The rise of the Farm-bot - ploughing through the possibilities

Profile picture for user cmiddleton By Chris Middleton June 21, 2018
A new research report to co-incide with UK Robotics Week digs into the possibilities for robots in agriculture.

Robot farming
Agriculturally produced food is the largest manufacturing sector in the UK, supporting a food chain that generates £108 billion in revenues a year, with nearly four million employees and exports of £20 billion. The sector is of similar local importance to other economies.

But there is a problem: globally, the food chain is under pressure from a range of complex factors, including population growth, climate change, political pressures affecting migration – in the UK, connected with Brexit and tightened immigration policies – a worldwide drift from rural to urban living as cities expand, and an ageing population.

In the UK alone, the numbers of citizens aged 65+ will increase from 12 to 17 million by 2035, while in the US, 65+ citizens will rise from 15 to 24% of the population by 2060.

Water (and water pollution) is part of the challenge as the climate changes: agriculture uses 70 % of global fresh water supplies, and yet four billion people live in regions where water is scarce. That problem can only grow.

Meanwhile, in the UK, the many different soil types create challenges of their own for any attempt to impose overall technology solutions to make farming more efficient and sustainable.

The knock-on effect of all this is that food security is a growing problem worldwide. And with the UK now politically adrift from many of its allies and arguing with itself about what its future place in the world looks like, those food chain challenges could become remarkably pressing for a developed nation with a long agricultural heritage.

Robotics and autonomous systems (RAS) could be a core part of the solution to these local and global challenges, according to a new white paper from UK-RAS, the umbrella organisation for UK robotics research, and part of the Engineering and Physical Sciences research Council (EPSRC).

The paper, The Future of Robotic Agriculture, has been published to coincide with UK Robotics Week 2018 (21-29 June).

It says that the opportunities for the smart application of robotics include:

  • the development of robots that can assist human workers in the field by carrying payloads and conducting specialist operations, such as weeding and drilling.
  • integration of autonomous technologies into existing farm equipment, such as tractors.
  • the introduction of robotic systems to harvest crops.
  • the use of collaborative applications to augment worker productivity.
  • advanced robotic applications, including the use of soft robotics, to drive productivity beyond the farm gate and into factories and shops.
  • increased levels of automation in land management.

Links between all of these technologies – on the ground, in the air, and at the computer screen – offer promising avenues for innovation.

Digging into the detail

Some of the specific applications of robotics could be transformative, says UK-RAS. For example, the use of synthetic pesticides has become increasingly controversial in recent years. Robotics could counter that trend, the researchers suggest:

There is a global need to find new ways to produce crops that do not require, or which reduce the use of pesticides. There are now a number of crop-weeding robots that reduce the need for herbicides by deploying camera-guided hoes, precision sprayers, or lasers to manage weeds. Although in its infancy, this technology shows great promise.

In addition, novel sensors deployed on robots can reduce pesticide use by both detecting pests and diseases, and precisely targeting the application of insecticides and fungicides.  Robots could also be deployed as part of integrated pest management systems, for example, for the accurate and low-cost dispersal of bio-pesticides to counteract crop pests and diseases.

Precision agriculture – aka smart farming – could be another key area, says the white paper:

One approach is to utilise more intelligent machines to reduce and target inputs in more effective ways. The advent of autonomous system architectures gives us the opportunity to develop a new range of flexible agricultural equipment – based on small, smart machines –that reduces waste, improves economic viability, reduces environmental impact, and increases food sustainability.

Meanwhile, drones and unmanned aerial platforms could be combined with localisation and mapping technologies, computer vision, multispectral sensors, and even AR & VR, to help farmers monitor their land, livestock, and crops in three dimensions, while also enabling mass phenotyping in the field under true farming conditions.

Robotic systems could also be developed for use in livestock management and aquaculture, says the paper, along with new technologies for vertical, indoor, or urban farming – non-traditional farms that grow crops indoors in sensor- and climate-controlled environments, moving food production closer to big population centres.

The Internet of Things (IoT) and the increasing availability of low-cost, low-power sensor technologies are central to this new farming revolution, explains UK-RAS:

Sensory data collected by robotic platforms in the field can further provide a wealth of information about soil, seeds, livestock, crops, costs, farm equipment, and the use of water and fertiliser.

Low-cost IoT technologies and advanced analytics are already beginning to help farmers analyse data on weather, temperature, moisture, prices, etc, and provide insights into how to optimise yield, improve planning, make smarter decisions about the level of resources needed, and determine when and where to distribute those resources in order to minimise waste and increase yields

.Future telecommunications availability is likely to enhance IoT capacity, with agri-tech test beds already under development.

At the other end of the food production process, agricultural robotics could also facilitate earlier labelling and tracking of food products throughout the supply chain, “bringing numerous benefits, such as improved information for consumers on where their food is from and faster action to mitigate food safety issues”, says the paper:

In turn, the food metadata could be fed back to the field operations to further improve primary production.

