File photo: Apples are seen on a tree at Stocks Farm which employs migrant workers to help harvest the fruit, in Suckley, Britain October 10, 2016. (REUTERS/Eddie Keogh)
Few things are American than apple pie, and a new technique that utilizes machines and technology has set out to make apple harvesting more efficient and less daunting on humans.
Techcrunch reports that Abundant Robotics, a Hayward, Calif.-based company, began working with the apple industry about four years ago. Though plentiful, when apples are being picked, they risk damage in the form of punctured skins or bruises, which can potentially render the fruit useless on the market. Because of this, harvesting apples through automation is not an easy feat.
The machines compensate for the fruit’s specific handling requirements by using computer vision to identify apples that are ready to be picked while still on the branch. Once an apple is ready, the machines use a vacuum-like apparatus to pick them instead of using a claw or a hand-like grasper. The robots can be recharged by being plugged into tractors.
The machines have been testing in orchards in the United States and Australia and are able to work around the clock, picking ripened apples day and night.
THESE ROBOTS AT MIT CAN TEACH ONE ANOTHER
Co-founded by Steve Steere, Curt Salisbury and Michael Erkisen, Abundant Robotics was organized about a year ago after the team identified the agriculture space presented a promising market opportunity. Prior to founding the company, the team worked on harvesting automation research funded by SRI and non-dilutive grants from the Washington Tree Fruit commission, according to Techcrunch.
SRI Ventures is an arm of SRI International, a non-profit research organization. Techcrunch describes SRI Ventures as a “kind of startup incubator.” In 2016, SRI spun out several companies including Superflex, “a full-body suit filled with soft muscle-like actuators that detect your movements and give them a boost,” according to Techcrunch.
SRI Ventures President Manish Kothari told Techcrunch that without the recent developments in computer vision and image processing, automation of apple picking would not be possible. “You direct this robot to go someplace, see and pick an apple, and go again. It’s a very nontrivial engineering challenge,” he said. “To detect apples very precisely you have to see down at the millimeter level in real time. That requires software, and on the hardware side, chips that allow you to do real time image processing on the fly.”
Techcrunch further reported that Apples are the second-most consumed fruit in the US and farmers produce over 9 billion pounds of apples domestically, according to the USDA. Notably, 2.3 billion pounds were exported in 2014-2015 and international consumption is growing.
Going forward, Abundant Robotics plans to produce its automated robotic apple pickers with machines that can work in orchards within two years. The company will also grow its eight person team, which is currently based at SRI in Menlo Park, Calif.
Abundant Robotics and SRI Ventures have not responded to Fox News' request for comment on the project.
Get a daily look at what’s developing in science and technology throughout the world.