The researchers claim it could produce multi-million dollar savings for food processors but add that it won’t be commercially available for at least a few years.
The Intelligent Cutting and Deboning System uses imaging technology and a robotic cutting arm to automatically debone chicken and other poultry products.
The system uses 3-D imaging and sensor-based cutting technology, which determines where to cut the bird to optimize yield and reduces the risk of bone fragments in the finished product because it gets a closure cut to the bone.
The researchers had to overcome the problem of each bird being a different size and shape, to ensure the automated deboning system could adapt to the individual bird.
They hope that by being able to test all possible cut geometries, a smaller and more simplified final system could be designed.
First test attempt
Gary McMurray, chief of GTRI's Food Processing Technology Division, told FoodProductionDaily.com that the project started in 2004 but this month will be the first attempt to integrate all of the technological components into a single test and determine the yield of the cut.
“The biggest problem with the current attempts to automate has been the various size birds. This is why they always go back to manual labour.
“For us, we can detect the difference size of the bird and construct a cutting trajectory that is designed for just that bird.
“Then, if they still cut incorrectly and run into the bone, we can guide the blade around the bone and complete the cut.”
The bird is mounted on a robot arm that allows alignment to any desired position. The robot arm places the bird under the vision system, and then it moves the bird with respect to the cutting robot.
McMurray said: “The impact of blade sharpness on the cut is something that we have not implemented (right now, we simply change the blade after every five-seven birds). We have some ideas on how to do it, we just have not had the time.”
Multi-million dollar savings
He added that the robot could produce multi-million dollar savings each year but it is several years away from being commercially ready.
“Dealing with a natural product is extremely difficult. We spent a lot of time modeling cutting of biomaterials in order to be able to interpret the force data that we were getting.
“There are many parameters that go into this: blade sharpness, angle of the blade relative to the meat, and speed of the cut as well as all of the material properties (biomaterials are incredibly non-linear and not well understood).”
When asked what happens if something goes wrong with the robot, McMurray said: “This is a very interesting topic actually. Our current thought is that it is best for the robot to simply flag any bird that it made a mistake on or could not cut.
“In those cases, manual backup could correct any situation. This is very common on deboning lines.”
The Intelligent Cutting and Deboning System research is funded by the state of Georgia through the Agricultural Technology Research Program at GTRI.