Estimating Forces of Robotic Pouring Using a LSTM RNN

TL;DR

This paper explores using an LSTM RNN to estimate the forces involved in robotic pouring by analyzing sequential data, aiming to enhance AI's ability to understand and predict system dynamics.

Contribution

It demonstrates the application of LSTM RNNs for estimating system dynamics from sequential data in robotic pouring tasks, including data preprocessing and network architecture design.

Findings

LSTM RNN effectively estimates pouring forces from sequential data.

The study discusses data preprocessing and network architecture improvements.

Results support LSTM's potential in robotic dynamic estimation.

Abstract

In machine learning, it is very important for a robot to be able to estimate dynamics from sequences of input data. This problem can be solved using a recurrent neural network. In this paper, we will discuss the preprocessing of 10 states of the dataset, then the use of a LSTM recurrent neural network to estimate one output state (dynamics) from the other 9 input states. We will discuss the architecture of the recurrent neural network, the data collection and preprocessing, the loss function, the results of the test data, and the discussion of changes that could improve the network. The results of this paper will be used for artificial intelligence research and identify the capabilities of a LSTM recurrent neural network architecture to estimate dynamics of a system.