SliceIt!: Simulation Based Reinforcement Learning for Robotic Food Slicing

Teaching robots how to slice food ingredients is easier said than done. SliceIt! is a simulation based approach for training food slicing skills. The approach consists of:

collecting a small dataset of real food-cutting examples, then calibrating high-fidelity simulations of knife-food cutting interactions and robot motion control. Reinforcement learning agents are trained in this calibrated simulation environment to learn optimal compliance control policies that modulate knife forces.

Once the info is transferred to the robot, it will be able to perform food slicing tasks efficiently and safely.

[HT]