Evolutionary design for robust self-adaptive control

Detalhes bibliográficos
Autor(a) principal: Morais, Gustavo Alves Prudencio de
Data de Publicação: 2024
Tipo de documento: Tese
Idioma: eng
Título da fonte: Biblioteca Digital de Teses e Dissertações da USP
Texto Completo: https://www.teses.usp.br/teses/disponiveis/18/18153/tde-08102024-161622/
Resumo: Dealing with parametric uncertainties in mobile autonomous systems is a critical challenge. The difficulties scale when self-driving systems are operating in unconfined spaces or with interaction with people and other autonomous agents. Robust controllers have emerged as efficient solutions for ensuring autonomous navigation in such scenarios. However, uncertainty matrices for these agents are typically established using algebraic methods, necessitating prior knowledge of system dynamics. Consequently, control system designers rely heavily on the accuracy of uncertain models to achieve optimal control performance. To address these limitations, this study proposes a robust recursive controller developed through evolutionary optimization. A self-adapted algorithm was designed to incorporate robust control in single and multiobjective scenarios. Additionally, a local search strategy for addressing multiobjective optimization challenges is introduced. This methodology can be applied to any established multiobjective evolutionary algorithm found in existing literature. The findings demonstrate that this combination of a modelbased controller and machine learning significantly enhances system effectiveness in terms of robustness, stability, and smoothness. Moreover, this approach offers a more adaptable and comprehensive solution for scenarios with uncertainties in vision-based control and for heavy vehicles with significant mass variation.
id USP_3319e89b86be4c5b9b24010849b4d210
oai_identifier_str oai:teses.usp.br:tde-08102024-161622
network_acronym_str USP
network_name_str Biblioteca Digital de Teses e Dissertações da USP
repository_id_str 2721
spelling Evolutionary design for robust self-adaptive controlDesign evolutivo para controle robusto auto adaptativoalgoritmos evolutivosautonomous systemscontrole robustoevolutionary algorithmsotimização uni e multiobjetivorobust controlsingle and multiobjective optimizationsistemas autônomosDealing with parametric uncertainties in mobile autonomous systems is a critical challenge. The difficulties scale when self-driving systems are operating in unconfined spaces or with interaction with people and other autonomous agents. Robust controllers have emerged as efficient solutions for ensuring autonomous navigation in such scenarios. However, uncertainty matrices for these agents are typically established using algebraic methods, necessitating prior knowledge of system dynamics. Consequently, control system designers rely heavily on the accuracy of uncertain models to achieve optimal control performance. To address these limitations, this study proposes a robust recursive controller developed through evolutionary optimization. A self-adapted algorithm was designed to incorporate robust control in single and multiobjective scenarios. Additionally, a local search strategy for addressing multiobjective optimization challenges is introduced. This methodology can be applied to any established multiobjective evolutionary algorithm found in existing literature. The findings demonstrate that this combination of a modelbased controller and machine learning significantly enhances system effectiveness in terms of robustness, stability, and smoothness. Moreover, this approach offers a more adaptable and comprehensive solution for scenarios with uncertainties in vision-based control and for heavy vehicles with significant mass variation.Lidar com incertezas paramétricas em sistemas autônomos móveis é um desafio crucial. As dificuldades aumentam quando os sistemas de condução autônoma operam em espaços não confinados ou em interação com pessoas e outros agentes. Os controladores robustos surgiram como soluções eficientes para garantir a navegação autônoma em tais cenários. No entanto, as matrizes de incerteza para estes agentes são normalmente estabelecidas utilizando métodos algébricos, o que exige um conhecimento prévio da dinâmica do sistema. Consequentemente, os projetistas de sistemas de controle dependem fortemente da precisão dos modelos de incertezas para obter um desempenho ótimo. Para resolver estas limitações, este estudo propõe um controlador recursivo robusto desenvolvido usando algoritmos de otimização evolutiva. Foi desenvolvido um algoritmo auto-adaptado que incorpora o controle robusto em cenários de objetivo único e multiobjetivo. Ademais, foi introduzida uma estratégia de busca local para lidar com os desafios de otimização multiobjetivo. Esta metodologia pode ser aplicada a qualquer algoritmo evolutivo multiobjetivo existente na literatura. Os resultados demonstram que esta combinação de controle baseado em modelos matemáticos