Nov 20, 2008Carnegie Mellon developing automated systems to enable precision farming
Two groups of researchers at Carnegie Mellon University’s Robotics Institute have received a total of $10 million in grants from USDA to build automated farming systems. One is for apple growers and one is for orange growers, but both are designed to improve fruit quality and lower production costs.
The systems use sensors on autonomous robotic vehicles or at fixed sites within the orchards to gather a multitude of data about tree health and crop status. Robotic vehicles will be used to administer precise amounts of water or agricultural chemicals to specific areas or trees. The vehicles also will be used to automate routine tasks such as mowing between tree rows.
The projects were funded this fall through USDA’s new Specialty Crop Research Initiative. The Comprehensive Automation for Specialty Crops (CASC) Program, led by Sanjiv Singh, research professor of robotics, received a four-year, $6-million grant to develop systems for the apple industry. The Integrated Automation for Sustainable Specialty Crop Farming Project, led by Tony Stentz and Herman Herman of the Robotics Institute’s National Robotics Engineering Center (NREC), received a three-year, $4-million grant to develop systems for the citrus industry. Both project grants will be matched dollar for dollar by industry, state governments and other funding sources.
“We are taking automation to a level never before demonstrated in an agricultural setting,” said Herman of the NREC project. “This will provide an early look at how the automated farm may someday operate and promises to deliver insights and lessons far beyond what should be expected from small demonstrations of autonomous scouts.”
“Mobile sensors and computer tracking will enable growers to monitor their orchards in unprecedented detail,” Singh said. “Growers will receive early warning of diseases and insect infestations, as well as continuous updates on crop status. With this information, growers can make timely decisions that will save them money and improve the quality of their crop.”
Although Carnegie Mellon is not a university traditionally associated with agricultural research, the Robotics Institute’s Field Robotics Center has been involved in agricultural automation since the early ’90s, and the NREC has worked with agricultural equipment manufacturers since it opened in 1996. Moreover, both organizations have experience in managing research programs involving academic, industrial and governmental researchers working closely with end users.
“This level of collaboration between academia, government and industry is not at all common in agriculture research,” said Jim McFerson, manager of the Washington Tree Fruit Research Commission.
The technologies developed will be applicable not only to apple and orange growers, but to producers of all kinds of tree fruits, he added.
“Growers can use the data generated by this new approach to make decisions throughout the year regarding pest management, pruning, fertilization, irrigation and yield estimates,” McFerson said. “We believe this will result in higher-quality fruit at a lower per-unit cost, as well as a more productive and safer workplace.”
The CASC Program will work with apple growers in Pennsylvania, Oregon and Washington and includes collaborators from Penn State, Washington State, Oregon State and Purdue universities, as well as the USDA Agricultural Research Service. Researchers will use a fleet of automated, four-wheel vehicles that can perform multiple tasks including tree monitoring and chemical spraying. Industrial partners include Toro, Trimble, Vision Robotics, IONco and Sensible Machines.
The NREC’s Integrated Automation for Sustainable Specialty Crop Farming Project will deploy a fleet of networked, unmanned tractors in the orange groves of Southern Gardens Citrus (SGC), one of Florida’s largest growers. In addition to SGC, collaborators include researchers at the University of Florida, Cornell University and Deere & Co.
Harvesting remains one of the most labor-intensive operations at orchards, but it also is challenging to automate because of demanding handling and cost requirements. Both projects will investigate new designs for mechanical harvesters, including a vacuum-assisted device that CASC will use for apple harvesting – but the emphasis will be on aiding human harvesters rather than replacing them.