Exploration and Rescue of Shipwreck Survivors using Reinforcement Learning-Empowered Drone Swarms

Página do item simplificado
dc.contributor.authorAbreu, Leonardo D. M. de
dc.contributor.authorCarrete, Luis F. S.
dc.contributor.authorCastanares, Manuel
dc.contributor.authorDamiani, Enrico F.
dc.contributor.authorBrancalion, Jose Fernando B.
dc.contributor.authorBarth, Fabrício J.
dc.creatorAbreu, Leonardo D. M. de
dc.creatorCarrete, Luis F. S.
dc.creatorCastanares, Manuel
dc.creatorDamiani, Enrico F.
dc.creatorBrancalion, Jose Fernando B.
dc.creatorBarth, Fabrício J.
dc.date.accessioned2025-01-08T17:17:20Z
dc.date.available2025-01-08T17:17:20Z
dc.date.issued2023
dc.description.abstractThe goal of this project is to create a reinforcement learning algorithm that locates shipwrecked individuals using a swarm of drones. A simulated environment was developed to train and visualize the outcome of the trained algorithm considering the ocean’s dynamic circumstances. This project does not discuss image recognition of shipwrecked people, since the true focus of this project is to optimize the search routine of a drone to find the target in the most efficient way possible. The implemented Reinforce algorithm takes into account a dynamic map of probabilities, representing the chances of a person being found, as well as the position of other agents. Outcomes include an open-source Python package for the environment and the implementation of the reinforcement learning algorithm. The algorithm demonstrates superiority over the predefined approach, proving the advantages of reinforcement learning in efficiency and effectiveness.en
dc.formatDigital
dc.format.extent6 p.
dc.identifier.issn1983-7402
dc.identifier.urihttps://repositorio.insper.edu.br/handle/11224/7246
dc.language.isoInglês
dc.subjectMulti-Agent Systemsen
dc.subjectReinforcement Learningen
dc.subjectSimulationen
dc.titleExploration and Rescue of Shipwreck Survivors using Reinforcement Learning-Empowered Drone Swarms
dc.typeconference paper
dspace.entity.typePublication
local.description.eventXXV Simpósio de Aplicações Operacionais em Áreas de Defesa
local.identifier.sourceUrihttps://www.sige.ita.br/#
local.publisher.countryNão Informado
local.typeTrabalho de Evento
Arquivos
Pacote Original
Agora exibindo 1 - 2 de 2
N/D
Nome:
Primeira_Pagina_Trabalho_de_Evento_2023_Exploration_and_rescue_of_shipwreck_survivors_using_reinforcement_learning_empowered_drone_swarms_TC.pdf
Tamanho:
651.32 KB
Formato:
Adobe Portable Document Format
Baixar
N/D
Nome:
ACESSO_RESTRITO_Trabalho_de_Evento_2023_Exploration_and_rescue_of_shipwreck_survivors_using_reinforcement_learning_empowered_drone_swarms_TC.pdf
Tamanho:
1.37 MB
Formato:
Adobe Portable Document Format
Baixar
Licença do Pacote
Agora exibindo 1 - 1 de 1
N/D
Nome:
license.txt
Tamanho:
236 B
Formato:
Item-specific license agreed upon to submission
Descrição:
Baixar
Coleções
Coleção de Trabalhos Apresentados em Eventos