A hybrid reinforcement learning perspective for autonomous mobile robot control

The low-level control of autonomous mobile robots has been extensivelyaddressed by classical control techniques. However, the variable operativeconditions and different environmental factors faced by these robots havedriven researchers towards the formulation of adaptive control approaches.In this s...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Carlucho, Ignacio
Formato: Artículo revista
Lenguaje:Inglés
Publicado: Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ingeniería 2019
Materias:
Robots móviles autónomos
Refuerzos híbridos
Estrategias inteligentes de control
Robótica
Inteligencia artificial
Redes neuronales
Acceso en línea:https://www.ridaa.unicen.edu.ar/xmlui/handle/123456789/2619
Aporte de:
Repositorio Institucional de Acceso Abierto (RIDAA) de Universidad Nacional del Centro
id I21-R190-123456789-2619
record_format ojs
institution Universidad Nacional del Centro
institution_str I-21
repository_str R-190
container_title_str Repositorio Institucional de Acceso Abierto (RIDAA)
language Inglés
format Artículo revista
topic Robots móviles autónomos
Refuerzos híbridos
Estrategias inteligentes de control
Robótica
Inteligencia artificial
Redes neuronales
spellingShingle Robots móviles autónomos
Refuerzos híbridos
Estrategias inteligentes de control
Robótica
Inteligencia artificial
Redes neuronales
Carlucho, Ignacio
A hybrid reinforcement learning perspective for autonomous mobile robot control
topic_facet Robots móviles autónomos
Refuerzos híbridos
Estrategias inteligentes de control
Robótica
Inteligencia artificial
Redes neuronales
author Carlucho, Ignacio
author_facet Carlucho, Ignacio
author_sort Carlucho, Ignacio
title A hybrid reinforcement learning perspective for autonomous mobile robot control
title_short A hybrid reinforcement learning perspective for autonomous mobile robot control
title_full A hybrid reinforcement learning perspective for autonomous mobile robot control
title_fullStr A hybrid reinforcement learning perspective for autonomous mobile robot control
title_full_unstemmed A hybrid reinforcement learning perspective for autonomous mobile robot control
title_sort hybrid reinforcement learning perspective for autonomous mobile robot control
description The low-level control of autonomous mobile robots has been extensivelyaddressed by classical control techniques. However, the variable operativeconditions and different environmental factors faced by these robots havedriven researchers towards the formulation of adaptive control approaches.In this sense, artificial intelligence techniques seem promising since theycan provide a higher level of abstraction to the robot, allowing for moregeneral decision making. Particularly, within these techniques, the rein-forcement learning paradigm has excelled in solving the most diverse typeof problems, by providing a model free unsupervised solution. Further-more, recent developments in the deep reinforcement learning field haveallowed the use of deep neural networks as function approximators of thepolicy function, increasing the generalization performance. In this thesisthe author studies the capabilities of the reinforcement learning paradigmfor the real time low-level control of mobile robots. Making use of existingclassical control techniques and reinforcement learning, hybrid controllersare obtained that take the best of both worlds, enhancing the overall per-formance and effectively achieving adaptive controllers. Extensive resultsin simulation and on different robotic platforms show the promising ap-plicability of these intelligent adaptive controllers for autonomous robots.
publisher Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ingeniería
publishDate 2019
url https://www.ridaa.unicen.edu.ar/xmlui/handle/123456789/2619
work_keys_str_mv AT carluchoignacio ahybridreinforcementlearningperspectiveforautonomousmobilerobotcontrol
AT carluchoignacio unaperspectivadeaprendizajeporrefuerzoshibridosparaelcontrolderobotsmoviles
AT carluchoignacio hybridreinforcementlearningperspectiveforautonomousmobilerobotcontrol
first_indexed 2022-07-04T14:27:06Z
last_indexed 2022-07-04T14:27:06Z
bdutipo_str Revistas
_version_ 1764819786182688769

Ejemplares similares