Raspberries are difficult fruit to harvest. Their delicate structure leaves them vulnerable to scratches or bruises. They need to be picked by hand instead of machines.
But what if robots, equipped with advanced actuators and sensors, could lend a helping hand? Engineers at EPFL‘s Computational Robot Design & Fabrication (CREATE) lab have set out to tackle this very challenge.
Engineers created a silicone raspberry to train harvesting robots to grasp fruit without exerting too much pressure. In simple words, they are making a viable alternative to harvesting the fruit by hand.
Josie Hughes, a professor at CREATE, said, “It’s an exciting dilemma for us as robotics engineers. 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.”
Plucking raspberries is no easy task: you need to support the berry from below, grasp it gently between your thumb and index finger, then pull carefully until it detaches from the receptacle and falls into the palm of your hand.
To help harvesting robots get trained with this task, the CREATE engineers designed and built a silicone raspberry that can “tell” the robot how much pressure is being applied while the fruit is still attached to the receptacle and after it’s been released. The properties of the silicon raspberry can be adjusted to resemble the fruit’s resistance. Based on that, the robot exerts the necessary picking force.
Ph.D. student Kai Junge said, “Our sensorized raspberry, coupled with a machine learning program, can teach a robot to apply just the right amount of force. 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 raspberry is made from silicone, and its receptacle from 3D-printed plastic. It also contains a fluidic sensor consisting of a soft silicone tube to measure the compression force applied by the robot. Two attached magnets generate a pulling force that holds the fruit and receptacle together.
The team’s robot acts a bit like a gripper with two 3D-printed fingers. These fingers are covered with a thin silicon layer and attached to a robotic arm.
Hughes said, “While the CREATE team has demonstrated the proof of concept for their design, the technology itself is far from mature. It’s incredibly challenging.”
“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.”
Engineers are currently developing a camera system that will allow robots to feel raspberries and see where they’re located and whether they’re ready to be harvested.
Hughes said, “This kind of system could pick other berries too, for example. 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 team is planning to test their robot in the field this summer, during the local raspberry season.
- Soft Sensorized Physical Twin for Harvesting Raspberries, Kai Junge & Josie Hughes, RobotSoft 2022, April 4-8, 2022, Edinburgh.