High-level subsumption-based control architecture for sail-powered autonomous surface vehicles
This work proposes a high-level control architecture for an Autonomous Surface Vessel (ASV) designed to overcome the challenges associated with executing missions under varying weather conditions and with energy autonomy. The project is built on the understanding that while a number of low-level con...
Enregistré dans:
Auteur principal: | |
---|---|
Autres auteurs: | |
Format: | doctoralThesis |
Langue: | English |
Publié: |
Universidade Federal do Rio Grande do Norte
|
Sujets: | |
Accès en ligne: | https://repositorio.ufrn.br/handle/123456789/55159 |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
id |
ri-123456789-55159 |
---|---|
record_format |
dspace |
institution |
Repositório Institucional |
collection |
RI - UFRN |
language |
English |
topic |
Veleiros USV Arquitetura de controle Arquitetura de subsunção ROS Gazebo Reinforce Learning PPO Sailboats Control architectures Subsumption CNPQ::CIENCIAS EXATAS E DA TERRA |
spellingShingle |
Veleiros USV Arquitetura de controle Arquitetura de subsunção ROS Gazebo Reinforce Learning PPO Sailboats Control architectures Subsumption CNPQ::CIENCIAS EXATAS E DA TERRA Negreiros, Álvaro Pinto Fernandes de High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
description |
This work proposes a high-level control architecture for an Autonomous Surface Vessel (ASV) designed to overcome the challenges associated with executing missions under varying weather conditions and with energy autonomy. The project is built on the understanding that while a number of low-level control techniques are readily available as open source, there remains a need for a high-level control architecture. This architecture would facilitate the creation of a resilient, versatile sailing vessel capable of handling any mission without requiring the user to master navigation specifics, naval procedures, or corner cases. The proposed solution involves developing a control architecture inspired by sub- sumption, and centered on hierarchical behaviors. This structure incorporates a variety of specialized behaviors adapted to different contexts, each of which is established using reinforcement learning techniques (PPO). A combination of Gazebo simulation environment with the ROS framework for training was used to validate the proposed architecture. This simulation enables the digital replication of the vessel’s behaviors, which simplifies the implementation process and mitigates the challenges and costs tied to real-world sailing operations. The simulation results of this study indicate that the high-level control architecture of the virtual sailing vessel was successful in passing both perimeter scanning and long-distance tests. This suggests that the ASV is equipped to navigate the several situations it might encounter in real-world missions |
author2 |
Gonçalves, Luiz Marcos Garcia |
author_facet |
Gonçalves, Luiz Marcos Garcia Negreiros, Álvaro Pinto Fernandes de |
format |
doctoralThesis |
author |
Negreiros, Álvaro Pinto Fernandes de |
author_sort |
Negreiros, Álvaro Pinto Fernandes de |
title |
High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
title_short |
High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
title_full |
High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
title_fullStr |
High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
title_full_unstemmed |
High-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
title_sort |
high-level subsumption-based control architecture for sail-powered autonomous surface vehicles |
publisher |
Universidade Federal do Rio Grande do Norte |
publishDate |
2023 |
url |
https://repositorio.ufrn.br/handle/123456789/55159 |
work_keys_str_mv |
AT negreirosalvaropintofernandesde highlevelsubsumptionbasedcontrolarchitectureforsailpoweredautonomoussurfacevehicles |
_version_ |
1781992017484578816 |
spelling |
