July 23, 2015      

Where?s the robot for this job?

Next time you nip out to your local supermarket take a quick look at the fruit section, especially the multiple varieties of apples all neatly arranged and awaiting your purchase.

Hard to believe, but each apple was handpicked by someone, most times standing on a ladder and tossing the apples into a sack each is wearing. That?s work.

The State of Washington, according to its Department of Agriculture, produces 68 percent of all apples harvested for fresh consumption in the U.S., which means that nearly seven of every ten apples in your supermarket?s fruit section come from Washington.

U.S. total apple production of 263 million 42-pound cartons, represents only 6 percent of global output. By comparison, China?s 2014 apple crop was 54 percent of world production.

Washington?s annual crop is between 10 – 12 billion apples; all are handpicked, and all harvested in less than four months (from mid-August to mid-November).

Again, worldwide nearly all apples are picked by hand and harvested in a time-constrained harvest season.

Fast and gentle is key

Testing of a robotic apple picker may occur this fall by Washington State University engineers and scientists, which could help with labor shortages and save growers a lot in labor costs.

Prototype engineered, built and tested by Washington State University?s (WSU) Center for Precision & Automated Agricultural Systems.

?Engineers and scientists hope to test a robotic apple picker this fall that is able to pick apples fast and gently enough to make it economically viable,? reports the university?s WSU News.

The university received a grant from the National Robotics Initiative (U.S. Department of Agriculture) for $548,000 awarded in 2013, and now has built a prototype apple-picking robot that will be tested out in the upcoming harvest season.

marjoe and robot hand

?Unlike factories and other industrial applications, apples require a system that is delicate enough to pick the fruit without bruising it, while also maneuvering around tree branches, leaves and other obstructions,? said Manoj Karkee, principal investigator on the project and WSU assistant professor of biological systems engineering.

?That?s why it is more challenging and difficult compared to the robotics we have in industrial applications,? he said. ?It does not mean we cannot learn from what we have seen or known in the industrial environment, but it takes much more creative solutions to make it happen in orchards.?

Karkee is working with project co-investigators Qin Zhang, CPAAS director, and Karen Lewis, WSU regional tree fruit specialist, to approximate how the robot should move and manipulate to be most efficient and cause the least damage to the fruit and tree.

A 3D printer makes a part for an apple-picking robot.

Working with Changki Mo, assistant professor of mechanical engineering at WSU Tri-Cities, the team is focusing on the complementary nature of robots and humans to complete the apple-picking system.

?We are trying to use some level of human assistance in a co-robotic environment,? Karkee said. ?The robot would do about 95 to 98 percent of the job, but the remaining 2 percent would be done in assistance by a human operator. That makes it, at least in my opinion, possible to see the level of accuracy and productivity that we need to achieve.?

The robot features an arm and ?hand? in which eight motors operate in congruence with a vision system to delicately grasp and twist the fruit off the tree as a human does.

The robot?s vision system incorporates cameras and sensors to capture an image of the tree. Using algorithms to identify color, shape and texture, it differentiates fruit from the rest of the plant and determines fruit location so the robotic arm can be directed for picking.

Hope for the future

?This is one of the most challenging problems that scientists and agricultural engineers are dealing with right now,? he said. ?Based on what we know, it is really promising. We really think we have something.?

He said if they succeed in creating an apple-picking robot, it could potentially save growers millions in Washington?s multibillion dollar apple industry.

?(Apple picking) is labor intensive, costly, risky; there are not enough laborers to do it and it is seasonal,? he said. ?All of these factors encourage us to develop a machine. These are recognized problems that farmers, local bodies and the federal government are all trying to solve. We hope to be the solution to that problem.?

Karkee said he is pleased with the progress that?s been made and optimistic that a prototype could be commercialized in the near future.