Physics-based motion planning for grasping and manipulation

This thesis develops a series of knowledge-oriented physics-based motion planning algorithms for grasping and manipulation in cluttered an uncertain environments. The main idea is to use high-level knowledge-based reasoning to define the manipulation constraints that define the way how robot should...

Descripción completa

Detalles Bibliográficos
Autor: Ud Din, Muhayy
Tipo de recurso: tesis doctoral
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:2117/125843
Acceso en línea:https://hdl.handle.net/2117/125843
https://dx.doi.org/10.5821/dissertation-2117-125843
Access Level:acceso abierto
Palabra clave:Àrees temàtiques de la UPC::Informàtica
id ES_04396781237eefe2a6d341dca9642cec
oai_identifier_str oai:upcommons.upc.edu:2117/125843
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Physics-based motion planning for grasping and manipulation
title Physics-based motion planning for grasping and manipulation
spellingShingle Physics-based motion planning for grasping and manipulation
Ud Din, Muhayy
Àrees temàtiques de la UPC::Informàtica
title_short Physics-based motion planning for grasping and manipulation
title_full Physics-based motion planning for grasping and manipulation
title_fullStr Physics-based motion planning for grasping and manipulation
title_full_unstemmed Physics-based motion planning for grasping and manipulation
title_sort Physics-based motion planning for grasping and manipulation
dc.creator.none.fl_str_mv Ud Din, Muhayy
author Ud Din, Muhayy
author_facet Ud Din, Muhayy
author_role author
dc.contributor.none.fl_str_mv Peña Pitarch, Esteve
Rosell Gratacòs, Jan
dc.subject.none.fl_str_mv Àrees temàtiques de la UPC::Informàtica
topic Àrees temàtiques de la UPC::Informàtica
description This thesis develops a series of knowledge-oriented physics-based motion planning algorithms for grasping and manipulation in cluttered an uncertain environments. The main idea is to use high-level knowledge-based reasoning to define the manipulation constraints that define the way how robot should interact with the objects in the environment. These interactions are modeled by incorporating the physics-based model of rigid body dynamics in planning. The first part of the thesis is focused on the techniques to integrate the knowledge with physics-based motion planning. The knowledge is represented in terms of ontologies, a prologbased knowledge inference process is introduced that defines the manipulation constraints. These constraints are used in the state validation procedure of sampling-based kinodynamic motion planners. The state propagator of the motion planner is replaced by a physics-engine that takes care of the kinodynamic and physics-based constraints. To make the interaction humanlike, a low-level physics-based reasoning process is introduced that dynamically varies the control bounds by evaluating the physical properties of the objects. As a result, power efficient motion plans are obtained. Furthermore, a framework has been presented to incorporate linear temporal logic within physics-based motion planning to handle complex temporal goals. The second part of this thesis develops physics-based motion planning approaches to plan in cluttered and uncertain environments. The uncertainty is considered in 1) objects’ poses due to sensing and due to complex robot-object or object-object interactions; 2) uncertainty in the contact dynamics (such as friction coefficient); 3) uncertainty in robot controls. The solution is framed with sampling-based kinodynamic motion planners that solve the problem in open-loop, i.e., it considers uncertainty while planning and computes the solution in such a way that it successfully moves the robot from the start to the goal configuration even if there is uncertainty in the system. To implement the above stated approaches, a knowledge-oriented physics-based motion planning tool is presented. It is developed by extending The Kautham Project, a C++ based tool for sampling-based motion planning. Finally, the current research challenges and future research directions to extend the above stated approaches are discussed
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-12-04
2018
2018-12-14
dc.type.none.fl_str_mv doctoral thesis
http://purl.org/coar/resource_type/c_db06
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/125843
https://dx.doi.org/10.5821/dissertation-2117-125843
url https://hdl.handle.net/2117/125843
https://dx.doi.org/10.5821/dissertation-2117-125843
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-sa/4.0/
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-sa/4.0/
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_ 1869402779088322560