ri-123456789-551592023-11-03T22:17:07Z High-level subsumption-based control architecture for sail-powered autonomous surface vehicles Negreiros, Álvaro Pinto Fernandes de Gonçalves, Luiz Marcos Garcia https://orcid.org/0000-0001-8162-7144 http://lattes.cnpq.br/1359449865610489 https://orcid.org/0000-0002-7735-5630 http://lattes.cnpq.br/1562357566810393 Vasconcelos, Eduardo Charles http://lattes.cnpq.br/9622415604083776 Santos, Davi Henrique dos https://orcid.org/0000-0002-4286-235X http://lattes.cnpq.br/5492310878477548 https://orcid.org/0000-0001-5650-1718 http://lattes.cnpq.br/4791589931798048 Silva, João Moreno Vilas Boas de Souza https://orcid.org/0000-0002-3200-6605 http://lattes.cnpq.br/8722766030280997 Alsina, Pablo Javier https://orcid.org/0000-0002-2882-5237 http://lattes.cnpq.br/3653597363789712 Veleiros USV Arquitetura de controle Arquitetura de subsunção ROS Gazebo Reinforce Learning PPO Sailboats Control architectures Subsumption CNPQ::CIENCIAS EXATAS E DA TERRA This work proposes a high-level control architecture for an Autonomous Surface Vessel (ASV) designed to overcome the challenges associated with executing missions under varying weather conditions and with energy autonomy. The project is built on the understanding that while a number of low-level control techniques are readily available as open source, there remains a need for a high-level control architecture. This architecture would facilitate the creation of a resilient, versatile sailing vessel capable of handling any mission without requiring the user to master navigation specifics, naval procedures, or corner cases. The proposed solution involves developing a control architecture inspired by sub- sumption, and centered on hierarchical behaviors. This structure incorporates a variety of specialized behaviors adapted to different contexts, each of which is established using reinforcement learning techniques (PPO). A combination of Gazebo simulation environment with the ROS framework for training was used to validate the proposed architecture. This simulation enables the digital replication of the vessel’s behaviors, which simplifies the implementation process and mitigates the challenges and costs tied to real-world sailing operations. The simulation results of this study indicate that the high-level control architecture of the virtual sailing vessel was successful in passing both perimeter scanning and long-distance tests. This suggests that the ASV is equipped to navigate the several situations it might encounter in real-world missions CAPES Propomos uma arquitetura de controle de alto nível para uma Embarcação Autônoma de Superfície (USV) projetada para superar os desafios associados à execução de missões sob condições climáticas variadas e com autonomia energética. O projeto é construído com base no entendimento de que, embora várias técnicas de controle de baixo nível estejam prontamente disponíveis como código-fonte aberto, ainda existe a necessidade de uma arquitetura de controle de alto nível. Essa arquitetura facilita a criação de um veleiro resiliente e versátil, capaz de lidar com qualquer missão sem exigir que o usuário domine detalhes de navegação, procedimentos navais ou casos de borda. A solução proposta envolve o desenvolvimento de uma arquitetura de controle inspirada na arquitetura subsunção e centrada em comportamentos hierárquicos. Essa estrutura incorpora uma variedade de comportamentos especializados adaptados a diferentes contextos, cada um dos quais é estabelecido usando técnicas de aprendizado por reforço (PPO). Uma combinação do ambiente de simulação Gazebo com o framework ROS para treinamento foi utilizada para validar a arquitetura proposta. Essa simulação permite a replicação digital dos comportamentos da embarcação, o que simplifica o processo de implementação e mitiga os desafios e custos vinculados às operações de navegação no mundo real. Os resultados deste estudo indicam que a arquitetura de controle de alto nível foi bem-sucedida em um veleiro virtual, tanto na verificação de percursos de perímetro quanto nos testes de longa distância. Isso sugere que o USV está equipado para navegar em diversas situações que pode encontrar em missões do mundo real. 2023-11-03T22:15:25Z 2023-11-03T22:15:25Z 2023-08-04 doctoralThesis NEGREIROS, Álvaro Pinto Fernandes de. High-level subsumption-based control architecture for sail-powered autonomous surface vehicles. 2023. 168f. Orientador: Dr. Luiz Marcos Garcia Gonçalves. Tese (Doutorado em Engenharia Elétrica e Computação) - Universidade Federal do Rio Grande do Norte, Centro de Tecnologia, Programa de Pós-graduação em Engenharia Elétrica e Computação, Natal, 2023. https://repositorio.ufrn.br/handle/123456789/55159 en Acesso Aberto application/pdf Universidade Federal do Rio Grande do Norte Brasil UFRN Programa de Pós-graduação em Engenharia Elétrica e de Computação |