Cargando…

Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot

We propose a neural learning approach for a humanoid exercise robot that can automatically analyze and correct physical exercises. Such an exercise robot should be able to train many different human partners over time and thus requires the ability for lifelong learning. To this end, we develop a mod...

Descripción completa

Detalles Bibliográficos
Autores principales: Duczek, Nicolas, Kerzel, Matthias, Allgeuer , Philipp, Wermter , Stefan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9585214/
https://www.ncbi.nlm.nih.gov/pubmed/36274912
http://dx.doi.org/10.3389/frobt.2022.669719
_version_ 1784813441534394368
author Duczek, Nicolas
Kerzel, Matthias
Allgeuer , Philipp
Wermter , Stefan
author_facet Duczek, Nicolas
Kerzel, Matthias
Allgeuer , Philipp
Wermter , Stefan
author_sort Duczek, Nicolas
collection PubMed
description We propose a neural learning approach for a humanoid exercise robot that can automatically analyze and correct physical exercises. Such an exercise robot should be able to train many different human partners over time and thus requires the ability for lifelong learning. To this end, we develop a modified Grow-When-Required (GWR) network with recurrent connections, episodic memory and a novel subnode mechanism for learning spatiotemporal relationships of body movements and poses. Once an exercise is successfully demonstrated, the information of pose and movement per frame is stored in the Subnode-GWR network. For every frame, the current pose and motion pair is compared against a predicted output of the GWR, allowing for feedback not only on the pose but also on the velocity of the motion. Since both the pose and motion depend on a user’s body morphology, the exercise demonstration by one individual cannot easily be used as a reference for further users. We allow the GWR to grow online with each further demonstration. The subnode mechanism ensures that exercise information for individual humans is stored and retrieved correctly and is not forgotten over time. In the application scenario, a physical exercise is performed in the presence of an expert like a physiotherapist and then used as a reference for a humanoid robot like Pepper to give feedback on further executions of the same exercise. For evaluation, we developed a new synthetic exercise dataset with virtual avatars. We also test our method on real-world data recorded in an office scenario. Overall, we claim that our novel GWR-based architecture can use a learned exercise reference for different body variations through incremental online learning while preventing catastrophic forgetting, enabling an engaging long-term human-robot experience with a humanoid robot.
format Online
Article
Text
id pubmed-9585214
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95852142022-10-22 Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot Duczek, Nicolas Kerzel, Matthias Allgeuer , Philipp Wermter , Stefan Front Robot AI Robotics and AI We propose a neural learning approach for a humanoid exercise robot that can automatically analyze and correct physical exercises. Such an exercise robot should be able to train many different human partners over time and thus requires the ability for lifelong learning. To this end, we develop a modified Grow-When-Required (GWR) network with recurrent connections, episodic memory and a novel subnode mechanism for learning spatiotemporal relationships of body movements and poses. Once an exercise is successfully demonstrated, the information of pose and movement per frame is stored in the Subnode-GWR network. For every frame, the current pose and motion pair is compared against a predicted output of the GWR, allowing for feedback not only on the pose but also on the velocity of the motion. Since both the pose and motion depend on a user’s body morphology, the exercise demonstration by one individual cannot easily be used as a reference for further users. We allow the GWR to grow online with each further demonstration. The subnode mechanism ensures that exercise information for individual humans is stored and retrieved correctly and is not forgotten over time. In the application scenario, a physical exercise is performed in the presence of an expert like a physiotherapist and then used as a reference for a humanoid robot like Pepper to give feedback on further executions of the same exercise. For evaluation, we developed a new synthetic exercise dataset with virtual avatars. We also test our method on real-world data recorded in an office scenario. Overall, we claim that our novel GWR-based architecture can use a learned exercise reference for different body variations through incremental online learning while preventing catastrophic forgetting, enabling an engaging long-term human-robot experience with a humanoid robot. Frontiers Media S.A. 2022-10-07 /pmc/articles/PMC9585214/ /pubmed/36274912 http://dx.doi.org/10.3389/frobt.2022.669719 Text en Copyright © 2022 Duczek, Kerzel, Allgeuer  and Wermter . https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Robotics and AI
Duczek, Nicolas
Kerzel, Matthias
Allgeuer , Philipp
Wermter , Stefan
Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title_full Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title_fullStr Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title_full_unstemmed Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title_short Self-organized Learning from Synthetic and Real-World Data for a Humanoid Exercise Robot
title_sort self-organized learning from synthetic and real-world data for a humanoid exercise robot
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9585214/
https://www.ncbi.nlm.nih.gov/pubmed/36274912
http://dx.doi.org/10.3389/frobt.2022.669719
work_keys_str_mv AT duczeknicolas selforganizedlearningfromsyntheticandrealworlddataforahumanoidexerciserobot
AT kerzelmatthias selforganizedlearningfromsyntheticandrealworlddataforahumanoidexerciserobot
AT allgeuerphilipp selforganizedlearningfromsyntheticandrealworlddataforahumanoidexerciserobot
AT wermterstefan selforganizedlearningfromsyntheticandrealworlddataforahumanoidexerciserobot