spelling Physics-based motion planning for grasping and manipulationUd Din, MuhayyÀrees temàtiques de la UPC::InformàticaThis thesis develops a series of knowledge-oriented physics-based motion planning algorithms for grasping and manipulation in cluttered an uncertain environments. The main idea is to use high-level knowledge-based reasoning to define the manipulation constraints that define the way how robot should interact with the objects in the environment. These interactions are modeled by incorporating the physics-based model of rigid body dynamics in planning. The first part of the thesis is focused on the techniques to integrate the knowledge with physics-based motion planning. The knowledge is represented in terms of ontologies, a prologbased knowledge inference process is introduced that defines the manipulation constraints. These constraints are used in the state validation procedure of sampling-based kinodynamic motion planners. The state propagator of the motion planner is replaced by a physics-engine that takes care of the kinodynamic and physics-based constraints. To make the interaction humanlike, a low-level physics-based reasoning process is introduced that dynamically varies the control bounds by evaluating the physical properties of the objects. As a result, power efficient motion plans are obtained. Furthermore, a framework has been presented to incorporate linear temporal logic within physics-based motion planning to handle complex temporal goals. The second part of this thesis develops physics-based motion planning approaches to plan in cluttered and uncertain environments. The uncertainty is considered in 1) objects’ poses due to sensing and due to complex robot-object or object-object interactions; 2) uncertainty in the contact dynamics (such as friction coefficient); 3) uncertainty in robot controls. The solution is framed with sampling-based kinodynamic motion planners that solve the problem in open-loop, i.e., it considers uncertainty while planning and computes the solution in such a way that it successfully moves the robot from the start to the goal configuration even if there is uncertainty in the system. To implement the above stated approaches, a knowledge-oriented physics-based motion planning tool is presented. It is developed by extending The Kautham Project, a C++ based tool for sampling-based motion planning. Finally, the current research challenges and future research directions to extend the above stated approaches are discussedEsta tesis desarrolla una serie de algoritmos de planificación del movimientos para la aprehensión y la manipulación de objetos en entornos desordenados e inciertos, basados en la física y el conocimiento. La idea principal es utilizar el razonamiento de alto nivel basado en el conocimiento para definir las restricciones de manipulación que definen la forma en que el robot debería interactuar con los objetos en el entorno. Estas interacciones se modelan incorporando en la planificación el modelo dinámico de los sólidos rígidos. La primera parte de la tesis se centra en las técnicas para integrar el conocimiento con la planificación del movimientos basada en la física. Para ello, se representa el conocimiento mediante ontologías y se introduce un proceso de razonamiento basado en Prolog para definir las restricciones de manipulación. Estas restricciones se usan en los procedimientos de validación del estado de los algoritmos de planificación basados en muestreo, cuyo propagador de estado se susituye por un motor basado en la física que tiene en cuenta las restricciones físicas y kinodinámicas. Además se ha implementado un proceso de razonamiento de bajo nivel que permite adaptar los límites de los controles aplicados a las propiedades físicas de los objetos. Complementariamente, se introduce un marco de desarrollo para la inclusión de la lógica temporal lineal en la planificación de movimientos basada en la física. La segunda parte de esta tesis extiende el enfoque a planificación del movimiento basados en la física en entornos desordenados e inciertos. La incertidumbre se considera en 1) las poses de los objetos debido a la medición y a las interacciones complejas robot-objeto y objeto-objeto; 2) incertidumbre en la dinámica de los contactos (como el coeficiente de fricción); 3) incertidumbre en los controles del robot. La solución se enmarca en planificadores kinodinámicos basados en muestro que solucionan el problema en lazo abierto, es decir que consideran la incertidumbre en la planificación para calcular una solución robusta que permita mover al robot de la configuración inicial a la final a pesar de la incertidumbre. Para implementar los enfoques mencionados anteriormente, se presenta una herramienta de planificación del movimientos basada en la física y guiada por el conocimiento, desarrollada extendiendo The Kautham Project, una herramienta implementada en C++ para la planificación de movimientos basada en muestreo. Finalmente, de discute los retos actuales y las futuras lineas de investigación a seguir para extender los enfoques presentados.Universitat Politècnica de CatalunyaPeña Pitarch, EsteveRosell Gratacòs, Jan20182018-12-0420182018-12-14doctoral thesishttp://purl.org/coar/resource_type/c_db06VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/doctoralThesisapplication/pdfhttps://hdl.handle.net/2117/125843https://dx.doi.org/10.5821/dissertation-2117-125843reponame: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-sa/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1258432026-05-27T15:37:01Z
score 15.300724

Similares en LA Referencia