Skip to Content
Artificial intelligence

Robotic Farmers Can Literally Reap What They Sow

September 12, 2017

If you want to grow a field full of barley but don’t want to get your hands dirty, never fear: robots can do the whole dang thing.

That’s what researchers from Harper Adams University in the U.K. have shown. In a sleepy hectare of land in Shropshire, England, robots have been tending the land without a human setting foot on the field. A series of roboticized tractors and harvesters, along with drones for aerial surveillance, have carefully planted seeds, taken soil and crop samples, sprayed herbicides and fertilizers, and even harvested the resulting crop of barley. You can see them in action above.

As IEEE Spectrum points out, the yields achieved by the Hands Free Hectare project are so far uninspiring. Without the careful eye of a farmer checking the crops in person, the researchers only managed to generate 4.5 metric tons of barley per hectare—which is some way off the average 6.8 metric tons you might expect on a regular farm.

But this is a proof of concept, and it serves to show that robots are certainly able to take over from humans when it comes to the repetitive efforts of farm labor—especially if they get a little better with practice. The researchers also point out that automation allows the use of smaller, lighter vehicles, which makes sowing and harvesting more precise and reduces damage caused to land as they trundle across fields.

Still not convinced? Then how about this: last week, tractor maker John Deere acquired a Silicon Valley AI firm, which precision-targets weed killer using machine learning, for a cool $300 million. The future of farming is headed in one direction, and it’s automated.

Deep Dive

Artificial intelligence

Why Meta’s latest large language model survived only three days online

Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.

DeepMind’s game-playing AI has beaten a 50-year-old record in computer science

The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.

A bot that watched 70,000 hours of Minecraft could unlock AI’s next big thing

Online videos are a vast and untapped source of training data—and OpenAI says it has a new way to use it.

Google’s new AI can hear a snippet of song—and then keep on playing

The technique, called AudioLM, generates naturalistic sounds without the need for human annotation.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.