A stochastic approach to generate emergent behaviors in robotic swarms
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/65401 |
Resumo: | In this dissertation, we present a novel methodology that extends the concepts of Gibbs Random Fields (GRFs) to the context of swarm robotics, allowing us to design control mechanisms that produce different swarm behaviors using only local information. In this context, a GRF is a probabilistic graph model that describes the interactions and behaviors of a group of robots. The robots are assumed to interact with each other in a way that can be described by a set of random variables. These variables define a random field, and the joint probability function is a Gibbs distribution that describes the probability of the swarm being in a given configuration. By using a Markov Chain Monte Carlo (MCMC) method, each robot sample velocity commands in a decentralized way, forcing them to move toward the global minimum of the potential, leading the entire swarm to converge to the desired behavior. This approach has several advantages over more traditional methods for controlling the behavior of a swarm. For example, it allows for decentralized control, where each robot makes decisions based on local information rather than relying on a central controller. This makes the system more robust and scalable, as there is no single point of failure, and the swarm can continue to operate even if individual robots fail. Additionally, it allows for a more flexible and adaptable approach to swarm behavior, as the potential function can be modified to account for changing environmental conditions or new goals for the swarm. To demonstrate the application of our methodology, we investigate the design of methods that tackle three significant challenges in swarm robotics: flocking and segregation, cooperative object transportation, and pattern formation. Numerical simulations and real-world experiments show that these methods are scalable, adaptable, and robust, even in the presence of noise, failures, and changes in the environment. More specifically, the first method shows to be able to adequately segregate a group of heterogeneous robots while keeping cohesive navigation and avoiding obstacles in the environment. The second method supports the transportation of objects of different shapes, sizes, and masses. It is also scalable and resilient to changes in goal location and robot failures. The third method experiments show the ability to create diverse patterns using different neighborhood constraints and that it may serve as a basis for more tangible applications such as the construction of chain or bridge-like structures using a swarm of heterogeneous robots. Overall, the proposed methodology shows promise for contributing to the field of swarm robotics, enabling the designing of mechanisms that adequately produce different behaviors of a swarm of robots. |
id |
UFMG_da3117710c6e31bbab203e8e4501b9b9 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/65401 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Luiz Chaimowiczhttp://lattes.cnpq.br/4499928813481251Douglas Guimarães MacharetRenato Martins AssunçãoValdir Grassi JúniorDavid Julián Saldaña Santacruzhttp://lattes.cnpq.br/6192098741452112Paulo Alfredo Frota Rezeck2024-03-06T21:31:21Z2024-03-06T21:31:21Z2023-12-04http://hdl.handle.net/1843/65401In this dissertation, we present a novel methodology that extends the concepts of Gibbs Random Fields (GRFs) to the context of swarm robotics, allowing us to design control mechanisms that produce different swarm behaviors using only local information. In this context, a GRF is a probabilistic graph model that describes the interactions and behaviors of a group of robots. The robots are assumed to interact with each other in a way that can be described by a set of random variables. These variables define a random field, and the joint probability function is a Gibbs distribution that describes the probability of the swarm being in a given configuration. By using a Markov Chain Monte Carlo (MCMC) method, each robot sample velocity commands in a decentralized way, forcing them to move toward the global minimum of the potential, leading the entire swarm to converge to the desired behavior. This approach has several advantages over more traditional methods for controlling the behavior of a swarm. For example, it allows for decentralized control, where each robot makes decisions based on local information rather than relying on a central controller. This makes the system more robust and scalable, as there is no single point of failure, and the swarm can continue to operate even if individual robots fail. Additionally, it allows for a more flexible and adaptable approach to swarm behavior, as the potential function can be modified to account for changing environmental conditions or new goals for the swarm. To demonstrate the application of our methodology, we investigate the design of methods that tackle three significant challenges in swarm robotics: flocking and segregation, cooperative object transportation, and pattern formation. Numerical simulations and real-world experiments show that these methods are scalable, adaptable, and robust, even in the presence of noise, failures, and changes in the environment. More specifically, the first method shows to be able to adequately