Scientists train fruit-picking robots with silicon raspberries

The replica raspberries are marvels of engineering.
Loukia Papadopoulos
The replica raspberry.jpg
The replica raspberry.


Raspberries might be delicious but they are notoriously hard to harvest since they are soft and dewy making them easily damaged. But what if robots, equipped with advanced actuators and sensors, could pick them gracefully?

Engineers at EPFL’s Computational Robot Design & Fabrication (CREATE) lab are training robots to pick the famous fruit on a silicone version that mimics the real thing.

This is according to a press release by the institution published last month.

“It’s an exciting dilemma for us as robotics engineers,” said Josie Hughes, a professor at CREATE. 

“The raspberry harvesting season is so short, and the fruit is so valuable, that wasting them simply isn’t an option. What’s more, the cost and logistical challenges of testing different options out in the field are prohibitive. That’s why we decided to run our tests in the lab and develop a replica raspberry for training harvesting robots.”

And what they have achieved is no small feat: the CREATE engineers designed and built a silicone raspberry that can “tell” the robot how much pressure is being applied, allowing the machines to harvest the fruit without damaging it. 

“Our sensorized raspberry, coupled with a machine learning program, can teach a robot to apply just the right amount of force,” explained PhD student Kai Junge. 

“The hardest part is training the robot to loosen its grip once the raspberry detaches from the receptacle so that the fruit doesn’t get squashed. That’s hard to achieve with conventional robots.”

CREATE’s replica raspberry is a marvel of engineering consisting of flesh made from silicone and a receptacle produced from 3D-printed plastic.

The research is still at its infancy with the lab’s harvesting robot consisting of little more than a gripper with two 3D-printed fingers covered with a thin layer of silicone and attached to a robotic arm. As such, the technology itself is far from mature.

 “It’s incredibly challenging,” added Hughes. “So far we’ve been using a very simple feedback system in our robot. The next step will be to design and build more complex controllers so that robots can pick raspberries on a larger scale without crushing them.” 

For next steps, the engineers are focused on  developing a camera system that will allow robots to not only “feel” raspberries, but also “see” them.

“This kind of system could be used to pick other berries too for example,” concluded Hughes in the statement.

“We’d also like to develop technology for other soft fruit and apply this physical-twin concept to more complicated tasks like other berries, tomatoes, apricots or grapes.”

The researchers have ambitious plans to test their robots in the summer raspberry picking fields.

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board