After a career in farming and engineering I decided I wanted to contribute my expertise to solving the biggest problems in the UK providing fresh, healthy food in a rapidly changing climate. In my opinion UK Government sponsorship of agricultural research has had very little impact on farming and quality food production that has diminished in my lifetime. The reasons for this failure would take an angry book to discuss. I prefer to be active by doing what I think is important on my own land and lead by practical example.
The key things I want to work on are:-
the loss of connection of the people from the ability to grow food
the overuse of agrochemicals
the changing climate particularly in rainfall patterns
the improvement of soil carbon levels
the production of vegetables and fruit throughout the year
reducing the drudgery in field work with robotic tools
In 2022 after a long search during those strange isolational years I managed to buy an unnamed field in Devon. I chose it for its South facing aspect, fertile Pebblebed soil and easy access from a busy main road. It is not far from Exeter and I suspect that in a few years it will effectively be a green island in the suburban sprawl favoured by the District Council.
My first actions were to give the field the name Robot Hayes to reflect my aims, plant shelter belts to reduce wind damage in the long term, install a polytunnel to extend the growing season and a lockup container for tools and seeds. I divided the best part of the land into 48 x 100 sq m allotments and began renting these out to local people. That brings a whole different aspect to the field which I suspect was basically a sheep run and hay field without a single human for 360 days a year.
After adding some solar panels I was able to install a small robot inside the polytunnel to manage the vegetables with image processing and controledl watering and weeding. In the second winter I began planting fruit trees and vines. Of course the first things that happened was a heatwave in 2023 and then a wet wet growing season in 2024. This convinced me more and more that the management of field crops in the UK needs to adapt.
The heavy rain that seems to becoming common is now capable of damaging growing plants and washing away topsoil. Although average temperatures are rising we also get sudden bursts of polar wind that can cause frost damage.
So we need to integrate more rows of sheltering bush perennial crops, shade and rainbreak covers, and ventilated polytunnels. This of course is in addition to planting, growing and weeding without resort to chemical warfare on the environment, while protecting crops from rabbits, deer and insects.
After two years of hard work it is time to start talking about Robot Hayes
Most British people now get a large proportion of their calories from processed and ultra-processed food and drinks stabilised chemically for a long shelf life and these foods are associated with rising nutritional disorders such as obesity and type 2 Diabetes. The cost and scarcity of labour close to our cities has caused retailers to source “fresh” food from distant areas such as Spain, Peru and so on. The changes to the ecosystems in areas such as Murcia in Spain are dramatic and unsustainable thus reducing food security. Growing our own vegetables and fruits close to the point of consumption has to be a key policy objective for the new government. We need to encourage more local production and the development of labour saving technology and this is what I have set out to do at Robot Hayes.
I have had a long career in agricultural engineering research co-inventing robotic milking, and developing sensors for monitoring dairy cow health and fertility. During the pandemic I sold my two start up businesses and used the money in 2022 to buy a small south facing field with good soil and road access so as to do my part in solving the food crisis which is destroying people’s health. The word Hayes is common in Devon signifying an enclosure or field so as I will develop and test robots here I gave it that name.
I now rent out 100 sq m allotments to local people to grow whatever they want. . The allotment system has been around in the UK for centuries but fell into the hands of local authorities who have been slow to respond to the huge demand for people to grow their own food. Allotment areas have long waiting lists even as some plots fall into disuse. A mature allotment area is often the most biodiverse area in the urban environment. There are hundreds of people on the waiting lists for allotments nearby. In the area East of the M5 at Exeter eight thousand (8000) new houses and flats are planned to join the 1000s already being built at Cranbrook with tiny gardens within a couple of miles of my field.
The enthusiasm of my dozen or so gardeners is overwhelming and a genuine community spirit is developing with many young families. I love the sound of children’s voices as they play in the gardens. Already we have buzzards and owls flying over as the vole and field mice populate the uncultivated fringes of woodland that I have planted and herons look for prey in the ponds. I daresay some existing locals will dislike the visual intrusion and prefer vast empty fields of commodity crops. More farmers should offer allotments, it doesn’t require planning permission and has a margin per hectare ten times that of cereals.
