Researchers at Cornell University have developed a soft robotic gripper capable of detecting fruit ripeness by touch and harvesting delicate produce without causing bruising or damage.
The technology uses stretchable fiber-optic sensors to allow the robot to assess the stiffness of fruit, enabling it to predict ripeness before gently twisting the fruit from its vine. The research was published in Nature Communications and was led by former postdoctoral researcher Anand Mishra in the lab of Rob Shepherd, the John F. Carr Professor of Mechanical Engineering in Cornell’s Duffield College of Engineering.
According to the researchers, the project could support more resilient and sustainable food production systems, while also improving the commercial viability of fruit species that are difficult to cultivate or transport.
“The great thing about Cornell is we’re a really great agriculture school, and a lot of avenues are opening up because of it,” Shepherd said. “It really allows us to uniquely combine our robotics expertise with our agricultural prominence.”
To develop and test the system, the team partnered with Marvin Pritts, professor of horticulture and global development, and used strawberries as a model crop. Shepherd explained that strawberries provided a reliable benchmark because their ripeness can be visually confirmed through color.
“You can accurately tell when strawberries are ripe by their color,” Shepherd said. “So we could train our model to know if it’s ripe based on touch, then validate our model by looking at the color.”
The gripper includes two fiber-optic sensing systems: one measures the curvature of the robotic fingers, while the other measures pressure at the fingertip. This allows the robot to estimate the fruit’s shape and apply an appropriate grip without damaging the surface.
Researchers also added a planetary gear mechanism that allows the robotic wrist to rotate and twist fruit from the vine rather than pulling it free, reducing strain on delicate produce. A camera mounted in the palm of the gripper helps identify fruit obscured by leaves or vegetation.
The team believes the technology could eventually support more diverse and sustainable farming practices by enabling smaller robotic systems to manage mixed-crop agriculture more efficiently.
“Robots will allow us to do things we cannot do economically right now,” Shepherd said. “We have row crops because row crops fit our machines. But if we have a larger amount of smaller robots, we can have mixed cropping of different species that support each other.”
Article Source: Cornell Chronicle
