Effective Behavioural Dynamic Coupling through Echo State Networks
This work presents a novel approach and paradigm for the coupling of human and robot dynamics with respect to control. We present an adaptive system based on Reservoir Computing and Recurrent Neural Networks able to couple control signals and robotic behaviours. A supervised method is utilised for t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/9/7/1300 |
id |
doaj-3ea7d02ec46d45319c0524d15d1eb375 |
---|---|
record_format |
Article |
spelling |
doaj-3ea7d02ec46d45319c0524d15d1eb3752020-11-25T00:52:24ZengMDPI AGApplied Sciences2076-34172019-03-0197130010.3390/app9071300app9071300Effective Behavioural Dynamic Coupling through Echo State NetworksChristos Melidis0Davide Marocco1School of Computing, Electronics and Mathematics, Plymouth University, Drake Circus, Plymouth PL4 8AA, UKDipartimento di Studi Umanistici, University of Naples “Federico II”, via Porta di Massa 1, 80138 Naples, ItalyThis work presents a novel approach and paradigm for the coupling of human and robot dynamics with respect to control. We present an adaptive system based on Reservoir Computing and Recurrent Neural Networks able to couple control signals and robotic behaviours. A supervised method is utilised for the training of the network together with an unsupervised method for the adaptation of the reservoir. The proposed method is tested and analysed using a public dataset, a set of dynamic gestures and a group of users under a scenario of robot navigation. First, the architecture is benchmarked and placed among the state of the art. Second, based on our dataset we provide an analysis for key properties of the architecture. We test and provide analysis on the variability of the lengths of the trained patterns, propagation of geometrical properties of the input signal, handling of transitions by the architecture and recognition of partial input signals. Based on the user testing scenarios, we test how the architecture responds to real scenarios and users. In conclusion, the synergistic approach that we follow shows a way forward towards human in-the-loop systems and the evidence provided establish its competitiveness with available methods, while the key properties analysed the merits of the approach to the commonly used ones. Finally, reflective remarks on the applicability and usage in other fields are discussed.https://www.mdpi.com/2076-3417/9/7/1300dynamic neural networksmobile robot navigationgesture recognitionbehaviour dynamicsreal-time action recognition |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Christos Melidis Davide Marocco |
spellingShingle |
Christos Melidis Davide Marocco Effective Behavioural Dynamic Coupling through Echo State Networks Applied Sciences dynamic neural networks mobile robot navigation gesture recognition behaviour dynamics real-time action recognition |
author_facet |
Christos Melidis Davide Marocco |
author_sort |
Christos Melidis |
title |
Effective Behavioural Dynamic Coupling through Echo State Networks |
title_short |
Effective Behavioural Dynamic Coupling through Echo State Networks |
title_full |
Effective Behavioural Dynamic Coupling through Echo State Networks |
title_fullStr |
Effective Behavioural Dynamic Coupling through Echo State Networks |
title_full_unstemmed |
Effective Behavioural Dynamic Coupling through Echo State Networks |
title_sort |
effective behavioural dynamic coupling through echo state networks |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2019-03-01 |
description |
This work presents a novel approach and paradigm for the coupling of human and robot dynamics with respect to control. We present an adaptive system based on Reservoir Computing and Recurrent Neural Networks able to couple control signals and robotic behaviours. A supervised method is utilised for the training of the network together with an unsupervised method for the adaptation of the reservoir. The proposed method is tested and analysed using a public dataset, a set of dynamic gestures and a group of users under a scenario of robot navigation. First, the architecture is benchmarked and placed among the state of the art. Second, based on our dataset we provide an analysis for key properties of the architecture. We test and provide analysis on the variability of the lengths of the trained patterns, propagation of geometrical properties of the input signal, handling of transitions by the architecture and recognition of partial input signals. Based on the user testing scenarios, we test how the architecture responds to real scenarios and users. In conclusion, the synergistic approach that we follow shows a way forward towards human in-the-loop systems and the evidence provided establish its competitiveness with available methods, while the key properties analysed the merits of the approach to the commonly used ones. Finally, reflective remarks on the applicability and usage in other fields are discussed. |
topic |
dynamic neural networks mobile robot navigation gesture recognition behaviour dynamics real-time action recognition |
url |
https://www.mdpi.com/2076-3417/9/7/1300 |
work_keys_str_mv |
AT christosmelidis effectivebehaviouraldynamiccouplingthroughechostatenetworks AT davidemarocco effectivebehaviouraldynamiccouplingthroughechostatenetworks |
_version_ |
1725242555727085568 |