Arkansas team develops robot to handle poultry carcasses
Imitation-learning system mimics human movements in plants
12 March 2026
1 minute read
By: Researchers at the Arkansas Agricultural Experiment Station have developed a robotic system that can learn by imitating human movements to handle chickens on poultry processing lines, according to a news release from Arkansas State University.
The system, called ChicGrasp, uses an advanced imitation learning algorithm and camera perceptions to guide a dual-jaw robotic gripper with pinchers that can grasp a chicken carcass by the legs, lift it and hang it on a shackle conveyor for further processing.
The technology was initially developed in response to labour shortages in poultry processing plants during the COVID-19 pandemic.
"Embodied AI is used to create intelligent, agent-like robotics to interact with a real-world environment," said Dongyi Wang, leader of the project and an assistant professor in the Departments of Biological and Agricultural Engineering and Food Science.
"It's a physical art that has just developed in the past couple of years, which you see in things like full self-driving cars," he said. "We are trying to do similar things using that imitation learning idea, but in chicken processing."
The project has been supported by a $1 million grant from a joint program between the U.S. Department of Agriculture’s National Institute of Food and Agriculture and the National Science Foundation. Results of the study were published in Advanced Robotics Research, and the team released all design files, code and datasets as open source.
The researchers designed the system to address challenges faced by traditional robotics on poultry processing lines, where birds can be cold, slippery and irregular in size and posture.
"In imitation learning, the role of the human is to give a trajectory, give a ground truth to the robot, so we don't need to start from scratch to learn," said Amirreza Davar, a graduate student who designed the gripper and modified the learning system. "It's more efficient and more accurate. From the get-go, the robot knows what we need to do."
So far, ChicGrasp has demonstrated a success rate of nearly 81%. However, speed remains a challenge. While a human worker can hang a chicken carcass on a conveyor in about three seconds, the full cycle for ChicGrasp currently takes about 38 seconds.
The prototype system cost about $59,000 to build using off-the-shelf robotic arm hardware and 3D-printed components. Researchers said future work will focus on improving speed and refining the algorithm to move the technology closer to industrial use.