segregate a group of heterogeneous robots while keeping cohesive navigation and avoiding obstacles in the environment. The second method supports the transportation of objects of different shapes, sizes, and masses. It is also scalable and resilient to changes in goal location and robot failures. The third method experiments show the ability to create diverse patterns using different neighborhood constraints and that it may serve as a basis for more tangible applications such as the construction of chain or bridge-like structures using a swarm of heterogeneous robots. Overall, the proposed methodology shows promise for contributing to the field of swarm robotics, enabling the designing of mechanisms that adequately produce different behaviors of a swarm of robots.Esta tese apresenta uma nova metodologia que estende os conceitos de Campos Aleatórios de Gibbs (GRFs) para o contexto da robótica de enxame, permitindo projetar mecanismos de controle que produzem diferentes comportamentos de enxame usando apenas informações locais. Nesse contexto, um GRF é um modelo gráfico probabilístico que descreve as interações e comportamentos de um grupo de robôs. Assume-se que os robôs interagem uns com os outros de uma forma que pode ser descrita por um conjunto de variáveis aleatórias. Essas variáveis definem um campo aleatório e a função de probabilidade conjunta é uma distribuição de Gibbs que descreve a probabilidade do enxame estar em uma determinada configuração. Utilizando o método Markov Chain Monte Carlo (MCMC), cada robô amostra comandos de velocidade de forma descentralizada, forçando-os a se moverem em direção ao mínimo global do potencial, o que direciona todo o enxame a convergir para o comportamento desejado. Esta abordagem tem várias vantagens sobre os métodos mais tradicionais para controlar o comportamento de um enxame. Por exemplo, permite o controle descentralizado, onde cada robô toma decisões com base em informações locais, em vez de depender de um controlador central. Isso torna o sistema mais robusto e escalável, pois não existe um único ponto de falha e o enxame pode continuar a operar mesmo se os robôs individuais falharem. Além disso, permite uma abordagem mais flexível e adaptável ao comportamento do enxame, pois a função potencial pode ser modificada para levar em conta mudanças nas condições ambientais ou novos objetivos para o enxame. Para demonstrar a aplicação de nossa metodologia, investigamos o design de métodos que abordam três desafios significativos na robótica de enxame: flocking e segregação, transporte cooperativo de objetos e formação de padrões. Simulações numéricas e experimentos utilizando robôs reais mostram que esses métodos são escaláveis, adaptáveis e robustos, mesmo na presença de ruído, falhas e mudanças no ambiente. Mais especificamente, o primeiro método mostra ser capaz de segregar adequadamente um grupo de robôs heterogêneos, mantendo a navegação coesa e evitando obstáculos no ambiente. O segundo método demonstra o transporte de objetos de diferentes formas, tamanhos e massas. Também é escalável e resiliente a mudanças na localização do objetivo e falhas nos robôs. Os experimentos do terceiro método mostram a capacidade de criar diversos padrões usando diferentes restrições de vizinhança e que podem servir de base para aplicações mais tangíveis de um enxame de robôs heterogêneos, como a construção de estruturas encadeadas ou semelhantes a pontes dinâmicas. No geral, a metodologia proposta mostra-se promissora e contribui para o campo da robótica de enxame, permitindo a concepção de mecanismos que produzam adequadamente diferentes comportamentos de um enxame de robôs.CNPq - Conselho Nacional de Desenvolvimento Científico e TecnológicoFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas GeraisCAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorengUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOhttp://creativecommons.org/licenses/by-nc/3.0/pt/info:eu-repo/semantics/openAccessComputação – TesesRobótica – TesesRobôs – Sistema de controles – TesesRoboticsMulti-agent systemSwarm roboticsProbabilistic roboticsA stochastic approach to generate emergent behaviors in robotic swarmsUma abordagem estocástica para a criação de comportamentos emergentes em enxames robóticosinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALTese_Doutorado_Paulo_Rezeck.pdfTese_Doutorado_Paulo_Rezeck.pdfapplication/pdf19862560https://repositorio.ufmg.br/bitstream/1843/65401/1/Tese_Doutorado_Paulo_Rezeck.pdfee8b7497ba8888f63b0e3290508a3e7bMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8920https://repositorio.ufmg.br/bitstream/1843/65401/2/license_rdf33b8016dc5c4681c1e7a582a4161162cMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/65401/3/license.txtcda590c95a0b51b4d15f60c9642ca272MD531843/654012024-03-06 18:31:22.088oai:repositorio.ufmg.br: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ório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2024-03-06T21:31:22Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
A stochastic approach to generate emergent behaviors in robotic swarms |
dc.title.alternative.pt_BR.fl_str_mv |
Uma abordagem estocástica para a criação de comportamentos emergentes em enxames robóticos |
title |
A stochastic approach to generate emergent behaviors in robotic swarms |
spellingShingle |