One of our newly established allotments
I retain a number of plots for myself so that I can develop systems to make organic vegetable production less labour intensive. No-one enjoys weeding vegetables, it is back breaking and continuous during the growing season. Our rental contracts are based on the typical local authority contract but with more flexibility and we have a few site rules such as no chemical pesticides or fertiliser so the emphasis is on innovating organic types of husbandry.
I bought and installed my first robot in a polytunnel in 2023. It is an open source design from farmBot in California using a Raspberry Pi computer running in the Python language and has many features that I have not had a chance to explore yet. I mostly use it for watering and hoeing and this winter I hope to demonstrate fresh vegetable production in our mild Devon climate. It needs to run in a polytunnel raised bed to protect its electroonics and aluminium drive rails from the weather. Because of its precision I think I will focus on raising seedlings of exotics (peppers and spices etc) in pots for planting out in the spring. With my hard won expertise I think we can start offering robotically managed polytunnels to hotels and restaurants and private houses locally to grow their own organic produce with minimal labour. I need to find a business partner who can focus on developing that business.
The first robot at Robot Hayes was bought from farmBot and installed in a polytunnel
Polytunnels have their place but we can grow a lot in open field situations and this is the focus of my engineering activity this year. I currently have a Defra funded Farm Innovation grant managed by InnovateUK to develop safer working practices for horticulture. I cannot say too much as some of the technology that I and my small team are developing will be patented. Our focus is to convert existing tractors to be more precise and safe. Modern SatNav systems can accurately position a hoe blade to within a centimetre of a target, which means that we can develop sowing and weeding systems that do not require manual labour. Cutting and porting vegetables is still very labour intensive, often on muddy winter fields so we need safety systems that will stop a machine if someone is in danger. Farm accidents with moving machinery are still common and we need new technology to reduce risks.
I am personally sad that Small Robot Company has gone into liquidation. Personally sad because I invested in it but also because it is probably the end of an academic dream that friends and colleagues believed in passionately. The dream failed to make it to market for a number of practical reasons.
Finance
Minimum Tillage
Weeding
Harvesting
Finance. Interviewed on BBC Radio 4 Farming Today the founder of Small Robot Company blamed the Agtech financing climate in the UK and I would agree from my experience starting eCow, Milkalyser and VirtualVet there are few investors or funds willing to take long term high risk investments in UK agtech. Investors mostly want companies with proven products and sales. Any company developing hardware that needs to be tested and developed over a number of seasons is going to struggle. Even if the product works and sells the cost of scaling is immense. Investors love software start ups because testing is usually quite quick and upgrades can be cheaply sent out over air. There is plenty of evidence that the Silicon Valley model of funding does not work well in farm machinery. These are not fast moving consumer goods bought as fashion items.
Minimum Tillage. For years the concept of reducing the soil compaction associated with heavy machinery has proposed that fleets of light weight robots could replace the heavy machines needed for field operations. The Tom robot mapped pests and then returned for spot spraying. The concept was that the major time cost for human labour could be replaced by a few machines taken out to the fields that would quietly work away. However, I think the real problem of compaction came from the previous fashion for deep tillage which requires huge motive power and thus heavy machines. Minimum or even no till requires a completely different approach with use of tramlines and accurate GPS. If spraying is to done then 24 m passes on tramlines and lighter machines that could be automated rather reduce the argument for the swarm of small robots.
Weeding As we move away from spraying weeds towards steered blades, electrocution and lasers we reintroduce the need for power on the implement. My abiding memory of the wonderful laser weeders working rocket beds is the sound of the diesel generators needed to power the servers and lasers. These will not be powered by small machines in the near future. Blade weeders need traction and good electrical supply too for the imaging computers.
Harvesting The biggest machines we always see are always harvesters after all we planted kilograms of seed and expect to harvest tonnes of crop. Cereals and forage crops get harvested when soils are dry in summer when compaction is lower risk but the high value vegetable crops with big labour demands have to be brought in over often soaking soils so again we need power.
