No eyes needed: China’s robot nails plat ID by touch with 97.7% accuracy

Robots are expected to aid human workers across various industries in the future.
Interestingly, the future may hold a reality where robots become the caretakers of the agricultural fields.
Researchers in China have introduced a futuristic concept.
They have developed a robot that can identify plant species with high accuracy. By simply “touching” leaves, this innovative device can determine its type, its stage of growth, and even potential health issues.
The robot demonstrated an average accuracy of 97.7% in identifying ten plant species. On the other hand, it achieved a perfect accuracy of 100% in classifying bauhinia leaves across different growth stages.
“It could revolutionize crop management and ecosystem studies and enable early disease detection, which is crucial for plant health and food security,” said Zhongqian Song, an associate professor at the Shandong First Medical University & Shandong Academy of Medical Sciences and study author.
Various plant parameters
The robot can measure properties like surface texture and water content, which are undetectable by visual methods.
The robot’s touching mechanism is inspired by human skin. The robot’s interconnected structures enable it to acquire information through tactile means.
The robot learns about a plant by touching its leaves with an electrode. As it makes contact with a leaf, it gathers a wealth of data including its charge storage capacity, electrical conductivity, and contact force.
This data is then processed using sophisticated machine-learning algorithms.
This model learns to recognize patterns in the data that correspond to different plant species and their growth stages.
This development is beneficial as existing devices rely on visual methods. This method significantly restricts the amount of data collected. Furthermore, these existing devices are vulnerable to external factors such as lighting conditions, weather changes, and background interference.
It may help boost crop yield
This robot has the potential to aid in crop management by assisting both large-scale farmers and agricultural experts in monitoring plant health and growth.
The team envisions farmers using this robot to monitor their crops in real time, optimizing water and fertilizer usage, and detecting diseases early on.
This could lead to higher yields, reduced waste, and a more sustainable food system.
However, the researchers note that the robot currently possesses several limitations that require further development.
The robot currently struggles to identify plants with complex leaf structures like burrs and needles. To overcome this, the researchers plan to redesign the robot’s electrode.
“It may take a relatively long period of time to reach large-scale production and deployment depending on technological and market developments,” added Song in the press release.
After this initial development, the researchers aim to improve the robot’s capabilities by expanding its plant database. They also aim to integrate a sensor for real-time display, even without external power.
Upon full development, this innovative technology could contribute to advancements in fields such as precision agriculture, ecological studies, and plant disease detection
Source: Interestingengineering

About the author

Gubba Group: