Sign Up for the Newsletter
The most up-to-date news and insights into the latest emerging technologies ... delivered right to your inbox!
The robotic gripper was trained using data from a 3D-printed, sensorized raspberry
June 27, 2023
Researchers have created a robotic gripper gentle and precise enough to pick soft, small fruits such as raspberries.
The team, from EPFL’s Computational Robot Design & Fabrication (CREATE) lab, set out to create a harvesting robot fitted with an array of advanced actuators and sensors to enable precise picking capabilities, without damaging the delicate fruit.
The resulting design was tested on a silicone raspberry to optimize its picking capabilities. The silicone fruit can “tell” the robot how much pressure is being applied, allowing the robot to adjust its grip accordingly and use this data to train its movement.
The raspberry is made of silicone and 3D-printed plastic and contains a “fluidic sensor” that measures the force exerted on it by the robot.
“Our sensorized raspberry, coupled with a machine learning program, can teach a robot to apply just the right amount of force,” said Kai Junge, CREATE engineer. “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.”
The team said its design responds to the “exciting dilemma” of the rising demand for automated solutions in the agricultural industry in response to ongoing labor shortages and high costs and the current lack of robotic solutions designed for the often delicate tasks.
“The raspberry harvesting season is so short, and the fruit is so valuable, that wasting them simply isn’t an option,” said Josie Hughes, CREATE engineer. “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.”
The team said its design remains in the proof-of-concept phase, with plans to create more complex controllers to allow the robots to pick raspberries on a larger scale, as well as possibly other fruits moving forward. A camera system for the robot is also in development, allowing the robot to see the fruit it’s picking, and determine whether they’re ready for harvesting.
Assistant Editor, IoT World Today
Scarlett Evans is the assistant editor for IoT World Today, with a particular focus on robotics and smart city technologies. Scarlett has previous experience in minerals and resources with Mine Australia, Mine Technology and Power Technology. She joined Informa in April 2022.
You May Also Like