Arkansas Researchers Develop Robotic Chicken Gripper

ChicGrasp uses imitation learning to handle poultry processing with 81% success rate

Published on Mar. 11, 2026

Got story updates? Submit your updates here. ›

Researchers at the University of Arkansas have developed a robotic gripper called ChicGrasp that can grasp and lift chicken carcasses using an advanced imitation learning algorithm. The system, which has shown an 81% success rate, aims to address labor shortages in poultry processing plants by automating the handling of delicate and irregularly-shaped chicken parts.

Why it matters

Automating poultry processing has been a challenge due to the unpredictable nature of chicken carcasses, which can vary in size and position. ChicGrasp's use of imitation learning to mimic human movements represents a novel approach to agricultural robotics that could help address labor shortages in the industry.

The details

The ChicGrasp system uses 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. The researchers used an advanced imitation learning algorithm called "diffusion policy" that allows the robot to learn from human movements rather than relying on pre-programmed scripts. This makes the system more adaptable to the unpredictable conditions of a poultry processing line. While ChicGrasp has shown an 81% success rate, the researchers note that speed is still a challenge, with the full cycle taking about 38 seconds compared to 3 seconds for a human.

  • The ChicGrasp project has been supported by a $1 million grant from a joint program between the USDA's National Institute of Food and Agriculture and the National Science Foundation.
  • Results of the study behind the development of ChicGrasp were published in Advanced Robotics Research in 2026.

The players

Dongyi Wang

Leader of the ChicGrasp project and an assistant professor in the departments of biological and agricultural engineering and food science at the University of Arkansas.

Amirreza Davar

A graduate student in the departments of mechanical engineering and biological and agricultural engineering at the University of Arkansas, who designed the gripper and modified the imitation learning algorithm for the ChicGrasp system.

University of Arkansas System Division of Agriculture

The research arm of the University of Arkansas System, which has supported the development of the ChicGrasp robotic gripper.

Got photos? Submit your photos here. ›

What they’re saying

“Embodied AI is used to create intelligent, agent-like robotics to interact with a real-world environment. 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. We are trying to do similar things using that imitation learning idea, but in chicken processing.”

— Dongyi Wang, Assistant Professor (miragenews.com)

“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. It's more efficient and more accurate. From the get-go, the robot knows what we need to do.”

— Amirreza Davar, Graduate Student (miragenews.com)

What’s next

The researchers plan to continue working on improving the speed and efficiency of the ChicGrasp system to make it more viable for industrial use in poultry processing plants.

The takeaway

The development of ChicGrasp demonstrates the potential of imitation learning and advanced robotics to automate tasks in the agricultural industry, particularly in areas like poultry processing where labor shortages have been a persistent challenge.