Artificial intelligence

Agricultural robots set to grow as labor costs rise

Receive free robotics updates

Their machines look more like miniature flying toys than autonomous farming tools, but researchers at Harvard’s Wyss Institute think their RoboBees – which can take off, hover and steer vertically – could eventually perform tasks such as pollinating crops and environmental monitoring.

So far, these RoboBees have yet to work outside of the lab, and commercialization remains a long way off. But advances in technology combined with labor shortages mean that more and more robots are becoming economically viable for use on the farm.

“Fruits within reach use them in tunnels and greenhouses, where they don’t get mud and rain,” says Belinda Clarke, director of Agri-TechE, a membership organization that supports innovation in agricultural technologies. “But, now they are moving on the pitch.”

Their growing abilities make possible a more tailored, plant-by-plant cultivation approach that can minimize inputs such as water and agrochemicals. For example, California-based FarmWise has developed a weeding robot that uses computer vision and artificial intelligence to distinguish weeds from crops, reducing labor costs and enabling farmers to use less of herbicides.

Until recently, agriculture had been slow to adopt robots. High levels of capital investment and limited seasonal deployment made it difficult to create value for the machines. “It hasn’t been a cracking investment theme so far,” says Adam Anders, managing partner at Anterra Capital, a food and agriculture venture capital firm.

But that is changing, he says. In mature economies, restrictions on migrant labour, aging farm workers and a lack of enthusiasm for backbreaking, boring and dirty work mean farm workers cost more and are harder to find. In the United States, for example, the inflation-adjusted hourly wage of agricultural workers increased by 28% between 2000 and 2022, compared to 17% for non-agricultural workers, according to the United States Department of Agriculture.

Because technologies such as computer vision and machine learning enable robots to identify and respond appropriately to objects, some machines can now weed or pick fruits and vegetables with speed, precision and reliability. that were once only achievable by humans.

Additionally, “soft robotics,” using rubber cups or small bean bags, can gently grasp and remove delicate, high-value produce such as peaches and raspberries from the plants without damaging them.

Tjarko Leifer, managing director of FarmWise, anticipates a new wave of robotic farm automation. “Computers can now see and have the dexterity to replace some of those human jobs,” he says.

There may also be durability benefits. Drones and robots in the field can use smart sensors and computer vision to collect and transmit data and images in real time – on everything from local weather and soil conditions to plant growth rates.

FarmWise boss Tjarko Leifer says robotics can tailor nutrient application ‘plant by plant’

Applying machine learning to such large volumes of data can also generate new insights into how and where to grow crops. And, by tracking how plants in different parts of a field respond to inputs such as water and chemicals, robots can help farmers minimize the use of these resources.

This takes precision farming to another level, says Anders: “Instead of applying fertilizers or pesticides en masse, you can apply less of them and be more precise.”

Another advantage of the next generation of robots is that they are smaller than traditional machines, such as combines and tractors. “We want these little beasts to be light and nimble,” says Clarke. “Something powered by a rechargeable battery could be powered by solar energy, which opens up a new opportunity to use robots in a sustainable way.”

Lighter, the machines compact the ground less when they move on it. Compaction makes it harder for plants to access nutrients and for the soil to retain water. “You want the soil to act like a sponge so the water is there when the crop needs it,” Clarke explains.

But, as they become more economically viable in mature markets, few farmers in developing countries are still able to afford robotics. “These things will need to be widely marketed in developed markets,” Anders says.

Another obstacle to the widespread adoption of agricultural robots is regulation. “Whether you’re talking about things that operate completely autonomously on a farm or in the sky, out of sight, there are still uncertainties,” Anders notes. “In the United States, a drone cannot operate out of sight, which more or less defeats the purpose in terms of scaling.”

However, he thinks that is likely to change as governments seek to increase food security and sustainability in agriculture, and also as autonomous machines become smarter and people adapt to their presence.

Leifer believes the success of robotics in advancing precision agriculture will accelerate its adoption. “We can apply the right nutrients and the right crop protection chemistry to every plant in a field and adapt that plant by plant,” he says. “And through that, we benefit the farmer, the consumer and the environment.”

Leave a Reply