Using symmetries in reinforcement learning of bimanual robotic tasks

The learning of bimanual robotic tasks, i.e., tasks executed by two manipulators together, can be particularly important in the new scenarios opened by the rise of humanoid robotics, one of the most interesting trend currently in the field. The work presented wants to build a method to simplify the...

Descripción completa

Detalles Bibliográficos
Autor: Amadio, Fabio
Tipo de recurso: tesis de maestría
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/167695
Acceso en línea:https://hdl.handle.net/2117/167695
Access Level:acceso abierto
Palabra clave:Robots -- Programming
Robots -- Kinematics
Artificial arms
Robots -- Programació
Robots -- Cinemàtica
Braços artificials
id ES_46d7f340034e9b1fafe87e6aa9400a28
oai_identifier_str oai:upcommons.upc.edu:2117/167695
network_acronym_str ES
network_name_str España
repository_id_str
spelling Using symmetries in reinforcement learning of bimanual robotic tasksAmadio, FabioRobots -- ProgrammingRobots -- KinematicsArtificial armsRobots -- ProgramacióRobots -- CinemàticaBraços artificialsThe learning of bimanual robotic tasks, i.e., tasks executed by two manipulators together, can be particularly important in the new scenarios opened by the rise of humanoid robotics, one of the most interesting trend currently in the field. The work presented wants to build a method to simplify the dimensionality of parameter space in this particular context, exploiting the presence of symmetries between the movements executed by the two arms. The aim is to develop a reduced-order representation of the bimanual motion, with the purpose of increase the speed of learning process. In chapter 1, kinematics of the used robots is studied, in order to know how to correctly command the position of the robots while executing a task. Robotic movements are then modeled using Probabilistic Movement Primitives (ProMPs), a stochastic interpretation of robot movements (details in chapter 2). The first objective is to develop a symmetrization method for those kind of policies, and this part is treated in chapter 3. This will give the chance of representing the movement of two robotic arms, with only a single ProMP (instead of two, one for each arm), from which obtain the second policy applying symmetrization. In this way the amount of parameters representing motion can be halved. The most common kind of symmetry is the one defined by a plane, but also other cases can be explored, e.g., spherical or cylindrical symmetry. If the symmetry surface is not explicitly given in the bimanual task description, it is critical to have a reliable method to estimate it in order to exploit it in the learning process. In chapter 4 it is reported a way to obtain this estimation of the parameters describing the symmetry surface from the initially demonstrated trajectories. Finally, in chapter 5 it is defined a symmetric policy representation for bimanual task, that depends only on a single ProMP and a symmetry surface. The effectiveness of this parameter reduction has been tested applying it in reinforcement learning of some tasks, in comparison to the results obtained by the standard way of proceeding, that model the bimanual task with two separated ProMPs, one for each robotic arm.Universitat Politècnica de CatalunyaColomé Figueras, AdriàSerra, Maria20182018-06-2120192019-08-26master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/167695reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2http://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1676952026-05-27T15:37:01Z
dc.title.none.fl_str_mv Using symmetries in reinforcement learning of bimanual robotic tasks
title Using symmetries in reinforcement learning of bimanual robotic tasks
spellingShingle Using symmetries in reinforcement learning of bimanual robotic tasks
Amadio, Fabio
Robots -- Programming
Robots -- Kinematics
Artificial arms
Robots -- Programació
Robots -- Cinemàtica
Braços artificials
title_short Using symmetries in reinforcement learning of bimanual robotic tasks
title_full Using symmetries in reinforcement learning of bimanual robotic tasks
title_fullStr Using symmetries in reinforcement learning of bimanual robotic tasks
title_full_unstemmed Using symmetries in reinforcement learning of bimanual robotic tasks
title_sort Using symmetries in reinforcement learning of bimanual robotic tasks
dc.creator.none.fl_str_mv Amadio, Fabio
author Amadio, Fabio
author_facet Amadio, Fabio
author_role author
dc.contributor.none.fl_str_mv Colomé Figueras, Adrià
Serra, Maria
dc.subject.none.fl_str_mv Robots -- Programming
Robots -- Kinematics
Artificial arms
Robots -- Programació
Robots -- Cinemàtica
Braços artificials
topic Robots -- Programming
Robots -- Kinematics
Artificial arms
Robots -- Programació
Robots -- Cinemàtica
Braços artificials
description The learning of bimanual robotic tasks, i.e., tasks executed by two manipulators together, can be particularly important in the new scenarios opened by the rise of humanoid robotics, one of the most interesting trend currently in the field. The work presented wants to build a method to simplify the dimensionality of parameter space in this particular context, exploiting the presence of symmetries between the movements executed by the two arms. The aim is to develop a reduced-order representation of the bimanual motion, with the purpose of increase the speed of learning process. In chapter 1, kinematics of the used robots is studied, in order to know how to correctly command the position of the robots while executing a task. Robotic movements are then modeled using Probabilistic Movement Primitives (ProMPs), a stochastic interpretation of robot movements (details in chapter 2). The first objective is to develop a symmetrization method for those kind of policies, and this part is treated in chapter 3. This will give the chance of representing the movement of two robotic arms, with only a single ProMP (instead of two, one for each arm), from which obtain the second policy applying symmetrization. In this way the amount of parameters representing motion can be halved. The most common kind of symmetry is the one defined by a plane, but also other cases can be explored, e.g., spherical or cylindrical symmetry. If the symmetry surface is not explicitly given in the bimanual task description, it is critical to have a reliable method to estimate it in order to exploit it in the learning process. In chapter 4 it is reported a way to obtain this estimation of the parameters describing the symmetry surface from the initially demonstrated trajectories. Finally, in chapter 5 it is defined a symmetric policy representation for bimanual task, that depends only on a single ProMP and a symmetry surface. The effectiveness of this parameter reduction has been tested applying it in reinforcement learning of some tasks, in comparison to the results obtained by the standard way of proceeding, that model the bimanual task with two separated ProMPs, one for each robotic arm.
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-06-21
2019
2019-08-26
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/167695
url https://hdl.handle.net/2117/167695
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407255109042176
score 15.300724