During the inaugural Future Farming Technology event, held in Birmingham’s NEC late last year, a key message was clear: agriculture in its current state is unfeasible. Practices that have barely changed in decades are typically resulting in stagnate yields across the globe. Many feel the industry is over-reliant on chemicals and machinery that’s pressing the life out of once-rich soils. But new technology is helping the sector reverse this plateau.
“We’re part of a global trend in how farming is changing,” said Sam Watson-Jones, co-founder of UK agritech startup, Small Robot Company (SRC). “We think that arable farming in its contemporary form doesn’t work.” As a fourth-generation Shropshire farmer, Watson-Jones was talking from experience. He said yields have been static for more than a quarter of an era, despite the UK using over a million tons of herbicides and fungicides each year.
“The third agricultural reconstruction is what we’re living through today,” he added. “Chemicals define it — it’s surrounded by fertilizer; it’s defined by big, heavy tractors. But it’s no long-drawn working for farmers, and we need something new to carry us into the future. “The fourth agricultural revolution, by contrast, can be determined by swarms of small, smart machines and minimum, or no, cultivation at all.”
Large tractors, sprayers, and harvesters deployed on farms globally are compacting soils and exhausting nutrients. This is a challenge. Downsizing the machinery not only preserves the soil, but it also allows workers to farm on a much more granular scale. This mean individual plants and crops can be attended to for better care. The process is called precision farming. However, smaller machinery and “precision farming” typically means more time is involved in the process.
“We’re moving away from considering our fields, to gathering data and taking action on the particular plant — every single plant in your field,” stated Watson-Jones.
It’s a method that’s been championed for over a decade by Professor Simon Blackmore of Harper Adams University in Shropshire, and one that sparked Watson-Jones and co-founder Ben Scott-Robinson to launch Small Robot Company (SRC) in 2017. Their robots Tom, Dick, and Harry individually look after field monitoring, weeding, cultivation, and planting.
Of the three, “Tom” is at the most advanced stage of development, due to enter commercial service this year. Its latest iteration was launched at Future Farming Technology, claiming a double camera system that increases the monitoring capability to four meters squared. According to SRC, Tom can cover approximately 20 hectares per day, feeding individual plant data back to an artificial intelligence system — identified as Wilma, which helps farmers evaluate the information.
“The robots are automating tasks, but “Wilma” is the brains behind the operation,” said Watson-Jones. “She’s the bit that is going to cause the shift to a new form of farming.”
Along with Tom, SRC also unveiled a commercial service for weed mapping, a world-first according to the business. Heat maps of broadleaved weeds let farmers use sprinklers more effectively and better shape future planting decisions. Eventually, “Dick” will also serve and weed autonomously, micro-spraying based on data and analysis from Tom and Wilma. Harry, the farming robot, is still at the prototype stage. All three will work under a service package where the company will charge by the hectare to distribute plots of land. This means farmers won’t be required to make important up-front investments.
SRC is also operating with a Warwickshire-based firm, called Rootwave, which uses an electrically energized metal arm to boil weeds from the inside, killing them from the root up. It’s all part of a master plan to transition from the mass use of chemicals to much more targeted use — and, perhaps, one day using zero chemicals at all.
“Reducing inputs is important,” said Jamie Butler, a dairy and arable farmer who has taken part in experiments with SRC. “Obviously, for farming economics, but it is also definitely the way forward for the environment, for soil health and management. I would say that 90 percent of the chemicals and fertilizers that we are embedding on (our fields) probably aren’t necessary and could be significantly decreased with the right technology.”
Butler agreed with Watson-Jones’s sentiments on farming’s more extensive problems. Despite remaining an early adopter of technology, he has had to diversify the Hampshire farm he operates with his brother. The duo offers glamping, self-storing houses, and corporate fly-fishing to supplement the regular income from crops and livestock.
“In some regards, I think the outputs on farms are — maybe not as high as they can go, they could go longer — but I’m not convinced that farmers would see the profit in that,” he said. “We’d just be furnishing an oversupplied market. Why do we need to produce more? What we require to do is produce more efficiently.”
UK markets may currently be oversupplied, with large retailers squeezing farmers’ margins to the limit. But tomorrow’s food preservation is more fragile. It’s estimated that the world population will hit 10 billion by 2050 to about 2.5 billion more than today. If chemical-heavy farming and monster machinery continue, soils could eventually be pushed past the point of no return. Consolidated with the added threat that climate change poses to land management, the status quo has to shift.
“I think precision farming is going to be an independent revolution, with autonomous vehicles and also with weed testimony,” said Butler.“At the moment, we’re not beyond, but if those like Small Robot Company realize their vision, we will be there.”
