Reinforcement learning for complex and dynamic manipulation tasks

Being able to teach complex capabilities, such as opening a dishwasher, to robotic manipulators is a very challenging task, which is often tackled using raw programming. This is an attrac- tive technique for tasks under controlled environments, where variables like relative positions or physical pro...

Descripción completa

Detalles Bibliográficos
Autor: Boix Granell, Arnau
Tipo de recurso: tesis de maestría
Fecha de publicación:2025
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:2117/428855
Acceso en línea:https://hdl.handle.net/2117/428855
Access Level:acceso abierto
Palabra clave:Reinforcement learning
Algorithms
Manipulators (Mechanism)
Aprenentatge per reforç
Algorismes
Manipuladors (Mecanismes)
Àrees temàtiques de la UPC::Informàtica::Robòtica
id ES_d07c80fcbce87a72be4e259ecb661ff1
oai_identifier_str oai:upcommons.upc.edu:2117/428855
network_acronym_str ES
network_name_str España
repository_id_str
spelling Reinforcement learning for complex and dynamic manipulation tasksBoix Granell, ArnauReinforcement learningAlgorithmsManipulators (Mechanism)Aprenentatge per reforçAlgorismesManipuladors (Mecanismes)Àrees temàtiques de la UPC::Informàtica::RobòticaBeing able to teach complex capabilities, such as opening a dishwasher, to robotic manipulators is a very challenging task, which is often tackled using raw programming. This is an attrac- tive technique for tasks under controlled environments, where variables like relative positions or physical properties are known and constant between tasks. On the other hand, its perfor- mance degrades in more uncontrolled environments, leading to reduced repeatability and suc- cess rates. Not only that but for some cases not even raw programming is feasible. In this thesis, NVIDIA’s advanced simulation tools, IsaacSim and IsaacLab, are used to create a novel framework that allows the training of reinforcement learning (RL) agents to develop some complex and dynamic manipulation tasks. With the objective of gaining familiarity with the software and iteratively enhance the simula- tion parameters, the framework is first used to explore some basic tasks. Through these pre- liminary tasks, fundamental RL principles were established, gaining insight to create more ad- vanced environments. Not only that but the thesis also explores ways to reduce the simulation to reality (Sim2Real) gap, a critical barrier to deploying simulation-trained models in the real world. Later, some of the studied techniques are used to upgrade the developed framework. The created environment is later used to train a Franka Emika Panda manipulator to open a dish- washer door under a simulated environment. Finally, a connection between simulation and reality is established using ROS2, and put to the test by trying to reproduce one of the simpler trained tasks in a real manipulator.Universitat Politècnica de CatalunyaGarcía Hidalgo, NéstorRosell Gratacòs, Jan20252025-01-3120252025-05-06master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/x-rar-compressedapplication/x-rar-compressedapplication/pdfhttps://hdl.handle.net/2117/428855reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4288552026-05-27T15:37:01Z
dc.title.none.fl_str_mv Reinforcement learning for complex and dynamic manipulation tasks
title Reinforcement learning for complex and dynamic manipulation tasks
spellingShingle Reinforcement learning for complex and dynamic manipulation tasks
Boix Granell, Arnau
Reinforcement learning
Algorithms
Manipulators (Mechanism)
Aprenentatge per reforç
Algorismes
Manipuladors (Mecanismes)
Àrees temàtiques de la UPC::Informàtica::Robòtica
title_short Reinforcement learning for complex and dynamic manipulation tasks
title_full Reinforcement learning for complex and dynamic manipulation tasks
title_fullStr Reinforcement learning for complex and dynamic manipulation tasks
title_full_unstemmed Reinforcement learning for complex and dynamic manipulation tasks
title_sort Reinforcement learning for complex and dynamic manipulation tasks
dc.creator.none.fl_str_mv Boix Granell, Arnau
author Boix Granell, Arnau
author_facet Boix Granell, Arnau
author_role author
dc.contributor.none.fl_str_mv García Hidalgo, Néstor
Rosell Gratacòs, Jan
dc.subject.none.fl_str_mv Reinforcement learning
Algorithms
Manipulators (Mechanism)
Aprenentatge per reforç
Algorismes
Manipuladors (Mecanismes)
Àrees temàtiques de la UPC::Informàtica::Robòtica
topic Reinforcement learning
Algorithms
Manipulators (Mechanism)
Aprenentatge per reforç
Algorismes
Manipuladors (Mecanismes)
Àrees temàtiques de la UPC::Informàtica::Robòtica
description Being able to teach complex capabilities, such as opening a dishwasher, to robotic manipulators is a very challenging task, which is often tackled using raw programming. This is an attrac- tive technique for tasks under controlled environments, where variables like relative positions or physical properties are known and constant between tasks. On the other hand, its perfor- mance degrades in more uncontrolled environments, leading to reduced repeatability and suc- cess rates. Not only that but for some cases not even raw programming is feasible. In this thesis, NVIDIA’s advanced simulation tools, IsaacSim and IsaacLab, are used to create a novel framework that allows the training of reinforcement learning (RL) agents to develop some complex and dynamic manipulation tasks. With the objective of gaining familiarity with the software and iteratively enhance the simula- tion parameters, the framework is first used to explore some basic tasks. Through these pre- liminary tasks, fundamental RL principles were established, gaining insight to create more ad- vanced environments. Not only that but the thesis also explores ways to reduce the simulation to reality (Sim2Real) gap, a critical barrier to deploying simulation-trained models in the real world. Later, some of the studied techniques are used to upgrade the developed framework. The created environment is later used to train a Franka Emika Panda manipulator to open a dish- washer door under a simulated environment. Finally, a connection between simulation and reality is established using ROS2, and put to the test by trying to reproduce one of the simpler trained tasks in a real manipulator.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-01-31
2025
2025-05-06
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/2117/428855
url https://hdl.handle.net/2117/428855
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
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/x-rar-compressed
application/x-rar-compressed
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_ 1869420178146590720
score 15,812429

Similares en LA Referencia