Autor(es)

Arantes, Jesimar da Silva ; Arantes, Marcio da Silva ; Missaglia, Andre Badawi ; Simoes, Eduardo do Valle ; Motta Toledo, Claudio Fabiao ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2017 IEEE 29TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2017); v. N/A, p. 8-pg., 2017-01-01.

Resumo

The present paper evaluates some strategies to apply path re-planning algorithms for emergency landing of Unmanned Aerial Vehicles (UAVs). The strategies proposed are based on executing only one path re-planning algorithm or a combination of them using an ensemble approach. The proposed methods are integrated to the security supervision system of the UAV, namely In-Fly Awareness (IFA), where decision-making algorithms are applying after a critical situation happens. The critical situations considered are battery overheating and engine failure. The performance of the proposed strategies for emergency landing is evaluated in a real world scenario using the Software-In-The-Loop (SITL) technique. Computational results reported show that these strategies are promising based on the success rate to land the UAV safely. (AU)

• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 14/11331-0 - Hybrid qualitative state plan problem e o planejamento de missão com VANTs
• Beneficiário: Márcio da Silva Arantes
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 15/23182-2 - Sistema autônomo para supervisão de missão e segurança de voo em VANTs
• Beneficiário: Jesimar da Silva Arantes
• Modalidade de apoio: Bolsas no Brasil - Doutorado