Farms Fund
Robots to Replace Migrant Fruit Pickers
Wired
By Eliza Strickland
June 21, 2007
As if the debate over immigration and guest worker
programs wasn't complicated enough, now a couple of robots
are rolling into the middle of it.
Vision Robotics, a San Diego company, is working on a
pair of robots that would trundle through orchards plucking
oranges, apples or other fruit from the trees. In a few
years, troops of these machines could perform the tedious
and labor-intensive task of fruit picking that currently
employs thousands of migrant workers each season.
The robotic work has been funded entirely by agricultural
associations, and pushed forward by the uncertainty
surrounding the migrant labor force. Farmers are "very, very
nervous about the availability and cost of labor in the near
future," says Vision Robotics CEO Derek Morikawa.
It's a surprising new market for Vision Robotics, which
had been focused on developing consumer devices, including a
robotic vacuum cleaner to compete with iRobot's Roomba.
When a member of the California Citrus Research Board
approached the company in 2004, Morikawa was doubtful that
an effective robotic picker was even feasible. A citrus
grower brought the skeptical engineers to an orange farm in
California's fertile Central Valley, where they walked down
the neat rows of trees and stared at the oranges hanging in
the branches.
Previous attempts at making a mechanical harvester were
thwarted by inefficiency, explains Morikawa. In the past,
experimental machines approached a tree as a human would,
picking one piece of fruit and then looking for the next. In
this slow process, the machine circled the tree repeatedly
until it was sure it had picked all the fruit.
Morikawa says his engineers had their breakthrough idea
right there in the orange grove. They realized that the task
could be divided between two robots: One would locate all
the oranges, and the second would pick them. "Once you know
where all the fruit is, then it becomes an easy job to
calculate the most efficient way to pick it all," says
Morikawa.
But it wasn't just technological challenges that held
back previous attempts at building a mechanical harvester –-
politics got involved, too. Cesar Chavez, the legendary
leader of the United Farm Workers, began a campaign against
mechanization back in 1978.
Chavez was outraged that the federal government was
funding research and development on agricultural machines,
but not spending any money to aid the farm workers who would
be displaced. In the '80s, that simmering anger merged with
a growing realization that the technology was nowhere near
ready, and government funding dried up.
This time around, growers' associations are funding the
research. By the end of this year, the orange growers will
have invested almost $1 million in the project, says Ted
Baskin, president of the California Citrus Research Board.
He estimates that it will take about $5 million more to get
to the finished product.
The farmers are willing to pay up because they've been
rattled by a labor shortage over the past few years --
California growers tell horror stories of watching their
fruit rot on the trees as they waited for the picking crews
to arrive. Last fall, growers rallied in front of the U.S.
Capitol, frustrated that Congress still hadn't created a
program to ease the passage of foreign guest workers across
the Mexico border.
With the supply-and-demand equation uncertain, growers
see the robots as a better option. "You can predict what
it's going to cost to buy a machine and maintain it," says
Baskin. "You can't predict the bargaining that we go through
with contract labor," he says.
The two robots would work as a team: one an eagle-eyed
scout, the other a metallic octopus with a gentle touch. The
first robot will scan the tree and build a 3-D map of the
location and size of each orange, calculating the best order
in which to pick them. It sends that information to the
second robot, a harvester that will pick the tree clean,
following a planned sequence that keeps its eight long arms
from bumping into each other.
The Vision Robotics engineers are currently building the
scout. They expect to have a prototype ready next year, with
the harvester to follow two or three years later. Baskin
says he doesn't expect the mechanical systems to pose any
serious problems. The hard work is writing the software.
After the scout robot makes a 3-D map of the tree, it has to
evaluate each piece of fruit. What size is the orange? What
color is it? Does it have black spots on it? "It's a
question of gathering the information, and then judging
whether it meets the parameters that are equal to a good
orange," Baskin says.
Vision Robotics has been working on that problem for
almost four years now, which might give some reassurance to
human pickers. The United Farm Workers' leaders say they
aren't worried about the robots, because they don't believe
the machines will ever be able to do the job as well as
people. Spokesman Marc Grossman predicts that mechanical
hands will damage the fruit and make it unappealing for
supermarket shoppers. "There are already machines that will
pick wine grapes, but the high end wine growers don’t use
them, because they want the quality," Grossman says.
Farmers don't seem to share that concern. The Washington
Tree Fruit Commission started investing in the project last
year, and Vision Robotics is talking to other agricultural
groups with crops ranging from cherries to asparagus.