Co-evolution of morphology and controller for a robot

Detalhes bibliográficos
Autor(a) principal: Silva, Ivo Manuel Caeiro da
Data de Publicação: 2018
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10071/17826
Resumo: Genetic algorithms are inspired by the process of natural selection that exists in nature. This process is what leads species to evolve and adapt to their surroundings, with the fittest species reproducing, leading to new generations that can take advantage of their surroundings better than before. This type of process can be used in evolutionary robotics to achieve controllers that are able to solve specific tasks to evolve morphologies for a specific purpose such as to walk, swim, grasp objects, among others. Robotic grippers are used in most factories nowadays, as well as in other workplaces such as hospitals and laboratories. They are used in tasks such as grabbing/moving objects, painting, surgeries, among many other uses. Grippers are therefore a case study with several possibilities that lend themselves to evolving morphologies through genetic algorithms. In this dissertation, we explore morphology generation through genetic algorithms. Using grippers as our case study, we were able to generate grippers capable of grabbing and lifting an object. To evolve these grippers, we created a simulated environment where grippers followed a script with instructions to grab the object and then move up. In total 120 different grippers were generated in these experiments. Out of those 120 generated grippers, 28% were able to grab and lift an object successfully. After the evaluation process was completed, we experimented with the grippers in five different scenarios to test their robustness. In these scenarios, the object’s starting conditions were different from those in the evaluation process.
id RCAP_27ce73ec1f2f9512eb2d79577c08f113
oai_identifier_str oai:repositorio.iscte-iul.pt:10071/17826
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Co-evolution of morphology and controller for a robotGripperMorphology generationGenetic algorithmsEngenharia eletrónicaAlgoritmo genéticoGeraçãoMorfologiaRobóticaAnálise de objetosGenetic algorithms are inspired by the process of natural selection that exists in nature. This process is what leads species to evolve and adapt to their surroundings, with the fittest species reproducing, leading to new generations that can take advantage of their surroundings better than before. This type of process can be used in evolutionary robotics to achieve controllers that are able to solve specific tasks to evolve morphologies for a specific purpose such as to walk, swim, grasp objects, among others. Robotic grippers are used in most factories nowadays, as well as in other workplaces such as hospitals and laboratories. They are used in tasks such as grabbing/moving objects, painting, surgeries, among many other uses. Grippers are therefore a case study with several possibilities that lend themselves to evolving morphologies through genetic algorithms. In this dissertation, we explore morphology generation through genetic algorithms. Using grippers as our case study, we were able to generate grippers capable of grabbing and lifting an object. To evolve these grippers, we created a simulated environment where grippers followed a script with instructions to grab the object and then move up. In total 120 different grippers were generated in these experiments. Out of those 120 generated grippers, 28% were able to grab and lift an object successfully. After the evaluation process was completed, we experimented with the grippers in five different scenarios to test their robustness. In these scenarios, the object’s starting conditions were different from those in the evaluation process.Os algoritmos genéticos são inspirados pelo processo de seleção natural que existe na natureza. Este processo leva espécies a evoluir e adaptar-se ao meio ambiente envolvente, com as espécies mais aptas reproduzindo, levando a que novas gerações possam tirar um melhor proveito do ambiente que as rodeia. Este tipo de processo pode ser utilizado na robótica evolucionária para evoluir controladores capazes de resolver tarefas de forma a evoluir morfologias para uma finalidade específica, tais como andar, nadar, agarrar objetos, entre outros. Garras robóticas são utilizadas na maioria das fábricas, assim como noutros locais de trabalho tais como hospitais e laboratórios. Podem ser utilizadas em tarefas como agarrar/mover objetos, pintura, cirurgias, entre outros usos. São, portanto, um caso de estudo com várias possibilidades que se prestam à evolução de morfologias através de algoritmos genéticos. Nesta dissertação, exploramos a geração de morfologia através de algoritmos genéticos. Utilizando garras como o nosso caso de estudo, conseguimos gerar garras capazes de agarrar e levantar um objeto. Para evoluir essas garras, criamos um ambiente simulado onde cada garra seguiu um script com instruções para agarrar o objeto e, em seguida, mover para cima. No total, 120 garras diferentes foram geradas nestas experiências. Dessas garras geradas 120, 28% foram capazes de capturar e levantar um objeto com êxito. Após a conclusão do processo de avaliação, experimentamos as garras em cinco cenários diferentes para testar a sua robustez. Nesses cenários, as condições iniciais em que os objetos começam eram diferentes das do processo de avaliação.2019-04-15T09:21:03Z2018-11-20T00:00:00Z2018-11-202018-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfapplication/octet-streamhttp://hdl.handle.net/10071/17826TID:202127397engSilva, Ivo Manuel Caeiro dainfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:37:38Zoai:repositorio.iscte-iul.pt:10071/17826Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:17:10.533117Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Co-evolution of morphology and controller for a robot
title Co-evolution of morphology and controller for a robot
spellingShingle Co-evolution of morphology and controller for a robot
Silva, Ivo Manuel Caeiro da
Gripper
Morphology generation
Genetic algorithms
Engenharia eletrónica
Algoritmo genético
Geração
Morfologia
Robótica
Análise de objetos
title_short Co-evolution of morphology and controller for a robot
title_full Co-evolution of morphology and controller for a robot
title_fullStr Co-evolution of morphology and controller for a robot
title_full_unstemmed Co-evolution of morphology and controller for a robot
title_sort Co-evolution of morphology and controller for a robot
author Silva, Ivo Manuel Caeiro da
author_facet Silva, Ivo Manuel Caeiro da
author_role author
dc.contributor.author.fl_str_mv Silva, Ivo Manuel Caeiro da
dc.subject.por.fl_str_mv Gripper
Morphology generation
Genetic algorithms
Engenharia eletrónica
Algoritmo genético
Geração
Morfologia
Robótica
Análise de objetos
topic Gripper
Morphology generation
Genetic algorithms
Engenharia eletrónica
Algoritmo genético
Geração
Morfologia
Robótica
Análise de objetos
description Genetic algorithms are inspired by the process of natural selection that exists in nature. This process is what leads species to evolve and adapt to their surroundings, with the fittest species reproducing, leading to new generations that can take advantage of their surroundings better than before. This type of process can be used in evolutionary robotics to achieve controllers that are able to solve specific tasks to evolve morphologies for a specific purpose such as to walk, swim, grasp objects, among others. Robotic grippers are used in most factories nowadays, as well as in other workplaces such as hospitals and laboratories. They are used in tasks such as grabbing/moving objects, painting, surgeries, among many other uses. Grippers are therefore a case study with several possibilities that lend themselves to evolving morphologies through genetic algorithms. In this dissertation, we explore morphology generation through genetic algorithms. Using grippers as our case study, we were able to generate grippers capable of grabbing and lifting an object. To evolve these grippers, we created a simulated environment where grippers followed a script with instructions to grab the object and then move up. In total 120 different grippers were generated in these experiments. Out of those 120 generated grippers, 28% were able to grab and lift an object successfully. After the evaluation process was completed, we experimented with the grippers in five different scenarios to test their robustness. In these scenarios, the object’s starting conditions were different from those in the evaluation process.
publishDate 2018
dc.date.none.fl_str_mv 2018-11-20T00:00:00Z
2018-11-20
2018-09
2019-04-15T09:21:03Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10071/17826
TID:202127397
url http://hdl.handle.net/10071/17826
identifier_str_mv TID:202127397
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/octet-stream
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134730439884800