Emergency Landing Spot Detection for Unmanned Aerial Vehicle
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.22/16804 |
Resumo: | The use and research of Unmanned Aerial Vehicle (UAV) have been increasing over the years due to the applicability in several operations such as search and rescue, delivery, surveillance and others. Considering the increased presence of these vehicles in the airspace, it becomes necessary to reflect on the safety issues or failures that UAV may have and what is the appropriate action to take. Furthermore, in many missions the vehicle will not return to its original location and, in case of fail to achieve the landing spot, need to have onboard capability to estimate the best spot to safely land. The vehicles are susceptible to external disturbance or electromechanical malfunction. In this emergency’s scenarios, UAVs must safely land in a way that will minimize damage to the robot and will not cause any human injury. The suitability of a landing site depends on two main factors: the distance of the aircraft to the landing site and the ground conditions. The ground conditions are all the factors that are relevant when the aircraft is in contact with the ground, such as slope, roughness and presence of obstacles. This dissertation addresses the scenario of finding a safe landing spot during operation. Therefore, the algorithm must be able to classify the incoming data and store the location of suitable areas. Specifically, by processing Light Detection and Ranging (LiDAR) data to identify potential landing zones and evaluating the detected spots continuously given certain conditions. In this dissertation, it was developed a method that analyses geometric features on point cloud data and detects potential good spots. The algorithm uses the Principal Component Analysis (PCA) to find planes in point clouds clusters. The planes that have slope less than a threshold are considered potential landing spots. These spots are then evaluated regarding ground and vehicles conditions such as the distance to the UAV, presence of obstacles, roughness of the area, slope of the spot. The output of the algorithm is the optimum spot to land and can vary during operation. |
id |
RCAP_efaa37c904db6fbc6df5ad334abf2152 |
---|---|
oai_identifier_str |
oai:recipp.ipp.pt:10400.22/16804 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Emergency Landing Spot Detection for Unmanned Aerial VehicleUnmanned aerial vehicleLiDARLanding spots detectionEmergency landingPoint cloudVeículos aéreos não tripuladosDeteção de pontos de aterragemAterragem de emergênciaNuvem de pontosThe use and research of Unmanned Aerial Vehicle (UAV) have been increasing over the years due to the applicability in several operations such as search and rescue, delivery, surveillance and others. Considering the increased presence of these vehicles in the airspace, it becomes necessary to reflect on the safety issues or failures that UAV may have and what is the appropriate action to take. Furthermore, in many missions the vehicle will not return to its original location and, in case of fail to achieve the landing spot, need to have onboard capability to estimate the best spot to safely land. The vehicles are susceptible to external disturbance or electromechanical malfunction. In this emergency’s scenarios, UAVs must safely land in a way that will minimize damage to the robot and will not cause any human injury. The suitability of a landing site depends on two main factors: the distance of the aircraft to the landing site and the ground conditions. The ground conditions are all the factors that are relevant when the aircraft is in contact with the ground, such as slope, roughness and presence of obstacles. This dissertation addresses the scenario of finding a safe landing spot during operation. Therefore, the algorithm must be able to classify the incoming data and store the location of suitable areas. Specifically, by processing Light Detection and Ranging (LiDAR) data to identify potential landing zones and evaluating the detected spots continuously given certain conditions. In this dissertation, it was developed a method that analyses geometric features on point cloud data and detects potential good spots. The algorithm uses the Principal Component Analysis (PCA) to find planes in point clouds clusters. The planes that have slope less than a threshold are considered potential landing spots. These spots are then evaluated regarding ground and vehicles conditions such as the distance to the UAV, presence of obstacles, roughness of the area, slope of the spot. The output of the algorithm is the optimum spot to land and can vary during operation.O uso e pesquisa de veículos aéreos não tripulados (VANT) têm aumentado ao longo dos anos devido à aplicabilidade em diversas operações, como busca e salvamento, entrega, vigilância e outras. Considerando a crescente presença desses veículos no espaço aéreo, torna-se necessário refletir sobre os problemas ou falhas de segurança que o veículo pode ter e qual é a ação apropriada a ser tomada. Além disso, em muitas missões, o veículo não retornará ao seu local original e, caso não seja possível alcançar a zona de aterragem, precisa ter a capacidade de estimar o melhor ponto para aterrar em segurança. Os veículos são suscetíveis a perturbações externas ou mau funcionamento eletromecânico. Nesses cenários de emergência, os UAVs precisam aterrar com segurança de forma a minimizar os danos ao robô e não causar ferimentos em pessoas. A adequação de