The need to accelerate and boost crop yields have scientists turning to robotics to help farmers meet the growing demands driven by increasing population.
Researchers from the University of Illinois have created a 13-inch-wide, 24-pound TerraSentia robot that is transportable, compact and autonomous. The robot captures each plant from top to bottom using a suite of sensors, algorithms and deep learning. Using a transfer learning method, researchers taught the robot to count corn plants with just 300 images.
"In Africa, the population will more than double by 2050, but today the yields are only a quarter of their potential,” said Girish Chowdhary, an assistant professor of field robotics in the Department of Agricultural and Biological Engineering and the Coordinated Science Lab at Illinois.
Farmers are trying to boost yields while also preparing crops to withstand severe weather and changing climates. In order to accomplish this, farmers must locate genes for high-yielding, hardy traits in crop plants’ DNA. Crop breeders are conducting experiments to compare thousands of different varieties of crops over hundreds of acres and key traits. The problem is humans can only manually measure a fraction of plants in a field.
Using robots that can count plants autonomously can help but with vast fields, the robot must stay within the tight rows which can be challenging. If the plants aren’t equally spaced, it can be an even larger challenge.
"We developed a method that uses the camera motion to adjust to varying inter-plant spacing, which has led to a fairly robust system for counting plants in different fields, with different and varying spacing, and at different speeds,” said Zhongzhong Zhang, a graduate student in the College of Agricultural Consumer and Environmental Science (ACES).