Mar 13 2018
Field scouting and data collection for seed companies, agronomists, and farmers could now be advanced by an innovative, low-cost, and lightweight agricultural robot.
Agricultural and biological engineering professor Girish Chowdhary is leading a team that includes crop scientists, computer scientists and engineers in developing TerraSentia, a crop phenotyping robot. (Image credit: L. Brian Stauffer)
A group of researchers from the University of Illinois has developed the TerraSentia crop phenotyping robot, which will be presented on March 14 at the 2018 Energy Innovation Summit Technology Showcase in National Harbor, Maryland.
The robot autonomously moves between rows of crops and evaluates the attributes of individual plants by using a range of sensors (which include cameras), and performs real-time transmission of data to the laptop computer or phone of the operator. A tablet computer and a custom app that is integrated into the robot allow the operator to guide the robot by using GPS and virtual reality.
The scientists said that TerraSentia is teachable and customizable. At present, they are creating machine-learning algorithms to “teach” the robot to find out and recognize common diseases, and to evaluate an increasing range of attributes, for example, leaf area index, plant and corn ear height, and biomass.
“These robots will fundamentally change the way people are collecting and utilizing data from their fields,” stated Girish Chowdhary, a agricultural and biological engineering professor at the University of Illinois. He is heading a group of engineers, students, and postdoctoral researchers in advancing the robot.
TerraSentia weighs a mere 24 pounds and hence is so lightweight that it could roll over young plants without any harm to them. The robot is 13 inches wide, making it portable and compact: An agronomist can easily place it inside a car trunk or on a truck seat to carry it to the field, stated Chowdhary.
Automation of analytics and data collection enables the breeding pipeline to be enhanced by unearthing the reason behind the disparities in the response of different plant varieties to environmental conditions, stated Carl Bernacchi, a University of Illinois plant biology professor, who is one of the researchers working on the project.
According to Bernacchi, data gathered by the robot can be used by plant breeders to recognize the genetic lineages presumed to yield the highest and best quality produce in particular locations.
Bernacchi and Stephen P. Long, a Stanley O. Ikenberry Endowed Chair and the Gutgsell Endowed University Professor of Crop Sciences and Plant Biology at Illinois, assisted in ascertaining the plant attributes that are significant for the robot to evaluate.
It will be transformative for growers to be able to measure every single plant in the field in a short period of time. Crop breeders may want to grow thousands of different genotypes, all slightly different from one another, and measure each plant quickly. That’s not possible right now unless you have an army of people - and that costs a lot of time and money and is a very subjective process.
A robot or swarm of robots could go into a field and do the same types of things that people are doing manually right now, but in a much more objective, faster and less expensive way.
Carl Bernacchi
TerraSentia fills “a big gap in the current agricultural equipment market” between huge machinery that rapidly sprays or cultivates several acres and human workers with the ability to carry out tasks necessitating accuracy but work much more gradually, stated Chowdhary.
There’s a big market for these robots not only in the U.S., where agriculture is a profitable business but also in developing countries such as Brazil and India, where subsistence farmers struggle with extreme weather conditions such as monsoons and harsh sunlight, along with weeds and pests.
Girish Chowdhary
As a phased introduction approach, large U.S. universities, various leading seed companies, and overseas collaborators will be performing field tests on 20 of the TerraSentia robots this spring using an early adopter program. According to Chowdhary, the robot is anticipated to be available to farmers in about three years, where the cost of specific models is expected to be less than 5000 dollars.
“We’re getting this technology into the hands of the users so they can tell us what’s working for them and what we need to improve,” stated Chowdhary. “We’re trying to de-risk the technology and create a product that’s immediately beneficial to growers and breeders in the state of Illinois and beyond.”
Commercial crop breeders and crop scientists can obtain the robot for the 2018 breeding season through EarthSense Inc.; a startup company co-founded by Chowdhary in partnership Chinmay P. Soman.
Soman is a former National Science Foundation postdoctoral fellow at the University of Illinois, and at present, he is the chief executive officer of EarthSense, which is based University of Illinois Research Park and includes a growing strength of computer scientists and engineers.
Advanced Research Projects Agency-Energy, a unit within the U.S. Department of Energy, has sponsored the Energy Innovation Summit Technology Showcase, to be conducted from March 13 to 15.
Funding of 3.1 million dollars was provided by ARPA-E’s Transportation Energy Resources from Renewable Agriculture program for the TERRA-Mobile Energy-crop Phenotyping Platform robot project, which created TerraSentia.
Ag Robot Speeds Data Collection