Cargando…

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Eoh, Gyuho, Park, Tae-Hyoung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309906/
https://www.ncbi.nlm.nih.gov/pubmed/34300518
http://dx.doi.org/10.3390/s21144780
_version_ 1783728633386369024
author Eoh, Gyuho
Park, Tae-Hyoung
author_facet Eoh, Gyuho
Park, Tae-Hyoung
author_sort Eoh, Gyuho
collection PubMed
description This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportation techniques have been proposed, which showed improved performance without precise controller design. However, DRL-based techniques not only take a long time to learn their policies but also sometimes fail to learn. It is difficult to learn the policy of DRL by random actions only. Therefore, we propose two curricula for the efficient learning of object transportation: region-growing and single- to multi-robot. During the learning process, the region-growing curriculum gradually extended to a region in which an object was initialized. This step-by-step learning raised the success probability of object transportation by restricting the working area. Multiple robots could easily learn a new policy by exploiting the pre-trained policy of a single robot. This single- to multi-robot curriculum can help robots to learn a transporting method with trial and error. Simulation results are presented to verify the proposed techniques.
format Online
Article
Text
id pubmed-8309906
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83099062021-07-25 Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning Eoh, Gyuho Park, Tae-Hyoung Sensors (Basel) Article This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportation techniques have been proposed, which showed improved performance without precise controller design. However, DRL-based techniques not only take a long time to learn their policies but also sometimes fail to learn. It is difficult to learn the policy of DRL by random actions only. Therefore, we propose two curricula for the efficient learning of object transportation: region-growing and single- to multi-robot. During the learning process, the region-growing curriculum gradually extended to a region in which an object was initialized. This step-by-step learning raised the success probability of object transportation by restricting the working area. Multiple robots could easily learn a new policy by exploiting the pre-trained policy of a single robot. This single- to multi-robot curriculum can help robots to learn a transporting method with trial and error. Simulation results are presented to verify the proposed techniques. MDPI 2021-07-13 /pmc/articles/PMC8309906/ /pubmed/34300518 http://dx.doi.org/10.3390/s21144780 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Eoh, Gyuho
Park, Tae-Hyoung
Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title_full Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title_fullStr Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title_full_unstemmed Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title_short Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning
title_sort cooperative object transportation using curriculum-based deep reinforcement learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309906/
https://www.ncbi.nlm.nih.gov/pubmed/34300518
http://dx.doi.org/10.3390/s21144780
work_keys_str_mv AT eohgyuho cooperativeobjecttransportationusingcurriculumbaseddeepreinforcementlearning
AT parktaehyoung cooperativeobjecttransportationusingcurriculumbaseddeepreinforcementlearning