Pose estimation and bin picking for deformable products
This addresses the challenge of handling variable and deformable natural foods in agricultural and food domains, which is incremental as it adapts existing methods to a specific application.
The paper tackled the problem of robotic bin picking and pose estimation for deformable poultry products, achieving high accuracy in real-world experiments.
Robotic systems in manufacturing applications commonly assume known object geometry and appearance. This simplifies the task for the 3D perception algorithms and allows the manipulation to be more deterministic. However, those approaches are not easily transferable to the agricultural and food domains due to the variability and deformability of natural food. We demonstrate an approach applied to poultry products that allows picking up a whole chicken from an unordered bin using a suction cup gripper, estimating its pose using a Deep Learning approach, and placing it in a canonical orientation where it can be further processed. Our robotic system was experimentally evaluated and is able to generalize to object variations and achieves high accuracy on bin picking and pose estimation tasks in a real-world environment.