GTRI

Case Study

Missing Link: Augmented Reality Technology May Bridge Communication Gap in Poultry Processing Plants

Published: July 14, 2005


Click for article gallery (3 images).

Technology that transfers computer-generated information onto the physical world is being tested for use in poultry plants to improve communication between computers and workers.

Using augmented reality (AR) technology, researchers have designed two systems that project graphical instructions from an automated inspection system onto birds on a processing line. These symbols tell workers how to trim or whether to discard defective products.

Right now, inspection is done visually by human screeners, who communicate instructions to trimmers using gestures. But an automated inspection system developed and field tested by the Georgia Tech Research Institute (GTRI) is being commercialized, and poultry plant officials are likely to implement the technology in the near term, said J. Craig Wyvill, head of the GTRI Food Technology Processing Division.

"When that happens, the industry will need an efficient way to link communication from the imaging system to the trimmers," Wyvill noted.

So in a project funded by GTRI's state-supported Agricultural Technology Research Program, GTRI researchers are collaborating with experts in the Georgia Tech College of Computing to use AR technology in poultry plants. AR applications have been successfully demonstrated in industrial assembly and inspection, as well as the medical field.

"It's easy to see this technology working in a poultry plant," said Blair Macintyre, an assistant professor in the Georgia Tech College of Computing and augmented reality (AR) expert. "The question is, ‘What is the best implementation of the technology to satisfy the environmental constraints?'"

Researchers have had to consider that poultry processing plants are typically wet and slippery and have to be thoroughly washed down with high-pressured water streams daily. Also, trimmers need simple, graphical instructions and must have their hands free of any object except a knife for cutting defective bird parts.

Two AR solutions developed by Macintyre and colleagues Parth Bhawalkar, a College of Computing graduate student, and Simeon Harbert, a GTRI research engineer, address these requirements. Macintyre will describe them in a presentation on July 17 at the annual meeting of the American Society of Agricultural Engineers in Tampa, Fla.

The first approach uses a location-tracked, see-through, head-mounted display worn by a trimmer. It directly overlays graphical instructions on a trimmer's view of the birds.

A second solution uses a laser scanner, mounted in a fixed location near the processing line, to project graphical instructions directly onto each bird that requires some action, such as trimming. In this approach, the product, but not the user, must be tracked for the instructions to appear on the product.

"Each solution appears to have advantages and disadvantages," Macintyre said. One of the greatest benefits that both solutions provide is the potential for advance warning to trimmers of the workload coming down the line, he added. Current practices don't provide this advantage.

"But our suspicion is that the laser-based system is the more practical in the near term and potentially in the long term," Macintyre said. "The real disadvantage of the head-mounted system is its cost. Heads-up displays cost about $3,600, but they are getting cheaper. Two years ago, they cost about $7,000 each."

Researchers plan to conduct laboratory experiments this fall with the two proof-of-concept prototypes they have designed. Experiments are expected to uncover the potential benefits or drawbacks of each AR application.

"The experiments are designed to have the same task, cognitive and physical load as an actual trimmer would have," Macintyre noted. "We'll use students or employees as the trimmers in our experiment. If our results are compelling, then we'd like to test the technologies in a poultry plant with actual trimmers."

Researchers will likely choose one of the two solutions to develop further based on economics and logistics, Macintyre said.

It may be several years before the technology is commercially available, Wyvill noted. The typical technology development time is four to six years; this project has been under way for more than a year now.

"But once the poultry industry implements automated inspection systems, it will need this communication link," Wyvill added. "This is kind of like a chess game. We're well down the line on imaging and automation technology. But we need a communication system to get information to people who remain on the processing line."

Wyvill and the researchers have high expectations for the AR technologies. "We think these technologies have the potential to be better than current practices," Macintyre said. "But, two humans working together over time have learned to use non-verbal cues and have developed a smooth communication system. That will be hard to beat at some level.

"The big advantage of these technologies is that we'll be able to show the trimmers what is about to come down the line," he added. "Right now, they basically get little warning. If they know nothing is coming, they can take advantage of momentary lulls to do other tasks, such as cleaning up and sharpening their knives."