e aprendizagem de máquinas melhora significativamente a eficácia do sistema em termos de robustez, estabilidade e suavidade. Além disso, esta abordagem oferece uma solução mais adaptável e abrangente para cenários com incertezas em controladores referenciados em visão e em veículos pesados com variação significativa de massa.Biblioteca Digitais de Teses e Dissertações da USPTerra, Marco HenriqueMorais, Gustavo Alves Prudencio de2024-08-30info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisapplication/pdfhttps://www.teses.usp.br/teses/disponiveis/18/18153/tde-08102024-161622/reponame:Biblioteca Digital de Teses e Dissertações da USPinstname:Universidade de São Paulo (USP)instacron:USPLiberar o conteúdo para acesso público.info:eu-repo/semantics/openAccesseng2024-10-09T19:32:02Zoai:teses.usp.br:tde-08102024-161622Biblioteca Digital de Teses e Dissertaçõeshttp://www.teses.usp.br/PUBhttp://www.teses.usp.br/cgi-bin/mtd2br.plvirginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.bropendoar:27212024-10-09T19:32:02Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)false
dc.title.none.fl_str_mv Evolutionary design for robust self-adaptive control
Design evolutivo para controle robusto auto adaptativo
title Evolutionary design for robust self-adaptive control
spellingShingle Evolutionary design for robust self-adaptive control
Morais, Gustavo Alves Prudencio de
algoritmos evolutivos
autonomous systems
controle robusto
evolutionary algorithms
otimização uni e multiobjetivo
robust control
single and multiobjective optimization
sistemas autônomos
title_short Evolutionary design for robust self-adaptive control
title_full Evolutionary design for robust self-adaptive control
title_fullStr Evolutionary design for robust self-adaptive control
title_full_unstemmed Evolutionary design for robust self-adaptive control
title_sort Evolutionary design for robust self-adaptive control
author Morais, Gustavo Alves Prudencio de
author_facet Morais, Gustavo Alves Prudencio de
author_role author
dc.contributor.none.fl_str_mv Terra, Marco Henrique
dc.contributor.author.fl_str_mv Morais, Gustavo Alves Prudencio de
dc.subject.por.fl_str_mv algoritmos evolutivos
autonomous systems
controle robusto
evolutionary algorithms
otimização uni e multiobjetivo
robust control
single and multiobjective optimization
sistemas autônomos
topic algoritmos evolutivos
autonomous systems
controle robusto
evolutionary algorithms
otimização uni e multiobjetivo
robust control
single and multiobjective optimization
sistemas autônomos
description Dealing with parametric uncertainties in mobile autonomous systems is a critical challenge. The difficulties scale when self-driving systems are operating in unconfined spaces or with interaction with people and other autonomous agents. Robust controllers have emerged as efficient solutions for ensuring autonomous navigation in such scenarios. However, uncertainty matrices for these agents are typically established using algebraic methods, necessitating prior knowledge of system dynamics. Consequently, control system designers rely heavily on the accuracy of uncertain models to achieve optimal control performance. To address these limitations, this study proposes a robust recursive controller developed through evolutionary optimization. A self-adapted algorithm was designed to incorporate robust control in single and multiobjective scenarios. Additionally, a local search strategy for addressing multiobjective optimization challenges is introduced. This methodology can be applied to any established multiobjective evolutionary algorithm found in existing literature. The findings demonstrate that this combination of a modelbased controller and machine learning significantly enhances system effectiveness in terms of robustness, stability, and smoothness. Moreover, this approach offers a more adaptable and comprehensive solution for scenarios with uncertainties in vision-based control and for heavy vehicles with significant mass variation.
publishDate 2024
dc.date.none.fl_str_mv 2024-08-30
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://www.teses.usp.br/teses/disponiveis/18/18153/tde-08102024-161622/
url https://www.teses.usp.br/teses/disponiveis/18/18153/tde-08102024-161622/
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv
dc.rights.driver.fl_str_mv Liberar o conteúdo para acesso público.
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Liberar o conteúdo para acesso público.
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv
dc.publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
dc.source.none.fl_str_mv
reponame:Biblioteca Digital de Teses e Dissertações da USP
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Biblioteca Digital de Teses e Dissertações da USP
collection Biblioteca Digital de Teses e Dissertações da USP
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)
repository.mail.fl_str_mv virginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.br
_version_ 1818279068707061760