SRC is by no means the only agency in the UK to research autonomous robots as a solution to agricultural issues. Harper Adams University has been running a research project on autonomous agriculture, using small, retrofitted engines and harvesters alongside drones and AI.
Known as the Hands-Free Hectare, the project affected its first crop of spring cereal in September 2017, with six tons of winter wheat following a year later. The project was continued for another three years, scaling from one ideal hectare to 35 hectares across five different areas. The project has since been re-labeled as the Hands-Free Farm.
“They’re fields that have not had any modifications from standard agriculture,” Jonathan Gill, a mechatronics engineer at Harper Adams and one of the project leaders, told a popular UK publication.
“We’ve got five fields, all of which have received non-straight headlands. The most challenging has got telegraph posts, it’s got a public right of way through the center of it, it’s undulant, it’s got four different soil types.”
Whereas SRC has purpose-built robots from the start, the Harper Adams team has taken a different approach, customizing current, compact machinery with technology that empowers it to farm autonomously. For the Hands-Free Farm, a second Iseki tractor has been added to the fleet, alongside a Claas combine with a much smaller footprint than their previous harvester. The team’s partner, Precision Decisions, is managing control systems and route planning, with FarmScanAG working on autonomous capabilities.
“What we’re looking at is the smart implement level, the implements and the machinery that goes on to the vehicle,” said Gill. “The new technology of grow systems, the new technology of bailing, and everything in between.”
For the original hectare, the team figured out the technology for planting, tending, and harvesting without any human behavior in the field. The Hands-Free Farm will take a more practical passageway, agronomists and students working in hand with the autonomous machinery, taking soil samples manually and making some judgments the old-fashioned way.
“I’d never really want to hold a farmer or agronomist going on the land and making decisions, so we’re not moving to do that,” said Gill. “What we’d like to do is provide additional tools to assist them to do it.
“It’s gotten a lot more sensible, it’s got a lot more professionalism behind the entire project to try and operate something on a routine basis instead of it just being like a feasibility study. This is not about the feasibility anymore, it’s more about proving the capability of autonomous farming.”
Part of that proof will involve drawing up a realistic vision of economics and determining where autonomy can potentially generate savings. Data from all vehicles concerning run times, distance, and fuel consumption will be collated and crunched. For crop data, new partner Pix4dFields has come on board to provide a drone system that will capture regular updates from above the fields.
Gill, a drone specialist himself, believes UAVs will play a crucial role in the coming agricultural revolution, and not just for monitoring. He points to the example of XAG, a Chinese manufacturer of precision spraying drones that have been deployed across two million hectares in China this year. It’s a technique that’s not currently permitted in the UK by the Chemicals Regulation Division (CRD), something that Gill thinks must change.
“A drone can fly at a lower height than a boom can operate at and deliver a chemical at a higher precision than most standard sprayers,” he explained. “A spray drone doesn’t have the same precision as a single nozzle-controlled sprayer, but it’s that middle ground in between, and the price of the technology is so much cheaper and it doesn’t cause any compaction.”
Drone spraying also frees up the possibility of cultivation when the ground is saturated, and farmers can’t get a conventional sprayer into the field.
“There are perfect abilities for these drones to operate and work within those environments,” stated Gill, “but we’re being hindered by our regulation system stopping us from actually operating these vehicles.”
Drones are ideal for controlling broad acre crops like wheat and corn, but keeping track of different fruits and vegetables requires technology in the trenches. Mamut, produced by engineers at Cambridge Consultants, is a compact four-wheeled robot that travels into fields collecting and analyzing data. By using stereo cameras, LIDAR, an inertial measurement unit, a gyrocompass, wheel odometers, and onboard AI, it can navigate new environments autonomously, offering a real-time picture of crop-health at ground level.
“Fruits and vegetables — in special citrus fruits — you can’t see what’s happening from earlier because the canopy covers it,” explained Niall Mottram, head of Agritech at Cambridge Consultants. “And there are not enough hours in the day for people to walk up and down the rows of an orchard or a vineyard to count grapes or apples.”
Center to Mamut’s effectiveness is its ability to operate independently of GPS or radio support, as well as its machine vision and AI that analyses crop data without the need for outside computation.
“That kind of AI on end, where you don’t need to use lots of Cloud compute platform power since that’s not practical in an agriculture environment, you do not have the real-time connectivity. This kind of approach is key if you’re working to see that AI jump out of the data center and into the field to deliver some interest,” said Mottram.
Filed Under: Blog entry, Tech Articles