Of course, supply chain optimisation and automation tools, combined with technologies such as the IoT, RFID tags, analytics, and blockchain, are already transforming all types of manufacturing, distribution, and logistics. The paper continues:

In general, there may be many potential synergies between agricultural robotics and the downstream processing of agricultural products in the food chain, where whole supply chain efficiencies could be unlocked through future application of RAS technologies.

Great British challenges

The UK could forge a leading position in each of these areas, says UK-RAS. However, there are significant barriers to overcome locally before that can happen.

One is that the UK robotics community within agri-food production is small, dispersed, and lacks dedicated training facilities, says the white paper. Another is that, while there has been substantial government investment in robotics and AI generally in recent years – and a lot of supportive noises from Whitehall, together with new Sector Deals – there is insufficient ongoing research in agricultural robotics specifically to capitalise on the opportunity.

Meanwhile, the successful delivery of robotics and automation projects in agriculture demands much closer collaboration between the technology/research communities and industry practitioners.

Until that happens, one repercussion is that robotics for agri-food production will continue failing to reach its full potential in the UK, at a time when the country needs to explore new avenues if farms can no longer rely on low-cost seasonal labour.

The projects currently being commissioned “are too few and too small-scale”, says UK-RAS. Greater ambition is essential when multiple discrete technologies need to be developed and integrated in large-scale industrial applications.

But beyond the need for coordination, collaboration, investment, and what UK-RAS calls ‘moon-shot’ proofs of concept at scale, what does the ideal future look like?  The white paper says: 

Our vision is a new generation of smart, flexible, robust, compliant, interconnected robotic and autonomous systems working seamlessly alongside their human co-workers in farms and food factories. Teams of multi-modal, interoperable robotic systems will self-organise and coordinate their activities with the ‘human in the loop’.

Electric farm and factory robots with interchangeable tools, including low-tillage solutions, soft robotic grasping technologies, and sensors, will support the sustainable intensification of agriculture, drive manufacturing productivity, and underpin future food security.  

But to deliver this vision demands the development of robust robotic platforms, suited to agricultural environments, and improved capabilities for sensing and perception, planning and coordination, manipulation and grasping, learning and adaptation, explains the report.

Human-robot collaboration, and interoperability between robots and existing machinery, are both vital, mirroring the trend in manufacturing towards ‘cobots’ – smart, programmable, collaborative machines that can work safely alongside human beings.

But none of this will be an overnight revolution in an industry as old as agriculture, acknowledges UK-RAS, despite farmers understanding better than anyone the need to invest in new tools and systems to operate as sustainably and profitably as possible. The white paper says:

While full automation is often hailed as the ultimate aim in technological development, and future agriculture systems may look very different from those of today, only very few large companies can afford the disruption of full automation. So to achieve this long-term vision will require a gradual transition from current farming practices, and most farmers will need technologies than can be introduced step by step, alongside and within their existing systems.

Furthermore, while some emerging robotic technologies are already achieving or approaching the robustness and cost-effectiveness required for real-world deployment, other technologies are not yet at that stage. For example, soft fruit-picking still requires fundamental research in sensing, manipulation, and soft robotics.

Thus, at least in the short term, collaboration between humans and robots is fundamental to increased productivity and food quality.There will be a transition period in which humans and robots work together as first simple, and then more complex, parts of work are conducted by robots, driving productivity and enabling human jobs to move up the value chain.

My take

Farming has long been in the vanguard of the development of new tools, and it stands to reason that greater automation of land management and agri-food production will take place – and is already happening in the UK, and in other parts of the world.

One counter-intuitive knock-on effect of combining robots, automation, sensors, big data, drones, analytics, the IoT, and other technologies, may be that food grows more naturally, not less, without the need for genetic engineering, or for harmful chemicals and pesticides.

For example, US startup Aerofarms is one of many now working in the field of vertical or urban farming. By growing crops in tightly managed ‘ideal’ environments, which are no longer a hostage to weather and other external factors, healthy, tasty, pesticide- and GM-free crops can be produced, much closer to the mouths that need feeding.

For the UK, though, the challenge is a tough one. A farming nation at war with itself over political ideology is crying out for a coordinated national strategy in this critical sector – partly to counterbalance the effects of its own decisions.

But while the UK has begun to get its house in order over robotics and AI policy in 2018, with Sector Deals, a new Office for AI, the revamped industrial strategy, and more, central funding remains the stumbling block.

While the UK is indeed investing millions of pounds in robotics, much of that funding is to replace the upcoming shortfall from the EU. Meanwhile, we are – in the words of a senior civil servant at an AI conference earlier this year – now actively being excluded from European research programmes.

Can you dig it?