# Learning to Pour

## TL;DR

This paper introduces a neural network-based method for generating pouring trajectories using force feedback, trained on demonstrations, and validated through simulation showing generalization to unseen pouring characteristics.

## Contribution

It presents a novel force feedback-driven pouring trajectory generation approach utilizing recurrent neural networks trained on demonstration data.

## Key findings

- System generalizes to unseen pouring characteristics
- Force estimation system performs well in simulation
- Neural network effectively predicts pouring velocity

## Abstract

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.