By Curt Harler
Angela Ribeiro and Pablo Gonzalez-de-Santos, at the Center for
Automation and Robotics (CSIC-UPM) spoke about the promising future for
robot fleets used for weed control during the International Annual
Meetings of the American Society of Agronomy (ASA), Crop Science Society
of America (CSSA), and Soil Science Society of America (SSSA). The
meetings was held in Cincinnati on Oct. 21-24.
Frits K. Van Evert and a team from the Wageningen University and
Research Centre in the Netherlands will talk about real-time detection
and control of weeds. Closer to home, David Hearn of Towson University,
near Baltimore, is working on the use of computational shape analysis
and identification keys to identify plants from digital images.David
Jacobs, University of Maryland, teamed with researchers from Columbia
University and the Smithsonian Institution towards similar ends with a
free app called Leafsnap. In its first iteration, it IDs trees but other
plants – including pesky weeds — should follow quickly.
While some of the initial robot-based weed identification and control
work is being done in field crops, the research should port nicely to
turfgrass. The symposium will feature engineers and biologists who are
working in the cutting edge field of sensor development and automation
for real-time plant identification. The technology boom is
revolutionizing management aspects of both crop and non-crop systems,
including advanced target recognition and application systems.
Superintendents will soon have a plant identification monitor sitting
next to their soil moisture and nutrient monitors in their utility
vehicle. Both on golf courses and in natural areas, managers and
conservationists will be able to identify invasive and other important
plant species using identification technology that is also equipped with
communication and environmental monitoring devices.
Now, if only we can get those robots to bring donuts for the rest of the grounds staff, we just might be good with that!