Agriculture ripe for change with robot farmhands

Farmers across the developed world did away with the backbreaking part of the work during the 19th century with the introduction of equipment like tractors and combines. Now, evolving technology is poised to make industrial agriculture greener and more efficient with the use of robots.

This tractor is fitted with a laser perception pod on top of its cab and a control system so it can navigate orchards autonomously (Credit: CMU/Tony Stenz)

It's a real possibility according to Tony Stentz, an engineer at Carnegie Mellon University's robotics institute. He recently told New Scientist three reasons why: first, mobile robots have now proved able to cope with complex outdoor environments; second, the price of production has fallen; and, finally, society should now see robot laborers as a benefit not a curse. (As for his last point, automating seasonal farmhand work is one thing, but the thought of unmanned tractors navigating a field is another as it may have some old-fashioned tractor operators up in arms.)

The technology that allows for mobile robots to find their way across unfamiliar, changing terrain such as groves of trees has its roots in DARPA autonomous car events. And the groundwork for a vision-based algorithm that guides a harvester by tracking the line between cut and uncut crop with a 3D laser ranging scanner, was developed over a decade ago by Stentz and his team.

Now, Stentz and Carnegie Mellon colleague Sanjiv Singh are working towards robots that can read a crop like a pro. To accomplish this, writes New Scientist, they're experimenting with sending autonomous mobile robots along the rows of a Florida orange grove and have the same scanner used for navigation capture detailed measurements of every tree's foliage and even count the oranges they bear. They're also gathering laser-ranging data in apple orchards in Pennsylvania. The article mentions that Singh has also modified an orchard platform – a vehicle that drives along lines of trees carrying workers aloft to reach high fruit – to drive without a human operator.

"Specialty crops like citrus, apples and other fruit trees have the most to gain from automation because they have not seen the same improvements in efficiency as other crops," Sing told New Scientist.

The tree-reading robots can also make for the smarter use of chemical sprays since the machines could record data more often and more thoroughly than humans.  "Instead of spraying at one constant rate, we can use [a robot-built] map to work out how to put down the minimal amount of chemical," Stentz said.

Additionally, the laser-based navigation system can be used at night when insects are active and winds are less strong, an ideal condition for the use of pesticides.

Such smart automation can save farmer's money and precision application of chemicals will minimize environmental damage and harm to field workers. It is unclear, however, how long it would take for widespread commercialization of the robots once introduced.