In my view the future of field robotics is to develop systems that allow farmers the flexibility of use of tractors and implements with automation tools that for routine field operations do not require a driver. I am working on remote control systems that can be used from off the seat but stop safely if humans are in danger around the machine. Only the largest farms can justify machines that can do limited operations.
Twenty years of incredible development have failed to replace humans as drivers.
Twenty years ago DARPA who sponsor advanced research in the USA ran a competition to develop a vehicle to save lives of the US military. This was hoped to lead to autonomous vehicles. This excellent book takes us through the exciting developments of the past 20 years of sensors and systems but we still have no autonomous vehicles on public roads. Exciting, and initially tech driven, the competitions in the Mojave desert are particularly well described. The first failed to find a vehicle that could complete the course but two years later several vehicles managed the 150 miles of rugged terrain. The action then moves to the even more dynamic environment of urban driving and the businesses that were created and failed to deliver a safe system to replace the human skill of driving. There is so much in this book of interest to engineers, drivers, business people and investors still looking for the secret sauce that will bring sensory intelligence to robots. Things that humans do with ease are difficult for robots and vice versa. This is Moravecs paradox explored with billions of dollars of investment money from Google, Uber, Ford, GM et al. and still there are no autonomous vehicles regularly on the road.
For me, with a Defra funded innovation project to develop safe working systems to stop tractors killing humans and animals this is a key text. The book maps out the development process that failed to constrain the operational design domain and demonstrates the hubris of some inventors one of whom ended up in prison for IP theft. The desire for a complete system prevented the development of the aftermarket of conversions of existing vehicles that could evolve autonomy. Whilst deep learning techniques of showing many tagged pictures of cats to a computer can teach it to recognise a cat, this has proved insufficient to learn the complexities of navigating a road without accidents.
For me this is welcome. I am disappointed with the displays of robotic tractor systems and there are many now appearing, they seem to have to have a narrow focus and few farms are big enough for a single purpose machine.
I want to keep the flexibility of the existing tractor fleet and provide a conversion kit that allows them to be used in many tasks, anything from feeding animals on a frosty morning or carrying tools and posts while fencing. I have defined a few problems where humans work with tractors and spend a lot of time jumping on an off and driving short distances.
Devon has a very mild climate with summer heat and winter chill moderated by the sea but even here we see the climate changing. This June it was so hot that my clay soil dried out to dust after a wet winter, temperatures in the polytunnel went over 50C. As for rain we seem to get showers so heavy that they smash plants and wash out any exposed soil.
I would love a greenhouse as the technology has advanced hugely and makes a perfect platform for robotic management even down to picking and packing vegetables but the capital costs are huge (say £20k for 100 sq m) and running costs subject to uncontrollable fuel cost variations.
So I need more flexible methods of controlling the exposure of plants to the elements at a reasonable cost. At the Venice Biennale I saw a very interesting exhibit of Taiwanese farm buildings evolved to manage their high value fruit and vegetable crops in semi tropical latitudes but with mountains that have cold and snowy conditions. They also get typhoons with very high winds and extreme rainfall.
This summer I used a tarpaulin over the polytunnel to reduce the solar exposure but this is a temporary and difficult to manage option. A polytunnel can of course be adapted with different covers and ventilation but it is hard to change the covering as we bury the sides in soil to stop the wind blowing the covers away.
Figure 1: Model of a fruit farm growing under a frame with an extendable shade/rain filter cover
The Taiwanese style is to create a rigid frame maybe 2.4 m (8’) above ground with tensile wire between the rigid frames that can support crops like tomatoes and beans and also provide a guide and support for covers that can be winched into position as required. I am going to try and experiment with these next season to understand the practicalities. We don’t get typhoons in Devon but we get a lot of wind and periodic heavy rain. I think I will use a mesh of plastic to allow rain to percolate and shade to stop severe burning.
