The idea of an automated farm has probably been around since rural electrification started in the early 20th century. Replacing back-breaking labor with robots has an obvious appeal, but so far cheap labor in many countries and the insistence of agriculture on being so darn rural has made automation limited in application. Despite this, Salah Sukkarieh, Professor of Robotics and Intelligent Systems at the Faculty of Engineering and Information Technologies of the University of Sydney, is heading a team working on developing robotic systems for farms with the aim of turning Australia into the “food bowl” of Asia.
As has been the case for centuries, Asia needs food, but it lacks farmland. With its abundant arable land, Australia has the potential of profiting by meeting this need, but Australian labor costs are high, so automation has the potential to increase yields and improve efficiency by eliminating many manual tasks. The current project is more than just a mechanized farm with robots added. It’s an approach that involves developing intelligent machines that not only carry out manual tasks, but can observe their surroundings and assess situations.
Professor Sukkarieh’s team is testing the new automated systems at the Horticulture Australia regional center in Mildura. The first phase is the development of robots that can patrol orchards and gather data for a “comprehensive in-ground and out-of-ground model.”
"Traditionally it has been necessary for someone to actually walk through the orchard, taking and analyzing soil and other samples and making decisions on the health and yield quality of the plants," said Sukkarieh. "The devices we've developed can collect, analyze and present this information autonomously, so a major part of the farmer's job can be done automatically."
Next year, the team will start the second phase, which will see the technology applied to standard tractors to allow them to automatically carry out tasks like applying fertilizers and pesticides, watering, sweeping and mowing.
The third phase is to develop harvesting robots. "The devices we've developed already can identify each individual fruit on the tree and its degree of ripeness, which is about 80 percent of the job done. But being able to harvest them is our ultimate goal," he said.
Professor Sukkarieh believes that the first of these technologies will be commercially available in a couple of years.
Source: University of Sydney