What is automation good for? Harvesting more broccoli than human workers can, according to Upwardsa Shropshire, UK-based agTech startup that uses computer vision AI plus farm-sized proprietary machines to boost crop yields.
The idea is not only that the specialized, AI-controlled harvester will make it more efficient to pick a familiar crop, but also that the process will reduce waste – by being able to extract more nutritious protein from a field of broccoli without an army of extra human workers to do it.
Upp says the smart machines it’s developing will allow broccoli growers to harvest more from the plant than they could possibly do with human field workers, because the AI-plus-tractor-tool combo will do it all: fully automate the spotting, cutting, lifting and carrying, with a speed of up to 3 km/h.
This AI-driven approach allows farmers to “upcycle” the 80% of the broccoli plant (i.e., extra stem and leaves) that would normally be left in the field as waste, according to Upp, and sell that as an additional product that can be processed into a form it suggests is similar to pea protein.
The startup’s concept system, which CEO and co-founder David Whitewood tells businesskinda.com was developed with help from Lincoln University technologists, includes a tractor equipped with a 3D camera and an on-board computer with a computer vision system. AI model trained to identify when broccoli heads are the right size for picking (with greater than human accuracy, it is claimed), along with a proprietary (patent pending) tractor-pulled cutting and harvesting tool.
“The job of harvesting broccoli is — first — to recognize which heads are ready to be harvested. So we teamed up with the University of Lincoln agriproducts team, who developed machine learning and AI,” he explains. “We tested a whole range of cameras with it and tackled the difficult problem of occlusion [where leaves may partly obscure the camera’s view of the broccoli head].
“They used a depth camera with the 3D piece in it to determine the size of that head. Because we don’t cut every head — we just cut those to the right size as requested by the supermarkets… That says ‘cut’ and that sends a signal to our on-board computer and then we activate our patented mechanism that grabs the plant — what would be like a human grabbing the stem of the plant – and then a very sharp blade flies in and cuts it in a fraction of a second. And then the plant is removed.”
The extra edible plant material harvested in this way is not intended for the shelves of supermarkets – where the strict cosmetics standards that supermarkets typically apply to their suppliers are a major contributor to food waste by refusing to stock less-than-perfect-looking fruits and vegetables. store – but the idea is that it is processed into a protein and nutrient-rich ingredient for sale to the food industry.
Upp envisions the dried broccoli protein being used in a range of products – from sports-style protein drinks to convenience foods and baked goods.
The broccoli pieces it targets for upcycling are 30% protein by dry weight, according to the startup’s website, and are also packed with nutrients (vitamins A, B, C, E, K, calcium, iron, potassium , phosphorus, zinc) – but also rich in fiber.
Upp seems to have had no trouble getting early interest from the food industry in the upcycled edible plant protein – with Whitewood noting that it has already inked a trio of industry partnerships (he can’t name names yet, but says one is worldwide) . “functional drinks” giant; another is a major British food brand; and the third is a specialized pastry shop).
“They are very interested in the health aspects of broccoli,” he continues. “They’re interested in it being clean and sustainable… So they’re excited, shall we say. I don’t think we have a problem with it if there’s a market for it – once we get it off the pitch.”
On the processing piece, Upp works together with experts at the James Hutton Institute in Dundee to find out how to “best recover the fractions of that plant that make it primarily suitable for the food industry,” said Whitewood.
Upp is zooming out and developing what it bills as a specialist “circular plant protein” company against a backdrop of growing demand for alternative, plant-based proteins as the food industry looks for ways to reduce its reliance on animal protein to reduce its carbon footprint — with global pressure on farmers and food companies to meet climate goals.
That’s why the startup predicts that its AI-harvested broccoli protein could grow into a billion-dollar market in the coming years.
On the marketing side, it claims an added environmental benefit – suggesting that broccoli protein is cleaner than pea protein (because it’s 4x less carbon intensive to produce), while also claiming it avoids the deforestation problem that has tarnished the reputation of soybean crops . So the pitch is this is one even greener vegetable protein.
A possible PR wrinkle is that a number of (human) employees will inevitably be displaced as a result of automating broccoli harvesting.
Whitewood says the system replaces about seven field workers, but he notes that “warm bodies” are still needed at the packing house to package broccoli products for retail. “Seven people who are hard to get,” he adds, painting a picture of the grueling work field workers usually have to do and arguing that these aren’t the kind of jobs anyone is going to miss. “No one wants to do this job. Even in China and India they struggle to get people to do this… It’s the 21st century and we still expect people to do this. It’s just crazy.”
While the technology of the 2022-founded startup has progressed to the concept stage, it is gearing up for the next phase – sharpening a robust technology that can be commercially deployed – with a series of “field-to-protein” pilots which are scheduled this year in the UK, Spain and California.
It expects to start commercial production (and generate its first revenue) by the end of 2024 – expected revenues will exceed £50 million in 2027 in its three pilot markets.
The company was founded last year as a spin-out of another British company called agTech Earth robber – where Whitewood had been CEO before moving to Upp as a co-founder when they decided to part ways into two different companies.
Today, the startup is announcing a £500,000 pre-seed investment Elbow Beach Capitalan investor in decarbonisation, sustainability and social impact, to fund the field trials — ahead of planned commercial deployment later next year.
Whitewood says the first commercial use of the technology will likely be in Spain or the UK, due to seasonality, before Upp proceeds to pitch California’s broccoli growers about automated crop yield optimization.
Why hasn’t anyone thought of getting more of the good stuff out of broccoli plants before? Whitewood says people have been thinking about the possibility of doing this for more than a decade, but he suggests it’s just “really difficult” – given the selective harvesting required, as well as the need to separate the harvested crop, with a part (the broccoli crown) go to supermarkets (to be sold fresh) and the rest require additional processing.
“It sounds simple – a lot of people have tried and a lot of people have failed,” he suggests. “Only since you have a specialized harvester that can handle all the bulk, you can suddenly start processing the rest. You need automation – and it needs major automation. Little robots can’t handle crops of this scale, this mass… You need farm-sized machines.”
Janice has been with businesskinda for 5 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider businesskinda team, Janice seeks to understand an audience before creating memorable, persuasive copy.