I am renting out 100 sq m allotments on a gentle south facing slope of Pebblebeds soil on the west edge of Aylesbeare, Devon. The field has been a sheep run and hayfield for many years and not treated with chemicals. I bought it last year as place to develop new techniques in robotic horticulture and I have created 48 plots that I rent out on allotment style leases, many are still available at £60 a year (incl VAT). I have planted shelter belts and dug water holding ponds around the perimeter which will provide a wild life zone and shelter belts in due course. My aim is to create a community food resource over the years. This winter I will plant more trees including some exotic fruits and nuts as our weather is changing to hotter and wetter conditions and we need to adapt. Contact me if you are interested. Instagram @robothayes linkedin.com/in/tobymottramdigitalagritech
Pebblebeds soil
south facing slope
Mains water
Main road access and parking off A3052
Close to Nine Oaks bus stop (9,9A)
One robot installed in polytunnel, another in development
Growing food was for thousands of years, and in much of the world still is, a set of backbreaking monotonous but skilled tasks. It was done by humans in all weathers from scorching to freezing from burning dry to continuously coal and soaked. It was largely staffed by unfree people serfs, slaves, peons, share croppers. Since people found that they could have a better life in the cities there has been a continuous migration which has driven agricultural technology for 250 years. The arrival of mobile power sources usually fossil fuelled allowed machines driven by a human to become huge and efficient in the use of labour. There was still a huge need for labour harvesting vegetables and picking fruit. The labour crisis is now so serious in UK that farms are ceasing production of some crops and even if migration restrictions are lifted the steady rise in living standards around the world means the traditional sources of labour are disappearing.
Two major advances are needed for robotic harvesting one is identifying the item you want to pick or cut and the other is to have a tool that can pick up the produce gently. Other parts of the system exist such as precision location which has been around for years and transporting and packing the fresh produce.
In this video you can see asparagus tips being picked, image processing detects the mature shoots and then a soft picker descends and holds the stem while a knife cuts it free.
Agrobot a Spanish strawberry harvester
And here you can see the types of new machines. The first observation is that this is great and complex technology and will take years to hone and improve as the test and development time is limited each season and so years may pass before all issues have been identified and fixed. Production runs are small and so the cost of producing and supporting these robots is going to be high for a while yet.
In a spirit of curiosity and in need of an adventure after the confinements of the last two years I took flight to California for a bit of October sunshine to visit FIRAUSA2022 to see the latest display of Californian Agricultural Robotics. Last year I managed to navigate Covid restrictions to visit FIRA2021 in Toulouse and my blog report of that meeting is here.
FIRA USA 2022 was held in Fresno a modern city of half a million at the Southern end of Central Valley region of California which is one of the great growing areas of the world where with irrigation water from the mountains pretty much anything can be grown. At the airport one is greeted with Welcome to Fresno, agricultural capital of the world.
The meeting was enjoyed by 1000 + delegates in a three day mix of R&D results, commercial interactions and most interestingly field demonstrations in salad crops and vineyards.
Figure 1: The design of full autonomous tractors completely reshapes the layout. They are basically a frame with wheels at each corner, a power source, sensors and a computer. This Naio machine has front mid and rear tool bars on hydraulic hitches.
Being California there was huge enthusiasm to invest in the new wave of technology based on autonomous robotics, image processing and precision navigation. I think the investment crowd may have been a little disappointed as various company founders expressed views that suggested company growth should be organic and that VC money was not always appropriate as rapid scaling of agritechnology and early exits were unlikely.
The main interest was in systems that address the key problem in horticulture and viticulture of labour shortage. Even Mexican growers present were complaining that there is a labour shortage there. So weeding by hoes, spot spraying or lasers were the most viewed systems along with sub systems suppliers for navigation, wifi charging or image processing etc,
Most of the blade weeders were relatively simple, agitating a blade to swipe a weed identified by image processing as not the crop. One company FarmWise had build a full autonomous vehicle to weed which begs the question why not just mount it on a tractor and apply navigation and autoturn controls such as those offered by several manufacturers now.
Figure 2: interplant and interrow weeding just has to identify a plant as not the crop to then chop its roots with a blade. The red circles are weeds left to dry out in the sunshine of California
More exciting was the laser weeder that could operate in beds of very small seedlings as it could burn out out weeds with pinpoint accuracy.
