Simulation of a simple E-Robot warehouse environment using reinforcement learning

Warehousing is an important part of a supply chain network. There are several types of operations that can occur in a warehouse environment; where most of the costs are associated with labor, mainly related to order-picking in warehouse building(s). Automating certain processes in a warehouse is a w...

Descripción completa

Detalles Bibliográficos
Autor: Salazar-Jimenez, Jose-Alberto
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/151901
Acceso en línea:https://hdl.handle.net/10609/151901
Access Level:acceso abierto
Palabra clave:reinforcement learning
autonomous mobile robot
deep reinforcement learning
warehousing operations
robot móvil autónomo
aprendizaje por refuerzo
aprendizaje por refuerzo profundo
modelado y simulación
operaciones de almacén
Automation -- TFM
Automatització -- TFM
id ES_b8a1395efb40edac689966c7e7c07d2d
oai_identifier_str oai:openaccess.uoc.edu:10609/151901
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Simulation of a simple E-Robot warehouse environment using reinforcement learning
title Simulation of a simple E-Robot warehouse environment using reinforcement learning
spellingShingle Simulation of a simple E-Robot warehouse environment using reinforcement learning
Salazar-Jimenez, Jose-Alberto
reinforcement learning
autonomous mobile robot
reinforcement learning
deep reinforcement learning
warehousing operations
robot móvil autónomo
aprendizaje por refuerzo
aprendizaje por refuerzo profundo
modelado y simulación
operaciones de almacén
Automation -- TFM
Automatització -- TFM
title_short Simulation of a simple E-Robot warehouse environment using reinforcement learning
title_full Simulation of a simple E-Robot warehouse environment using reinforcement learning
title_fullStr Simulation of a simple E-Robot warehouse environment using reinforcement learning
title_full_unstemmed Simulation of a simple E-Robot warehouse environment using reinforcement learning
title_sort Simulation of a simple E-Robot warehouse environment using reinforcement learning
dc.creator.none.fl_str_mv Salazar-Jimenez, Jose-Alberto
author Salazar-Jimenez, Jose-Alberto
author_facet Salazar-Jimenez, Jose-Alberto
author_role author
dc.contributor.none.fl_str_mv Juan, Angel A.
Gatnau Sarret, Marta
dc.subject.none.fl_str_mv reinforcement learning
autonomous mobile robot
reinforcement learning
deep reinforcement learning
warehousing operations
robot móvil autónomo
aprendizaje por refuerzo
aprendizaje por refuerzo profundo
modelado y simulación
operaciones de almacén
Automation -- TFM
Automatització -- TFM
topic reinforcement learning
autonomous mobile robot
reinforcement learning
deep reinforcement learning
warehousing operations
robot móvil autónomo
aprendizaje por refuerzo
aprendizaje por refuerzo profundo
modelado y simulación
operaciones de almacén
Automation -- TFM
Automatització -- TFM
description Warehousing is an important part of a supply chain network. There are several types of operations that can occur in a warehouse environment; where most of the costs are associated with labor, mainly related to order-picking in warehouse building(s). Automating certain processes in a warehouse is a way to try to reduce labor costs. There are different types of robots that can be deployed for such purpose, depending on the task(s) they are to carry out. One kind of growing interest are Autonomous Mobile Robots (AMRs), which use hardware and software to navigate their surroundings without requiring a pre-planned routing to perform their work. Efficiently coordinating a fleet of AMRs, with a specified set of rules and goals to follow, represents a complex optimization challenge, being an active topic of research and development, due to the positive impact this has and could have, such as the reduction of costs linked to processes involved in warehousing operations. The objective of this project was to develop a reinforcement learning model environment that simulates, to certain extend, the conditions and rules involved in a warehouse, to perform the order-picking process from storage/picking locations to delivery/shipping locations, by a fleet of AMRs powered by electric batteries; using as fewer computational resources as possible, so that it can run on a personal computer, with moderate specs. Six different experiments cases were carried out, whose results demonstrate the development of a simple RL model, controlling several robots (AMRs), capable of handling the “movement” of “packages” from “storing/picking locations” to “shipping/delivery locations” and the “recharging” of their “batteries”; with a decrease in performance, with the increase in the complexity of the environment and the number of robots; within the constraints and considerations of the RL model development.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/10609/151901
url https://hdl.handle.net/10609/151901
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv CC BY-NC-ND
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv CC BY-NC-ND
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Universitat Oberta de Catalunya (UOC)
publisher.none.fl_str_mv Universitat Oberta de Catalunya (UOC)
