Controle H infinito não linear adaptativo baseado em processos gaussianos para quadrotor

• Ano de defesa: 2023
• Autor(a) principal: Oliveira, Guilherme Rossi de Avelar
• Orientador(a): Inoue, Roberto Santos
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos; Câmpus São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Engenharia Elétrica - PPGEE
• Palavras-chave em Português: Quadrotor; Controle; Escala; Robusto; Adaptativo; Processos Gaussianos
• Palavras-chave em Inglês: Gaussian Process; Tracking; Control; H Infinity
• Área do conhecimento CNPq: ENGENHARIAS::ENGENHARIA ELETRICA; ENGENHARIAS::ENGENHARIA AEROESPACIAL::SISTEMAS AEROESPACIAIS::HOVERCRAFT
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/17785

The use of Unmanned Aerial Vehicles (UAVs), may be subject to external disturbances, such as wind gusts, aerodynamic forces, and parametric uncertainties, depending on the location where it is to be used. Therefore, the automatic control must be robust enough to perform a pre-established task. In this work, we propose a robust control strategy based on the dynamic model to mitigate external disturbances and parametric uncertainties. The H Infinity criterion has been used for other types of robots and will be applied to quadrotor aircraft in this work. In addition to this robust character of the adopted control criterion, this work uses Gaussian processes to complement the mathematical model of the quadrotor, estimating the uncertainties not modeled by the nominal model. This combination is backed up by ensuring the stability of the resulting robust control system. An analysis of the trajectory tracking of all controllers is made, considering different levels of parametric uncertainty and external disturbances. Along with the development of the controllers, a complete study is made about the implementation of control algorithms on a real quadrotor, proposing a localization system based on the odometry of the aircraft and on a visual SLAM algorithm, using the camera present in it.