A stochastic approach to generate emergent behaviors in robotic swarms Paulo Alfredo Frota Rezeck Robotics Multi-agent system Swarm robotics Probabilistic robotics Computação – Teses Robótica – Teses Robôs – Sistema de controles – Teses |
title_short |
A stochastic approach to generate emergent behaviors in robotic swarms |
title_full |
A stochastic approach to generate emergent behaviors in robotic swarms |
title_fullStr |
A stochastic approach to generate emergent behaviors in robotic swarms |
title_full_unstemmed |
A stochastic approach to generate emergent behaviors in robotic swarms |
title_sort |
A stochastic approach to generate emergent behaviors in robotic swarms |
author |
Paulo Alfredo Frota Rezeck |
author_facet |
Paulo Alfredo Frota Rezeck |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Luiz Chaimowicz |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/4499928813481251 |
dc.contributor.referee1.fl_str_mv |
Douglas Guimarães Macharet |
dc.contributor.referee2.fl_str_mv |
Renato Martins Assunção |
dc.contributor.referee3.fl_str_mv |
Valdir Grassi Júnior |
dc.contributor.referee4.fl_str_mv |
David Julián Saldaña Santacruz |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/6192098741452112 |
dc.contributor.author.fl_str_mv |
Paulo Alfredo Frota Rezeck |
contributor_str_mv |
Luiz Chaimowicz Douglas Guimarães Macharet Renato Martins Assunção Valdir Grassi Júnior David Julián Saldaña Santacruz |
dc.subject.por.fl_str_mv |
Robotics Multi-agent system Swarm robotics Probabilistic robotics |
topic |
Robotics Multi-agent system Swarm robotics Probabilistic robotics Computação – Teses Robótica – Teses Robôs – Sistema de controles – Teses |
dc.subject.other.pt_BR.fl_str_mv |
Computação – Teses Robótica – Teses Robôs – Sistema de controles – Teses |
description |
In this dissertation, we present a novel methodology that extends the concepts of Gibbs Random Fields (GRFs) to the context of swarm robotics, allowing us to design control mechanisms that produce different swarm behaviors using only local information. In this context, a GRF is a probabilistic graph model that describes the interactions and behaviors of a group of robots. The robots are assumed to interact with each other in a way that can be described by a set of random variables. These variables define a random field, and the joint probability function is a Gibbs distribution that describes the probability of the swarm being in a given configuration. By using a Markov Chain Monte Carlo (MCMC) method, each robot sample velocity commands in a decentralized way, forcing them to move toward the global minimum of the potential, leading the entire swarm to converge to the desired behavior. This approach has several advantages over more traditional methods for controlling the behavior of a swarm. For example, it allows for decentralized control, where each robot makes decisions based on local information rather than relying on a central controller. This makes the system more robust and scalable, as there is no single point of failure, and the swarm can continue to operate even if individual robots fail. Additionally, it allows for a more flexible and adaptable approach to swarm behavior, as the potential function can be modified to account for changing environmental conditions or new goals for the swarm. To demonstrate the application of our methodology, we investigate the design of methods that tackle three significant challenges in swarm robotics: flocking and segregation, cooperative object transportation, and pattern formation. Numerical simulations and real-world experiments show that these methods are scalable, adaptable, and robust, even in the presence of noise, failures, and changes in the environment. More specifically, the first method shows to be able to adequately segregate a group of heterogeneous robots while keeping cohesive navigation and avoiding obstacles in the environment. The second method supports the transportation of objects of different shapes, sizes, and masses. It is also scalable and resilient to changes in goal location and robot failures. The third method experiments show the ability to create diverse patterns using different neighborhood constraints and that it may serve as a basis for more tangible applications such as the construction of chain or bridge-like structures using a swarm of heterogeneous robots. Overall, the proposed methodology shows promise for contributing to the field of swarm robotics, enabling the designing of mechanisms that adequately produce different behaviors of a swarm of robots. |
publishDate |
2023 |
dc.date.issued.fl_str_mv |
2023-12-04 |
dc.date.accessioned.fl_str_mv |
2024-03-06T21:31:21Z |
dc.date.available.fl_str_mv |
2024-03-06T21:31:21Z |
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 |
http://hdl.handle.net/1843/65401 |
url |
http://hdl.handle.net/1843/65401 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/3.0/pt/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/3.0/pt/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/65401/1/Tese_Doutorado_Paulo_Rezeck.pdf https://repositorio.ufmg.br/bitstream/1843/65401/2/license_rdf https://repositorio.ufmg.br/bitstream/1843/65401/3/license.txt |
bitstream.checksum.fl_str_mv |
ee8b7497ba8888f63b0e3290508a3e7b 33b8016dc5c4681c1e7a582a4161162c cda590c95a0b51b4d15f60c9642ca272 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589461080014848 |