Pollinators play a significant role in the production of more than 150 food crops
in the United States with almost all fruit and grain crops requiring pollination
to produce their crop. Pollinators come in all shapes and sizes and if a research
West Virginia University has its way, they may also one day come in the
form of a robot.
And it’s not just any robot; it’s Cataglyphis, winner of the Sample Return Robot Challenge, part of NASA’s Centennial Challenge.
Yu Gu, assistant professor of mechanical and aerospace engineering, will lead a team of researchers that includes faculty from the Davis College of Agriculture, Natural Resources and Design as they attempt to turn the robot into a precision pollination robot. The three-year study is being funded by a more than $700,000 grant for the first two years from the National Robotics Initiative, a multi-agency effort that includes the National Science Foundation, NASA, the National Institutes of Health, the U.S. Department of Agriculture and the Department of Defense.
Other members of the research team from WVU include Jason Gross, assistant professor of mechanical and aerospace engineering; Xin Li, professor of computer science and electrical engineering; Giacomo Marani, research engineer with West Virginia’s Robotic Technology Center; Yong Lak Park, associate professor of entomology; and Nicole Waterland, assistant professor of horticulture.
The former collection basket on Cataglyphis will be turned into a robotic arm that will be used for precise flower manipulation including pollination. It will be tested in a greenhouse environment on bramble fruit, most notably blackberries and raspberries.
“Approximately $24 billion worth of crops per year in the U.S. rely on pollination by various pollinators,” said Park. “However, the recent decline of honey bees has greatly threatened productivity and the shortages of pollinators in the U.S. have significantly increased the cost of farmers’ renting them for pollination services.”
The pollinator robot design will support four main functions: robot navigation and mapping; flower detection, localization and evaluation; flower manipulation for pollination; and human-robot interaction.
Through the use of computer vision algorithms, which use image and video data to control the robot’s function, the robot will be able to estimate the flower position, size, orientation and physical condition, and to guide the robotic arm to capture and interact with flowers. A set of soft brush tips, mimicking bee’s hairs and motion, will then be used to pollinate the flowers.
The design parameters of the delicate robot-flower interface will be driven by a series of insect pollination experiments. The precision rover navigation, mapping and localization of individual flowers within complex greenhouse environments will be provided through a sensor fusion algorithm.
“A database will be automatically generated and updated by the robot, recording the history of flower development and pollination status,” Gu said. “This intelligent system will allow more selective, consistent and uniform pollination, which has the potential of leading to better fruit set and production at a large scale.”
According to Gu, robot experiments will be performed with incremental difficulties.
“The first two years of the project will be spent achieving precision autonomous robot navigation and mapping inside a greenhouse and identifying and cataloging the flowers through computer vision,” he said. “In year two, we will begin using the robotic manipulator, which will initially be fixed to a bench top, to pollinate flowers.”
The final evaluation of the prototype pollinator robot’s effectiveness will be performed in WVU’s Evansdale Greenhouse during the third year of the project.
“Blackberries and raspberries will be grown in the greenhouse under ambient light,” Gu said. “Four methods of pollination—bee pollination, manual pollination, autonomous robot pollination and mixed human-robot teaming on pollination—in addition to no pollination, will be performed and the efficiency of each pollination method will be compared.”
The effectiveness of pollination will be evaluated by determining the fruit yield per plant, fruit size, fruit weight, harvest time and overall distribution of fruit across a plant.
“Although the proposed experiments will only be focused on pollination, the technology can be further adapted for many other precision agriculture applications,” Waterland said. “Toward the end of the project, we will identify and work with 17 commercial partners to transition the developed precision robotics technology into real productivity in the agriculture field.”
Consulting on the project are Aaron Dollar, associate professor of mechanical engineering and materials science at Yale University, and Bob McConnell, grower, with McConnell Berry Farm, in Independence.