Sight, hearing, “mental” processing…, many robots already have all these characteristics, but touch was one of the debts of the robotic world. Until now. A team of Chinese experts has developed a robot that identifies different species of plants at different stages of growth “touching” its leaves with an electrode. The robot can measure properties such as surface texture and water content that cannot be determined with existing visual methods, according to the study, published in Cell.
According to the authors, the robot identified ten different plant species with an average accuracy of 97.7% and identified the leaves of the flowering bauhinia plant with 100% accuracy at various stages of growth.
“Eventually, large-scale farmers and botanical scientists could use the robot to monitor the health and growth of crops and take Specific decisions about how much water and fertilizer to give your plants and how to approach pest control – says Zhongqian Song, leader of the study -. “This advance could revolutionize crop management and ecosystem study and enable early disease detection, which is crucial for plant health and food security.”
Instead of making physical contact with a plant, existing devices capture more limited information using visual approaches, which are vulnerable to factors such as lighting conditions, changes in weather or background interference.
To overcome these limitations, Song’s team developed a robot that “touches” plants using a mechanism inspired by human skin, with structures that work together hierarchically to obtain information through touch. When an electrode on the robot makes contact with a leaf, The device learns about the plant by measuring various properties: the amount of charge that can be stored at a given voltage, the difficulty the electrical current has in moving through the blade, and the contact force when the robot grabs the blade.
This data is then processed using machine learning to classify the plant, as the different values for each measurement are correlate with different plant species and growth stages.
While the robot shows potential applications in fields ranging from precision agriculture to ecological studies and plant disease detection, it has several weaknesses that have not yet been addressed. For example, the device is not yet versatile enough to consistently identify types of plants with complicated structures, such as burrs and needle-like leaves. This could be remedied by improving the robot’s electrode design, the authors note.
“It may take a relatively long period of time to reach full-scale production and deployment, depending on technological and market advances”Song concludes.
The next step is to expand the number of plants the robot can recognize by collecting data from a wider range of species, which will boost the database they use to train algorithms. They also hope further integrate the device’s sensor so that it can display results in real timeeven without an external power source.