Pouring Dynamics Estimation Using Gated Recurrent Units

TL;DR

This paper introduces a deep learning approach using gated recurrent units to accurately estimate water volume changes during pouring, enhancing robotic manipulation precision.

Contribution

It presents a novel GRU-based model for water pouring estimation, with extensive evaluation and hyperparameter tuning for improved accuracy.

Findings

Achieved a validation mean squared error as low as 1e-4.

Demonstrated the effectiveness of GRU in pouring dynamics estimation.

Provided comprehensive analysis of recurrent neural network designs.

Abstract

One of the most commonly performed manipulation in a human's daily life is pouring. Many factors have an effect on target accuracy, including pouring velocity, rotation angle, geometric of the source, and the receiving containers. This paper presents an approach to increase the repeatability and accuracy of the robotic manipulator by estimating the change in the amount of water of the pouring cup to a sequence of pouring actions using multiple layers of the deep recurrent neural network, especially gated recurrent units (GRU). The proposed GRU model achieved a validation mean squared error as low as 1e-4 (lbf) for the predicted value of weight f(t). This paper contains a comprehensive evaluation and analysis of numerous experiments with various designs of recurrent neural networks and hyperparameters fine-tuning.