American Researchers test robotic arm for sorting fresh onions

During the pandemic, labour problems became acute on many farms in Georgia and across the country. Farms once staffed by humans to bring produce from the field to stores for purchase were suddenly short-staffed, and the global supply chain was severely impacted.

A team of researchers led by School of Computing Professor Prashant Doshi is now designing collaborative robots to mitigate some of these potential challenges. Working with the University of Georgia’s Vidalia Onion and Vegetable Research Center, a unit of the College of Agricultural and Environmental Sciences, and A&M Farms in Lyons, Georgia, they have tested the robotic arm.

The project has shown good progress in a task known as ‘pick-inspect-place’. Robots in agriculture or manufacturing have long been involved in picking and placing tasks. But in this case, the researchers use computer vision for the element of inspecting as well. The researchers use a robotic arm with cameras for the AI trained system.

A very tedious kind of job

The researchers are working to deploy robotic assistants in Georgia farm packing sheds, to help sort produce like onions. “The AI model will basically inspect the onions, and detect whether those onions are blemished or not”, Professor Doshi explains. “If the onions are blemished, then the robotic arm will remove them from the conveyor.”

“Currently, if you visit any packing shed in Georgia, you know how much of the sortation is done by human labour. It’s a manual very tedious kind of job. It involves doing the same thing over and over again. It can get quite boring. So, I think it would be amazing if the farmers or the packing shed owners have the option of deploying robotic automation at this really basic level.”

According to Prasanth Suresh, a doctoral student on the project, the system uses basically two AI models. “There’s one that teaches the robot the behaviour and one that detects the object using vision. The second AI model will detect the object and instruct the proper behaviour. This combination helps the system to inspect the onions for blemishes, so blemished onions can be thrown in the waste.”

Providing options

The technology can also be used for sorting other fruit and vegetables, Professor Doshi says. The idea, he emphasises, is not to eliminate these professions for human workers, but to provide options, protect the job from labour shortages and to upskill workers into positions that require less strenuous conditions.

“Often, these workers work through high heat, dust, or other conditions”, he says. “We are not trying to replace this worker. AI has suffered from a little bit of a perception issue. If you ask core AI researchers, their goal is not necessarily to design AI that acts like a human, but to design rational agents that act optimally given the knowledge they have.” Suresh and Doshi are joined by doctoral student Ehsan Asali on the project.