asked the team to develop an apple picker. After studying the working environment, Roberts says it became apparent that the greatest need was in transporting the apples back to the packinghouse rather than the task of picking. “Rather than developing an apple-picking robot, we looked at how we could improve the situation for the workers,” he explains. “So instead of replacing people with robots, we’re making the same number of workers more productive.”
However, not all projects work in the field. Roberts recalls the example of a startup that developed a strawberry picker and asked Cambridge Consultants to test it in field conditions. “Although the company achieved what it set out to do, it was a long way from successful,” he says. “The project’s goal was to pick a certain percentage of strawberries that were clearly visible and easy to reach, but of course the farmer doesn’t care about that — the farmer cares about picking all the strawberries. This meant the machine was never going to be profitable for the client.”
Addressing the Challenges
Based at the epicenter of agricultural robotics start-up activity in the United States, a team at the University of California, Davis led by Professor Stavros Vougioukas, vice-chair of its Department of Biological and Agricultural Engineering is looking at ways of optimizing robotic harvesting designs. In collaboration with two other universities — Carnegie Mellon in Pittsburgh, PA and Montana State in Bozeman — UC Davis has been awarded a federal grant for the development of a multi-armed harvesting robot by the National Institute of Food and Agriculture, the research arm of USDA.
The aim, according to Vougioukas, is to overcome two obstacles that robotic harvesters are facing: one is the low visibility of the fruit; the other is the inadequate speed of the robots.
“Everyone is talking about machine vision and AI, and they are great technologies, but unless something is visible from a camera you can’t really identify if it’s a fruit and if it’s ripe,” he explains. “So one of the biggest problems is, depending on the crop, some of the fruits are not even visible to the robot.
“For instance, if you go to a strawberry field when the plants are smaller, a robot with one or two cameras can find the fruit, but come June, July, or August when the plants are much bigger and there is more foliage, then a lot of the fruit is hidden under the leaves.”
This means, Vougioukas says, that it is challenging for a robotic solution to achieve harvesting of 95% or 100% of a fruit crop, especially in the case of low-lying produce such as strawberries that can be obscured by leaves.
“If you look at apples, if you miss a few apples it’s not as much of a problem, but it’s more of a financial issue,” he continues. “If the robot can only pick 70%, either you leave the remaining 30% on the trees and you lose that money, or you will have to bring people in and that fruit may not be the easiest to reach.”
UC Davis’ project is addressing the challenge in two ways: one is through multiple cameras providing a range of views of the canopy. By combining these different viewpoints, the robot is able to see more fruit.
Another approach being taken by Carnegie Mellon is blowing streams of air in a targeted, coordinated fashion to agitate the canopy and increase the visibility of fruit obscured by leaves. The other big goal of the project is to increase the speed of harvesting.
“If you build a robot that costs half a million dollars and can pick one fruit per 1.5 seconds, that’s a problem because it’s just one machine replacing one person,” says Vougioukas. “You really want to build machines that are very fast, so a machine can replace 10 people, not just one.”
To achieve that, Vougioukas says additional arms are necessary, whether that be five or 10. Of course, he says, then you have the challenge of being able to control them to maintain an optimal load balance, while at the same time being able to move the machine faster and pick more quickly.
“How to achieve that is not a trivial problem,” Vougioukas says. “The complexity is high, and you need to be able to solve the mathematical problem in real time. So, in this project, we are building a physical prototype of a robot with multiple arms and developing software that can control those arms and achieve speeds that are pretty high.”
With another 12 months to run, Professor Vougioukas anticipates that the UC Davis team will be able to demonstrate that the prototype is capable of picking much faster than existing machines. “This is a prototype that will show proof of concept and can be then taken by a company and incorporated into an actual picking machine,” he says.
Future Potential
So, where does this leave us?
“Agricultural robots enable us to implement high precision farming, which means we can use them to do the right thing in the right place at the right time, in the right way and at the right amount,” says Vougioukas. Such robots can range from specialized harvesting robots designed for a single purpose to solutions capable of removing weeds, pruning, spraying and pollinating, among other tasks.
“Instead of having to carpet-bomb a field to get rid of weeds, some companies are now building robots that move over the crop, find the individual weeds and only spray over those weeds, reducing chemical usage by a factor of maybe 90%,” explains Vougioukas.
The second major advantage such technologies offer is helping with farm labor problems by either replacing people in some tasks or by making it faster and easier for people to harvest.
This, says Vougioukas, has the advantage of making operations more efficient and less labor-intensive. “Rather than looking at these robots as evil machines that will take jobs away, the reality is there are no agricultural robots now that will harvest 100% of the crop,” he notes.
Although some harvesting robots are already in operation for produce such as apples, strawberries and kiwifruit, people are still required in the fields to pick fruit missed by automated solutions, and in packinghouses.
“These machines help people become faster, safer and more efficient when they harvest rather than replace them,” says Vougioukas. “And the farm labor problem isn’t just in the United States — it’s in Asia, Europe, Australia — even Latin America has issues. Not because they don’t have enough young people, but because they don’t have enough people to go and work in those fields.”
A further advantage is that robots are able to deliver information about each and every plant in unprecedented detail, including examining how fast they are growing week-to-week and how many pieces of fruit are being produced by each plant. “This kind of data can really help us optimize the management of the crop and production, so the technology has even more potential going forward,” notes Vougioukas.
As the produce industry undergoes increasing levels of automation, the role of agricultural robots stands out as a beacon of hope amid the continual worsening of farmworker shortages. These aren’t just machines doing the heavy lifting; they’re at the heart of a farming revolution.