Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics
A wide variety of approaches have been proposed to address the problem of task planning in robotics, from which partially observable Markov decision processes (POMDP) stand out due to their capacity to model the uncertainty of actions and keep track of the state of the world by means of a partially...
| Autor: | |
|---|---|
| Formato: | tesis de maestría |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2019 |
| País: | México |
| Recursos: | Instituto Nacional de Astrofísica, Óptica y Electrónica |
| Repositorio: | Repositorio Institucional del INAOE |
| Idioma: | inglés |
| OAI Identifier: | oai:inaoe.repositorioinstitucional.mx:1009/1949 |
| Acesso em linha: | http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1949 |
| Access Level: | acceso abierto |
| Palavra-chave: | info:eu-repo/classification/Inspec/Task planning info:eu-repo/classification/Inspec/Hierarchical POMDPs info:eu-repo/classification/Inspec/Service robotics info:eu-repo/classification/Inspec/Declarative programming info:eu-repo/classification/Inspec/General architecture info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/12 info:eu-repo/classification/cti/1203 info:eu-repo/classification/cti/120323 |
| id |
MX_5c32c1446cd9f86d31234c19ce7ced14 |
|---|---|
| oai_identifier_str |
oai:inaoe.repositorioinstitucional.mx:1009/1949 |
| network_acronym_str |
MX |
| network_name_str |
México |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| title |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| spellingShingle |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics Sergio Serrano info:eu-repo/classification/Inspec/Task planning info:eu-repo/classification/Inspec/Hierarchical POMDPs info:eu-repo/classification/Inspec/Service robotics info:eu-repo/classification/Inspec/Declarative programming info:eu-repo/classification/Inspec/General architecture info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/12 info:eu-repo/classification/cti/1203 info:eu-repo/classification/cti/120323 info:eu-repo/classification/cti/120323 |
| title_short |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| title_full |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| title_fullStr |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| title_full_unstemmed |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| title_sort |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics |
| dc.creator.none.fl_str_mv |
Sergio Serrano |
| author |
Sergio Serrano |
| author_facet |
Sergio Serrano |
| author_role |
author |
| dc.contributor.none.fl_str_mv |
Luis Enrique Sucar Succar |
| dc.subject.none.fl_str_mv |
info:eu-repo/classification/Inspec/Task planning info:eu-repo/classification/Inspec/Hierarchical POMDPs info:eu-repo/classification/Inspec/Service robotics info:eu-repo/classification/Inspec/Declarative programming info:eu-repo/classification/Inspec/General architecture info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/12 info:eu-repo/classification/cti/1203 info:eu-repo/classification/cti/120323 info:eu-repo/classification/cti/120323 |
| topic |
info:eu-repo/classification/Inspec/Task planning info:eu-repo/classification/Inspec/Hierarchical POMDPs info:eu-repo/classification/Inspec/Service robotics info:eu-repo/classification/Inspec/Declarative programming info:eu-repo/classification/Inspec/General architecture info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/12 info:eu-repo/classification/cti/1203 info:eu-repo/classification/cti/120323 info:eu-repo/classification/cti/120323 |
| description |
A wide variety of approaches have been proposed to address the problem of task planning in robotics, from which partially observable Markov decision processes (POMDP) stand out due to their capacity to model the uncertainty of actions and keep track of the state of the world by means of a partially observable representation of it. Nonetheless, there are some drawbacks inherent to the use of POMDPs, such as designing a representation that models as best as possible a particular problem, along with the complexity that represents to find a good policy for POMDPs with large state spaces. Therefore, in order to mitigate these challenges, in this thesis we propose an architecture for task planning oriented towards service robot applications, that combines a knowledge representation scheme and POMDPs to build a hierarchy of actions that enables the decomposition of problems into several smaller ones. The knowledge representation defines a list of parameters, so that domain specific information can be encoded by a designer, and used by the architecture to automatically generate and execute plans to solve tasks. Using the hierarchy of actions to generate plans, the system is able to exploit the structure of the environment and ignore those regions in the state space that are irrelevant for a specific task. To evaluate the proposed architecture, a mobile robot navigation domain is employed as case study. Experimental results show that, in scenarios with moderate uncertainty, the architecture is able to perform both reliably and time efficiently, as it generates plans in a time that is several orders smaller than baseline methods. |
| publishDate |
2019 |
| dc.date.none.fl_str_mv |
2019-11 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/masterThesis info:eu-repo/semantics/acceptedVersion |
| format |
masterThesis |
| status_str |
acceptedVersion |
| dc.identifier.none.fl_str_mv |
http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1949 |
| url |
http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1949 |
| dc.language.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.none.fl_str_mv |
citation:Arredondo Serrano, S., (2019), Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics, Tesis de Maestría, Instituto Nacional de Astrofísica, Óptica y Electrónica. |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-nd/4.0 |
