Modeling of Soft Pneumatic Actuators with Different Orientation Angles Using Echo State Networks for Irregular Time Series Data.

Ahmed G Radwan,Mennaallah Soliman,Mahmood A Saleh,Mahmoud Elsamanty,Mostafa A Mousa,Samuel M Youssef

doi:10.3390/mi13020216

Ahmed G Radwan, Mennaallah Soliman + Show 4 more

Open Access

https://doi.org/10.3390/mi13020216

Copy DOI

Journal: Micromachines	Publication Date: Jan 29, 2022
Citations: 6	License type: CC BY 4.0

Affiliation: Nile University, Cairo University, Benha University

Abstract

Modeling of soft robotics systems proves to be an extremely difficult task, due to the large deformation of the soft materials used to make such robots. Reliable and accurate models are necessary for the control task of these soft robots. In this paper, a data-driven approach using machine learning is presented to model the kinematics of Soft Pneumatic Actuators (SPAs). An Echo State Network (ESN) architecture is used to predict the SPA’s tip position in 3 axes. Initially, data from actual 3D printed SPAs is obtained to build a training dataset for the network. Irregular-intervals pressure inputs are used to drive the SPA in different actuation sequences. The network is then iteratively trained and optimized. The demonstrated method is shown to successfully model the complex non-linear behavior of the SPA, using only the control input without any feedback sensory data as additional input to the network. In addition, the ability of the network to estimate the kinematics of SPAs with different orientation angles is achieved. The ESN is compared to a Long Short-Term Memory (LSTM) network that is trained on the interpolated experimental data. Both networks are then tested on Finite Element Analysis (FEA) data for other angle SPAs not included in the training data. This methodology could offer a general approach to modeling SPAs with varying design parameters.

Highlights

The use of soft materials has recently gained traction in robotics and the field of soft robotics has seen many developments
One of the main hurdles of building soft robots is the complex non-linear dynamics they exhibit due to the compliant nature of the soft materials used to build them [2]
We used the Echo State Network (ESN), which is based on the concept of Reservoir Computing (RC), and compared its results with the Long Short-Term Memory (LSTM) network, which is one of the most promising networks used with time series data

Summary

Introduction

The use of soft materials has recently gained traction in robotics and the field of soft robotics has seen many developments. The main reason for this is the advantages gained by using soft materials instead of building completely rigid robots, the main advantage being the high flexibility that could be achieved by soft robots. One of the main hurdles of building soft robots is the complex non-linear dynamics they exhibit due to the compliant nature of the soft materials used to build them [2]. These complex dynamics are hard to model, and subsequently are very challenging to Micromachines 2022, 13, 216.

Methods

Results

Conclusion