dc.source.none.fl_str_mv reponame:O2, repositorio institucional de la UOC
instname:Universitat Oberta de Catalunya (UOC)
instname_str Universitat Oberta de Catalunya (UOC)
reponame_str O2, repositorio institucional de la UOC
collection O2, repositorio institucional de la UOC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417666009104384
spelling Simulation of a simple E-Robot warehouse environment using reinforcement learningSalazar-Jimenez, Jose-Albertoreinforcement learningautonomous mobile robotreinforcement learningdeep reinforcement learningwarehousing operationsrobot móvil autónomoaprendizaje por refuerzoaprendizaje por refuerzo profundomodelado y simulaciónoperaciones de almacénAutomation -- TFMAutomatització -- TFMWarehousing is an important part of a supply chain network. There are several types of operations that can occur in a warehouse environment; where most of the costs are associated with labor, mainly related to order-picking in warehouse building(s). Automating certain processes in a warehouse is a way to try to reduce labor costs. There are different types of robots that can be deployed for such purpose, depending on the task(s) they are to carry out. One kind of growing interest are Autonomous Mobile Robots (AMRs), which use hardware and software to navigate their surroundings without requiring a pre-planned routing to perform their work. Efficiently coordinating a fleet of AMRs, with a specified set of rules and goals to follow, represents a complex optimization challenge, being an active topic of research and development, due to the positive impact this has and could have, such as the reduction of costs linked to processes involved in warehousing operations. The objective of this project was to develop a reinforcement learning model environment that simulates, to certain extend, the conditions and rules involved in a warehouse, to perform the order-picking process from storage/picking locations to delivery/shipping locations, by a fleet of AMRs powered by electric batteries; using as fewer computational resources as possible, so that it can run on a personal computer, with moderate specs. Six different experiments cases were carried out, whose results demonstrate the development of a simple RL model, controlling several robots (AMRs), capable of handling the “movement” of “packages” from “storing/picking locations” to “shipping/delivery locations” and the “recharging” of their “batteries”; with a decrease in performance, with the increase in the complexity of the environment and the number of robots; within the constraints and considerations of the RL model development.El almacenamiento es una parte importante de una red de cadena de suministro. Existen varios tipos de operaciones que ocurren en un entorno de almacén; donde la mayoría de los costos se asocian a la mano de obra, principalmente relacionados con la preparación y movimiento de pedidos en los edificios del almacén. La automatización de ciertos procesos en un almacén es una forma de intentar reducir los costos de mano de obra. Existen diferentes tipos de robots que se pueden implementar para dicho propósito, según las tareas que deban llevar a cabo. Un tipo de interés creciente son los robots móviles autónomos (AMRs), que utilizan hardware y software para navegar por sus alrededores sin requerir una ruta planificada previamente para realizar su trabajo. Coordinar de manera eficiente una flota de AMRs, con un conjunto específico de objetivos y reglas a seguir, representa un desafío de optimización complejo, siendo un tema activo de investigación y desarrollo, debido al impacto positivo que esto tiene y podría tener, como la reducción de costos vinculados a los procesos involucrados en las operaciones de almacenamiento. El objetivo de este proyecto fue desarrollar un entorno de aprendizaje por refuerzo que simulara, en cierta medida, las condiciones y reglas involucradas en un almacén, para realizar la preparación de pedidos desde las ubicaciones de almacenamiento/recolección hasta las ubicaciones de entrega/envío, por una flota de robots móviles automatizados alimentados por baterías eléctricas; utilizando la menor cantidad de recurso computacional posible, pudiendo ser corrido en una computadora personal de especificaciones simples. Se llevaron a cabo seis casos experimentales diferentes, cuyos resultados demuestran el desarrollo de un modelo RL simple, controlando varios robots (AMRs), capaces de manejar el “movimiento” de “paquetes” desde las “ubicaciones de almacenamiento/recolección” hasta las “ubicaciones de envío/entrega” y la “recarga” de sus “baterías”; con una disminución en el rendimiento, con el aumento de la complejidad del entorno y el número de robots; dentro de las limitaciones y las consideraciones del desarrollo del modelo de RL.Universitat Oberta de Catalunya (UOC)Juan, Angel A.Gatnau Sarret, Marta202520252024info:eu-repo/semantics/masterThesisapplication/pdfapplication/pdfhttps://hdl.handle.net/10609/151901reponame:O2, repositorio institucional de la UOCinstname:Universitat Oberta de Catalunya (UOC)InglésCC BY-NC-NDhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:openaccess.uoc.edu:10609/1519012026-05-28T12:42:01Z
score 15,812429