It may be a while before robots and drones are as common as tractors and combines, but the high-tech tools may soon play a major role in helping feed the world’s rapidly growing population.
At the University of Georgia, a team of researchers is developing a robotic system of all-terrain rovers and unmanned aerial drones that can quickly and accurately gather and analyze data. This information is vital for scientists working to increase agricultural production.
The Need For Robots
“By mid-century, scientists estimate the world’s population will reach 9.1 billion people, a 30 percent increase in a little more than 30 years,” says Changying “Charlie” Li, a professor in UGA’s College of Engineering and the principal investigator on the project. “This increase will demand that we nearly double our current food production. One solution is to use genomic tools to develop high-quality, high-yield, adaptable plants.”
While scientists gather plant data now, the process is expensive and painstakingly slow. The team of robots developed by Li and his collaborators will one day allow researchers to compile data on entire fields of crops throughout the growing season.
Breaking The Bottleneck
The project addresses a major bottleneck in genetics research, says Andrew Paterson, a co-principal investigator. Paterson, a world leader in the mapping and sequencing of flowering-plant genomes, is a Regents Professor in UGA’s College of Agricultural and Environmental Sciences and Franklin College of Arts and Sciences.
“The robots offer us the means to gain information presently beyond our reach,” he says. “For example, by measuring plant height at weekly intervals instead of at the end of the season, we can learn about how different genotypes respond to specific environmental parameters, such as rainfall.”
In addition to multispectral, hyperspectral and thermal cameras, the robots will be outfitted with a remote sensing method that uses light in the form of a pulsed laser to measure distances. The technology will allow the researchers to create precise three-dimensional images of the plants they study.
Crunching Massive Data Sets
During preliminary testing last year at UGA’s Iron Horse Plant Sciences Farm, Li estimates the team collected 20 terabytes of data over the six-month growing season. He says the team will collect 30 times that amount when the robots are fully deployed.
To analyze these massive data sets, researchers are developing an artificial intelligence algorithm similar to the facial recognition program Facebook uses to facilitate the identification and “tagging” of people in a photograph.
“Our algorithm will be able to scan an aerial photo of a field and automatically identify the location and number of flowers on each plant,” says Li.
With teams of autonomous vehicles rumbling through rows of crops and hovering overhead, algorithms will also play a key role in making sure the robots and drones perform their assigned tasks while staying out of each other’s way. Javad Mohammadpour Velni, a co-principal investigator and an assistant professor in the College of Engineering, is developing tools that will allow the ground and aerial vehicles to operate independently but collaboratively to efficiently cover fields and collect different types of data.
Most Gains Through Genetics
The researchers believe their work will provide a platform for plant geneticists to gather massive amounts of phenotype data.
“Historically, genetics has been credited for about half of the yield gains,” Paterson says. “It’s realistic to envision that genetics will need to account for about half of the doubling of agricultural output that’s needed by 2050.”
The team’s project is supported by a $954,000 grant from the National Robotics Initiative, a program jointly sponsored by the National Science Foundation, the U.S. Department of Agriculture, the U.S. Department of Energy, NASA and the National Institutes of Health. PG
Article by Mike Wooten, external communications coordinator with the University of Georgia College of Engineering.