Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Strawberry-picking robots could replace human workers in the field

Add as a preferred source on Google
University of Essex

If you had banked on strawberry-picking as a potential career after your current job is taken by a robot, we have some bad news for you: That’s probably not going to be an option for much longer. In the U.K., robotics experts at the University of Essex have teamed up with a British jelly manufacturer to find ways to train robots to pick strawberries on farms.

Their rationale is that U.K. farms currently waste around 20 percent of their soft fruit due to problems recruiting enough workers. This situation could potentially get even harder after Brexit, which is why there’s a need to find alternative ways of harvesting this fruit.

Recommended Videos

But just because picking fruit is an easy task for humans doesn’t mean the same is necessarily true for machines.

“The main challenge is the unstructured dynamic nature of the problem,” Vishuu Mohan, a professor in the School of Computer Science and Electronic Engineering at Essex, told Digital Trends. “Berries grow with time, come in different shapes, sizes, order of ripeness, and the environment cannot be fully controlled. In such conditions, solving the identification or ‘what could be a ripe berry,’ localization or ‘where is it in space,’ and motion planning or ‘how do I move to reach, grasp, and cut it’ [problems] are the main challenges.”

Considering that a human can pick a berry in a fraction of a second, the robots the team is developing will have to exhibit an impressive amount of precision, speed, and other traits to compete. It can, however, be done. In the past, we’ve covered robots designed to pick everything from cucumbers to tomatoes. Meanwhile, a Belgian engineering company called Octinion is working on similar strawberry-picking tech, which it aims to have in around 100 greenhouses worldwide by next year.

At present, the University of Essex researchers have developed a robot that’s able to accurately identify and reach for berries, with the next step being to build an end effector that can cut stems as required. A prototype is expected to be unveiled in the next several months.

But while this may seem yet another quasi-depressing chapter on the road to total workplace automation, Mohan is more optimistic. “Contrary to the notion that ‘robots are taking jobs,’ they are actually not in this particular case, and humans can move higher up in the value chain — for example controlling the robots, [and] managing the logistics,” he said.

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Students who use AI every day may be falling behind, while moderate users pull ahead
New global testing data suggests more AI in the classroom isn't automatically better.
Logo, Text

I assumed more AI access might help students learn faster. However, a new OECD study dispels that misconception for me and everyone else who gave their children a paid version of AI chatbots, thinking it would help them through their educational journey. 

According to PISA 2025 data from 760,000 students in 91 countries, students who use AI daily score meaningfully worse on standardized tests than their peers. The full picture is more complicated than a simple ban would fix.

Read more
XPENG just put its humanoid robot on the production line, and it walked itself out
IRON clocks in for its first shift
XPENG Iron

XPENG’s humanoid robot has officially joined the workforce, and it even got an employee badge. The Chinese automaker announced on September 8 that its next-generation IRON had completed assembly and autonomously walked off its newly commissioned humanoid robot production line in Guangzhou.

CEO He Xiaopeng then pinned a staff badge onto the robot, symbolically welcoming it to the XPENG team. It is a charming little ceremony for a machine that the company hopes will eventually become a regular part of everyday life. XPENG is moving IRON beyond R&D prototypes toward production-line manufacturing, applying the quality-control systems and manufacturing experience it has developed through its electric vehicle business.

Read more
An AI-designed drug might help slow aging, but we’re not there yet
The results hint at a possible anti-aging effect, but there’s still a long way to go before we know what it means.
medical test tubes

Rentosertib, a drug Insilico Medicine designed almost entirely using AI, was created to treat idiopathic pulmonary fibrosis, a disease that scars and stiffens the lungs over time. But fighting lung disease was only half the plan from the start.

According to a new study published in Nature Biotechnology, the drug's target was chosen specifically because it overlaps heavily with the biology of aging, and the whole trial was designed to test whether treating the lungs could also mean turning back the body's biological clock.

Read more