Technology 3 min read

Vegebot Uses Machine Learning to Harvest Lettuce

Image Credit: University of Cambridge

Image Credit: University of Cambridge

Engineers have developed a vegetable-picking robot that uses machine learning to identify and harvest crops. They’re calling it Vegebot.

At first, the team of engineers at the University of Cambridge developed and trained the robot to harvest lettuce in a lab setting. But, it became more capable of time. Now, the robot can collect a variety of vegetables in the field condition.

While the prototype is not as fast or efficient as a human, it serves as a groundwork of how robotics can be applied in agriculture. This is particularly important for crops like Iceberg lettuce that are difficult to harvest mechanically.

Iceberg Lettuce’s Resistance to Automation

For almost a decade, crops like wheat and potatoes have been harvested mechanically at a large scale. However, other plants like Iceberg Lettuce have resisted such automation.

How is this possible, you ask?

Aside from getting easily damaged, the crop grows very close to the ground. Hence, it has always posed a challenge for robotic harvesters.

The researchers at the University of Cambridge thought; why not take on this challenge?

Speaking on the project, co-author of the study and researcher from the Cambridge’s Department of Engineering, Simon Birrell said:

“Every field is different, and every lettuce is different. But if we can make a robotic harvester work with iceberg lettuce, we could also make it work with many other crops.”

So, they did.

The engineers developed a machine-learning algorithm to recognize images of lettuce. Then they trained the machine to work under different conditions.

How the Vegebot Uses Machine Learning to Harvest Iceberg Lettuce

The Vegebot’s function is based on two primary components. These include a computer vision system and a cutting system.

Using its overhead camera, the robot first captures an image of the field and identifies all the lettuce. Then, it analyzes if each plant is healthy and ready for harvest.

If lettuce is not mature or has a disease, the robot can reject it. But for a healthy lettuce, the Vegebot moves to the cutting stage.

Thanks to a second camera near the Vegebot’s cutting blade, the harvesting is as smooth as ever. The researchers adjusted the pressure in the robot’s gripping arm such that it could firmly grip the lettuce without crushing it. They also made the grip adjustable for other crops.

As you can imagine, the whole process is inefficient and time-consuming.

Co-author Josie Hughes noted:

“For a human, the entire process takes a couple of seconds, but it’s a challenging problem for a robot.”

Still, it paints a picture of a robotic harvest’s future. It looks pretty.

Using Robots for Harvesting

Not only would robotic harvesters solve the issue of labor shortages in agriculture, but the machines could eliminate food shortage.

Right now, human workers only harvest each field once and discard unripe fruits or vegetables.

Robotic harvesters, on the other hand, can harvest around the clock. Using machine learning techniques, engineers can also train the machine to pick only ripe produce.

The researchers published their findings in the Journal of Field Robotics.

Read More: Robotic Farming is Coming Sooner Than You Think

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.

Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.