Hybrid model-based and data-driven wind velocity estimator for an autonomous robotic airship

Autor(es)

Marton, Apolo Silva ^[1] ; Fioravanti, Andre Ricardo ^[1] ; Azinheira, Jose Raul ^[2] ; de Paiva, Ely Carneiro ^[3]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Sch Mech Engn, Dept Computat Mech, Mendeleyev St 200, BR-13083180 Campinas - Brazil

^[2] Inst Super Tecn, Dept Mech Engn, P-1049001 Lisbon - Portugal

^[3] Univ Estadual Campinas, Sch Mech Engn, Dept Integrated Syst, Mendeleyev St 200, BR-13083180 Campinas - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Journal of the Brazilian Society of Mechanical Sciences and Engineering; v. 42, n. 3 FEB 19 2020.
• Citações Web of Science: 0

Resumo

In the context of autonomous airships, several works in control and guidance use wind velocity to design a control law. However, in general, this information is not directly measured in robotic airships. This paper presents three alternative versions for estimation of wind velocity. Firstly, an extended Kalman Filter is designed as a model-based approach. Then, a Neural Network is designed as a data-driven approach. Finally, a hybrid estimator is proposed by performing a fusion between the previous designed estimators: model-based and data-driven. All approaches consider only global positioning system, inertial measurement unit and a one-dimensional Pitot tube as available sensors. Simulations in a realistic nonlinear model of the airship suggest that the cooperation between these two techniques increases the estimation performance. (AU)

• Processo FAPESP: 14/50851-0 - INCT 2014: Instituto Nacional de Ciência e Tecnologia para Sistemas Autônomos Cooperativos Aplicados em Segurança e Meio Ambiente
• Beneficiário: Marco Henrique Terra
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/11423-0 - Abordagens de guiamento e planejamento de trajetória para a navegação de um dirigível autônomo em aplicações ambientais na Amazônia
• Beneficiário: Ely Carneiro de Paiva
• Modalidade de apoio: Bolsas no Exterior - Pesquisa