As the impact of heavy machines on soil health comes under increasing scrutiny, interest is growing in the potential for swarm robots to replace them.
Small, simple and inexpensive, swarm robots are poised to reverse the trend in agriculture towards ever bigger machines, according to their proponents.
The advantages they offer are said to include less damage to soil structure and greater precision for tasks such as planting, crop protection and harvesting.
But how close to reality is the use of robot swarms on farms and, importantly, what is needed to ensure their safe, responsible use?
Agri-Tech East recently brought together a group of experts to discuss the issues at a ‘Swarm Robotics – the agri- workforce of the future?’ forum.
Alan Millard, a lecturer in robotics at the University of Plymouth is working on the transition of swarm robots from the lab to the field.
“Lab-based swarm robots typically feature sensors for obstacle avoidance, a pair of wheels for simple locomotion, the ability to communicate with other robots – such as via Wi-Fi or Bluetooth – and sometimes a gripper for manipulating objects in the environment,” he says.
In agriculture, robot swarms could be applied to tasks such as soil and plant health monitoring, weed control, drilling, and harvesting.
The inspiration for swarm robotics came from natural self-organising systems incorporating many individual agents, such as flocks of birds, swarms of ants or shoals of fish.
“They all act without any kind of leader telling them what to do,” Dr Millard adds.
“We want to try and borrow desirable properties from those systems and put them into engineering systems.”
Whether swarm robots can successfully make the transition from lab to farm is as yet an unanswered question.
But perhaps more important questions are ‘Should we even bother? What is the point of swarm robots in agriculture?’ says Dr Millard.
The point, he suggests, is that labour shortages, arising either as a result of fewer people choosing to work in farming or restrictions imposed on migrant workers, will inevitably result in a need for more automation.
“Automation has got to happen. Swarm robotics is one way of achieving it and there seems to be a nice fit with agriculture,” he adds.
“We are probably never going to end up with a single robot that solves all crop issues. That is one of the main challenges we could face, to figure out how we develop systems that may be modular or configurable, so that we can take the concepts from one agricultural problem and apply it to another.”
Further significant challenges include connectivity in rural areas, development of a viable business model for use of swarm robots and public acceptance.
“These systems seem very science fiction in comparison to a traditional farming system. There is a long way for us to go to actually demonstrate that there
is a point in doing this,” Dr Millard says.
His work at the University of Plymouth is focused on the £10 million AgriTech Cornwall Project, a European Rural Development Fund (ERDF) initiative that also includes Rothamsted Research, Duchy College, University of Exeter and the Cornwall Development Company.
Projects include robotic harvesting of cauliflower, soil health mapping using robots and robot-mounted fluorescence imaging technology for detection of pre-symptomatic disease in plants.
But while robotics technology is exciting, some of those working on its development believe there are important questions to be answered at this early stage of its journey into agriculture.
Dr David Rose, lecturer in geography at the University of East Anglia, argues that responsible innovation requires inclusion of users from the start and consideration should be given to three questions before starting on an innovation pathway: Who benefits? Who loses? Who decides?
“All too often, decisions are made by powerful technology companies without the inclusion of user voices,” he says.
“Robotics might promise increased yields and profitability but there may be negative consequences which might mean we shouldn’t go down that route.
“We need to be aware of wider debates about change, why these technologies might change the nature of farming and how we mitigate some of the side effects of change.
“We have got a precedent here with GM, when a piece of technology was ready to go in this country and Europe, and people said no. That technology is still available, but we can’t use it because the public decided they didn’t want it.
“There are going to be public concerns about what farming looks like in this robotic world.
“I think with GM we designed the technology and then asked for permission to use it at the very end and it was too late to involve the public and opinions against it had already formed.
“As we are developing swarm robotics, we should be involving the public in debates about the future of farming. By involving the public, we can perhaps to some extent shape their views and change and alter our trajectory so we don’t get a backlash when swarm robotics is ready to go.
“There are a lot of conversations already happening on Facebook, on Twitter, in the press, that give some indication about what people think about the robot revolution in farming. And I think we need to enter those debates if we want ultimately to implement swarm robotics on farm.”
Reflecting on how swarm robotics might work in practice on-farm, farmer and Precision Decisions (now part of Map of Agriculture) CEO Clive Blacker
is seeking answers to some pressing questions.
“If we want more output from smaller machines we will need to work them for longer or need more of them,” he says.
“We are still very much in early phases of robotics in agriculture and unsure of the size of a fleet that may be needed to make it competitive. These are all questions we are trying to work out.
“However, what is clear is that automation on-farm will occur in one stage or another and smaller robotic machines have some really compelling benefits, which will also need developing and exploring before the market is comfortable to adopt them.
“That said, there is no lack of appetites or interest from farmers to know what this may look like in the future.”
However, for robotics to really take effect in agriculture, robotics needs a revolution, he adds.
“At the moment we are all really excited that these things are ploughing up and down the field but it is not the robot that is going to make the difference,” he says.
“It is how the robot operates, the sensors on the robot and how the robot applies the technology or the application or the product that will make the difference
Sam Watson-Jones, farmer and founder of the Small Robot Company sees robotics at the forefront of a new farming system that will see a shift away from heavy machinery, improvements in soil health, better data collection and use and ultimately a change in focus from the field as a management unit to individual plants.
“If you start to adopt that line of thinking, you begin to realise how much of the way the countryside looks is not because it has been determined as the most productive way to use the field, but as the most efficient way to use machinery,” he concludes.
Science fiction it may seem, but consider that in the dairy sector the robots have arrived. According to the latest Map of Agriculture farm survey results 7% of dairy farmers were already using robotics and a further 12% were considering investing.