There were a lot of interesting panel discussions and science presentations and one I caught said that blade weeders were over 90% effective weeding between lettuce plants in rows although timing is critical. In Arugula (Rocket in UK) where plants are grown in beds timing is even more critical and there a laser weeder came out very well. You can see it working in the video . I walked down the bed after the machine finished and saw only two weeds in 100 metres. Both were emerging contiguous to the Rocket seedling which would need a finger weeding if a human was doing it.
There was a lot of attention on viticulture robots mostly for spraying which is obviously a major operation. See the video for a view of some of them. My favourite machine is the Swarmfarm system which was not able to make the journey from Australia where a number of them are busy. They are basically a metal frame, a diesel power source, navigation and autosteer. The video demonstration is well worth watching. I spoke to Andrew Bates the founder and he said he has a couple coming to UK soon.
There was considerable discussion about whether legislation will hamper the deployment of autonomous robots on farms. No-one wants a farm worker or child hurt by a robot although scaring off ramblers and crop circlers might be acceptable.
The Californian equivalent of HSE have recently judged that fully autonomous tractors must be supervised by a human and this has dealt a major blow to progress on autonomy.
This maybe a hurdle we need to jump in the UK fairly soon as autonomous tractors are working at a number of farms in test conditions.
We need to shorter supply chains and local production
To kickstart the shift to my next agritech development and to do some research for my next book I took myself on an Unsettled retreat package to Podere San Georgio in the Tuscan hills near Pisa.
The Podere (or small farm) is an ancient former convent long ago converted into basic hotel accommodation and focused on providing high quality fresh cooked food from the locality. The local producers are all selected for using organic and biodynamic methods of production. Nothing comes out of packets from a food service facility, the wines and beer come from local producers too small to be available outside the area. The Podere has 500 olive trees of its own and lies on the via del vino so vineyards are all around. The sandy soil is an upraised seabed and fossilised sea shells are found in some layers. This soil provides the minerals for the tasty local wines and is ideal for olive tree production.
Local wineries in Tuscany are mostly too small to sell wine wholesale, this is one of the larger ones near San Gimigagno
The landscape is very hilly and wildly forested, the steep slopes and cliffs being too difficult for monocultural forestry so the air is clean. Birdsong is audible most of the day. Unsettled had brought together a diverse group of fourteen single visitors mostly mid-career professionals from around the world with about half being from the USA and Canada, I was the only European in the EMEA half of the group. This lent itself to great cultural interactions with nightly get togethers for dining and dancing under the moon.
Unsettled laid on visits to wineries, cheesemakers and a highlight for me being a truffle farm where we saw dogs hunt out truffles that we later cooked with homemade pasta.
In the evenings beside tasting the local wines and eating the excellent ad hoc meals provided, we had hands on demonstrations of pasta and pizza making. The chef Alessio specialises in using offcuts and seasonal vegetables and this being autumn there was plenty of variety.
Clearly the fertile soil of Tuscany and the local food traditions lend themselves to a high degree of self sufficiency which has to become a regional objective as we move away from the energy demands of long distance supply chains. I believe that this philosophy will allow us to stop relying on long shelf life processed food which has affected human health with outcomes such as obesity, auto-immune disorders and food fads. Any future farm I get into will include retail sales and maybe a cooked food service to add value to the offering.
The FIRA industry conference and show series is focused on autonomous field machines which have become of huge interest given labour shortages particularly in high value vegetable and fruit crops. This year’s show was held at the Diagora conference centre near Toulouse, France between 7-9 th December 2021 in a mix of face to face meetings and online presentations from across the world. The hybrid format worked well as live streaming is now fairly robust and there was excellent studio management so that even questioners appeared on screen live. In fact I found the video presentations easier to follow back in my hotel room chromecast to a wide screen TV rather than in the conference rooms where visual quality was sometimes poor and distant text was sometimes unreadable.
I had been hoping
for genuine live demonstrations but every company resorted to video
which of course is immune from real world problems. The robots move
up and down rows on video across flat fields.
The biggest company in terms of sales appears to be Naio whilst the longest development cycle seems to be AgroIntelli’s Robotti which grew out of a Kongskilde project and is now in early sales mode. There was a great demonstration of robust simplicity from Swarmfarm in Australia with 20+ machines in the field. The full list of exhibitors is available on the website.
