Robotic Bin-Picking Pipeline for Chicken Fillets with Deep Learning- Based Instance Segmentation using Synthetic Data

In the food processing industry, automation is getting more common for purposes such as increased food quality and compensation for worker shortages. An automation task such as gripping is challenging due to the deformation of the objects. Additionally, in order to manipulate food in a specific manner, it is important to know the location and orientation of the food object. Due to these deformation and location problems, automation of tasks such as bin-picking food objects is a difficult challenge.

In this research, we present a robotic pipeline for the bin-picking of chicken fillets. The individual chicken fillets are detected using instance segmentation via deep learning. The instance segmentation model is trained on synthetically rendered images of chicken fillets. Current methods for synthetic data generation only use rigid body simulations, whereas we also simulate the deforming physics on manually created 3D models.

Additionally, the path planning is based on a 3D reconstructed environment, using depth data from an RGB-D camera. We show that automation of bin-picking for chicken fillets using synthetic data is a realistic prospect.