| eu_rights_str_mv |
openAccess |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0 |
| dc.format.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Instituto Nacional de Astrofísica, Óptica y Electrónica |
| publisher.none.fl_str_mv |
Instituto Nacional de Astrofísica, Óptica y Electrónica |
| dc.source.none.fl_str_mv |
reponame:Repositorio Institucional del INAOE instname:Instituto Nacional de Astrofísica, Óptica y Electrónica instacron:INAOE |
| instname_str |
Instituto Nacional de Astrofísica, Óptica y Electrónica |
| instacron_str |
INAOE |
| institution |
INAOE |
| reponame_str |
Repositorio Institucional del INAOE |
| collection |
Repositorio Institucional del INAOE |
| repository.name.fl_str_mv |
|
| repository.mail.fl_str_mv |
|
| _version_ |
1858175394147991552 |
| spelling |
Automatic hierarchical nesting of partially observable markov decision processes for task planning in service roboticsSergio Serranoinfo:eu-repo/classification/Inspec/Task planninginfo:eu-repo/classification/Inspec/Hierarchical POMDPsinfo:eu-repo/classification/Inspec/Service roboticsinfo:eu-repo/classification/Inspec/Declarative programminginfo:eu-repo/classification/Inspec/General architectureinfo:eu-repo/classification/cti/1info:eu-repo/classification/cti/12info:eu-repo/classification/cti/1203info:eu-repo/classification/cti/120323info:eu-repo/classification/cti/120323A wide variety of approaches have been proposed to address the problem of task planning in robotics, from which partially observable Markov decision processes (POMDP) stand out due to their capacity to model the uncertainty of actions and keep track of the state of the world by means of a partially observable representation of it. Nonetheless, there are some drawbacks inherent to the use of POMDPs, such as designing a representation that models as best as possible a particular problem, along with the complexity that represents to find a good policy for POMDPs with large state spaces. Therefore, in order to mitigate these challenges, in this thesis we propose an architecture for task planning oriented towards service robot applications, that combines a knowledge representation scheme and POMDPs to build a hierarchy of actions that enables the decomposition of problems into several smaller ones. The knowledge representation defines a list of parameters, so that domain specific information can be encoded by a designer, and used by the architecture to automatically generate and execute plans to solve tasks. Using the hierarchy of actions to generate plans, the system is able to exploit the structure of the environment and ignore those regions in the state space that are irrelevant for a specific task. To evaluate the proposed architecture, a mobile robot navigation domain is employed as case study. Experimental results show that, in scenarios with moderate uncertainty, the architecture is able to perform both reliably and time efficiently, as it generates plans in a time that is several orders smaller than baseline methods.Una amplia variedad de enfoques han sido propuestos para abordar el problema de planificación de tareas en robótica, entre los cuales destacan los procesos de decisión de Markov parcialmente observables (POMDP por sus siglas en inglés) debido a su capacidad para modelar la incertidumbre en las acciones y realizar un seguimiento del estado del mundo mediante una representación parcialmente observable del mismo, lo cual es particularmente importante en robótica. No obstante, existen algunas desventajas inherentes al uso de los POMDPs, tales como el diseño de una representación que modele lo mejor posible un problema en particular, así como la complejidad que representa encontrar una buena política para POMDPs con espacios de estado grandes. Así, con el objetivo de mitigar estas dificultades, en esta tesis presentamos una arquitectura para la planificación de tareas orientada a aplicaciones de robótica de servicio, que combina un esquema de representación de conocimiento y POMDPs para construir una jerarquía de acciones que permite la descomposición de problemas en varios má pequeños. La representación del conocimiento define una lista de parámetros que permite que un diseñador codifique información específica del dominio, y su utilización por parte de la arquitectura para generar y ejecutar, de manera automática, planes con el objetivo de resolver tareas. Utilizar la jerarquía de acciones para planificar permite que el sistema aproveche la estructura del entorno e ignore regiones del espacio de estados que son irrelevantes para una tarea en específico. Para evaluar la arquitectura propuesta, un dominio de navegación de un robot móvil es empleado como caso de estudio. Resultados experimentales muestran que, en escenarios de incertidumbre moderada, la arquitectura es capaz de desempeñarse de manera confiable y eficiente, dado que genera planes en un tiempo que es menor en varios órdenes de magnitud al requerido por otros métodos base.Instituto Nacional de Astrofísica, Óptica y ElectrónicaLuis Enrique Sucar Succar2019-11info:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/acceptedVersionapplication/pdfhttp://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1949reponame:Repositorio Institucional del INAOEinstname:Instituto Nacional de Astrofísica, Óptica y Electrónicainstacron:INAOEengcitation:Arredondo Serrano, S., (2019), Automatic hierarchical nesting of partially observable markov decision processes for task planning in service robotics, Tesis de Maestría, Instituto Nacional de Astrofísica, Óptica y Electrónica.info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0oai:inaoe.repositorioinstitucional.mx:1009/19492024-08-28T03:23:02Z |
| score |
14,965132 |