A fully loaded Robotti from Denmark with diesel power packs
The basic format of
autonomous field robots is of a steel frame with an independently
driven and steered wheel at each corner. A mast on the frame gives
elevation to cameras and antennas, Sensors are mounted around the
frame for collision detection and data recording. Most machines have
one or more tool bars and a 3 point linkage to mount third party
implements such as hoes, seeders and even harvesting units.
An early stripped down prototype shows the essentials , frame, wheels, toolbar, GPS tower
Buses for power
(electric and hydraulic) and data distribution are a key element
attached to the frames. Machines are sized to standard widths for
viticulture or horticultural implements. It was claimed that machine
weights were 10% of conventional tractor and implement outfits. The
system concept is ideal for no till or minimal till rotations. They
do not have the power and weight for traditional ploughing and
cultivating and they do not cause soil compaction either except in
the tramlines. Given the need to reduce energy use and to sequester
carbon in soils the autonomous systems offer huge advantages as well
reducing the labour cost.
Most machines used either an off the shelf diesel engine powering hydraulic drive or a hybrid system using a small diesel engine to charge batteries and using electric drives. There was an interesting discussion about electric versus diesel versus hydrogen or fuel cell, The pragmatic solution is to use a modular approach that can be adapted as new power source technologies appear. A radical departure was the demonstration of a wireless charging station for batteries by Wiferion. The robot can drive to a shared station and wirelessly charge up with 93% of the power available from the associated power supply (mains, wind or solar + battery). This removes the need to fill up with diesel or plug in a power supply.
Most of the bigger machines had three point linkages so that third party implements can be fitted, this is the back end of a Sitia viticulture machine
One limitation of
the robots is that they cannot move from field to field on public
roads under robot control due to the same legislation that controls
autonomous cars and trucks. This is not a major issue for large
farms within a ring fence with internal paths but something to be
addressed to enable machine flexibility and sharing.
The most popular and simple application is spot spraying or weeding with bolt on modules that use image capture of weed species and deploy the chemical or mechanical knockout system according to the image and location of target. The difficulties and potential for developing better and faster systems of image capture was well described by Robovision who are specialists in capturing human expertise in visual tasks into software.
A little further from commercialization were robot harvesters and video was shown of systems picking strawberries, asparagus, and cauliflowers in open field conditions. These machines were in only their first season of operation so this is a space to watch for developments. Mishandling of the crop was held as the potential risk for adoption as any damage reduces shelf life and quality and thus price. Two machines in the USA (Harvest Croo and Advanced Farm) were picking the very delicate crop of strawberries and there a major part of the problem is post picking handling and transport. The Harvest Croo machine used image processing, multiple robot grapples and a liquid transport system to move and pack the fruit.
It was stated
several times that mechanised field harvesting can improve product
quality by removing human contamination of the crop (no exposure to
salmonella or covid from pickers) and also by grading the fruit in
the field the costs and difficulty of human labour in the packing
house could be significantly reduced. Naturally the heavier loads of
harvesting need a transport system that does not cause soil
compaction to carry produce off the field.
Various pricing
mechanisms for the technology were mentioned from outright purchase,
leasing and payment by materials harvested (which could then compete
directly with the human cost of harvesting). Some of the systems
developed have been by a partnership between producers identifying
the problem and the start up tech developers. As there is virtually
no long term operating experience repair cycles and fault detection
were barely discussed except as a legal risk. Only one farmer
mentioned the lack of any checking for the real things that happen
such as bearing failures causing misaligned weeding disks etc.
A stripped down MuddyMachine prototype has been picking asparagus after only one year in development
Although high value crops have significant niche markets which are under severe stress due to low labour availability from migration restrictions and a loss of traditional recruitment patterns in the countryside, they do not amount to scales that will massively reduce cost of production. While tractors sell in hundreds of thousands of units per year the take up of specialist autonomous platforms is likely to be in hundreds per year for the next few years until issues such as cost of use, serviceability, dealership response times have been resolved. There will still be a need for the flexible farm tractor for many years to come.