um local de pouso depende de dois fatores principais: a distância do veículo aéreo ao local de pouso e as condições do solo. As condições do solo são todos os fatores relevantes quando a aeronave está em contacto com o solo, como declividade, rugosidade e presença de obstáculos. Esta dissertação aborda o cenário de encontrar um local de pouso seguro durante a operação. Portanto, o algoritmo deve ser capaz de classificar os dados recebidos e armazenar a localização de áreas adequadas. Especificamente, processando dados de LiDAR para identificar possíveis zonas de aterragem e avaliando os pontos detetados continuamente, dadas determinadas condições. Nesta dissertação, foi desenvolvido um método que analisa características geométricas em nuvem de pontos e deteta possíveis bons locais de aterragem. O algoritmo usa a Análise de Componente Principal (PCA) para encontrar planos em clusters de nuvens de pontos. Os planos com inclinação menor que um limite são considerados possíveis pontos de aterragem. Esses pontos são então avaliados quanto às condições do solo e dos veículos, como a distância ao UAV, presença de obstáculos, rugosidade da área, inclinação do ponto. A saída do algoritmo é o local ideal para aterrar e pode variar durante a operação.Dias, André Miguel PinheiroRepositório Científico do Instituto Politécnico do PortoLoureiro, Gabriel da Silva Martins2021-02-01T11:28:19Z20202020-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.22/16804TID:202549933enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-13T13:04:29Zoai:recipp.ipp.pt:10400.22/16804Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:36:26.830632Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
title |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
spellingShingle |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle Loureiro, Gabriel da Silva Martins Unmanned aerial vehicle LiDAR Landing spots detection Emergency landing Point cloud Veículos aéreos não tripulados Deteção de pontos de aterragem Aterragem de emergência Nuvem de pontos |
title_short |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
title_full |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
title_fullStr |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
title_full_unstemmed |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
title_sort |
Emergency Landing Spot Detection for Unmanned Aerial Vehicle |
author |
Loureiro, Gabriel da Silva Martins |
author_facet |
Loureiro, Gabriel da Silva Martins |
author_role |
author |
dc.contributor.none.fl_str_mv |
Dias, André Miguel Pinheiro Repositório Científico do Instituto Politécnico do Porto |
dc.contributor.author.fl_str_mv |
Loureiro, Gabriel da Silva Martins |
dc.subject.por.fl_str_mv |
Unmanned aerial vehicle LiDAR Landing spots detection Emergency landing Point cloud Veículos aéreos não tripulados Deteção de pontos de aterragem Aterragem de emergência Nuvem de pontos |
topic |
Unmanned aerial vehicle LiDAR Landing spots detection Emergency landing Point cloud Veículos aéreos não tripulados Deteção de pontos de aterragem Aterragem de emergência Nuvem de pontos |
description |
The use and research of Unmanned Aerial Vehicle (UAV) have been increasing over the years due to the applicability in several operations such as search and rescue, delivery, surveillance and others. Considering the increased presence of these vehicles in the airspace, it becomes necessary to reflect on the safety issues or failures that UAV may have and what is the appropriate action to take. Furthermore, in many missions the vehicle will not return to its original location and, in case of fail to achieve the landing spot, need to have onboard capability to estimate the best spot to safely land. The vehicles are susceptible to external disturbance or electromechanical malfunction. In this emergency’s scenarios, UAVs must safely land in a way that will minimize damage to the robot and will not cause any human injury. The suitability of a landing site depends on two main factors: the distance of the aircraft to the landing site and the ground conditions. The ground conditions are all the factors that are relevant when the aircraft is in contact with the ground, such as slope, roughness and presence of obstacles. This dissertation addresses the scenario of finding a safe landing spot during operation. Therefore, the algorithm must be able to classify the incoming data and store the location of suitable areas. Specifically, by processing Light Detection and Ranging (LiDAR) data to identify potential landing zones and evaluating the detected spots continuously given certain conditions. In this dissertation, it was developed a method that analyses geometric features on point cloud data and detects potential good spots. The algorithm uses the Principal Component Analysis (PCA) to find planes in point clouds clusters. The planes that have slope less than a threshold are considered potential landing spots. These spots are then evaluated regarding ground and vehicles conditions such as the distance to the UAV, presence of obstacles, roughness of the area, slope of the spot. The output of the algorithm is the optimum spot to land and can vary during operation. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 2020-01-01T00:00:00Z 2021-02-01T11:28:19Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.22/16804 TID:202549933 |
url |
http://hdl.handle.net/10400.22/16804 |
identifier_str_mv |
TID:202549933 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799131455800999936 |