Learning to Pour
This work addresses a specific robotic task in cooking scenarios, but it is incremental as it builds on existing methods with limited generalization.
The paper tackles the problem of generating pouring trajectories for robots by using force feedback from a cup to determine future pouring velocity, employing recurrent neural networks trained on collected demonstrations. The simulated experiments demonstrate that the system can generalize to a single unseen element of pouring characteristics.
Pouring is a simple task people perform daily. It is the second most frequently executed motion in cooking scenarios, after pick-and-place. We present a pouring trajectory generation approach, which uses force feedback from the cup to determine the future velocity of pouring. The approach uses recurrent neural networks as its building blocks. We collected the pouring demonstrations which we used for training. To test our approach in simulation, we also created and trained a force estimation system. The simulated experiments show that the system is able to generalize to single unseen element of the pouring characteristics.