Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

On constructing efficient UAV aerodynamic surrogate models for digital twins

  • Aláez Gómez, Daniel
  • Prieto Míguez, Manuel
  • Villadangos Alonso, Jesús
  • Astrain Escola, José Javier
Aerodynamic modeling and optimization for unmanned aerial vehicles (UAVs) are complex and computationally intensive tasks. Surrogate models have emerged as a powerful tool for increasing efficiency in the aircraft design and optimization process. We review and evaluate some modeling techniques, such as artificial neural networks and support vector regression, showing that Gaussian process regression generally provides a well-performing solution to this type of problem. We propose an active learning algorithm based on the relevance factor, that combines bias estimated from nearest-neighbor Euclidean distance and variance, to achieve higher accuracy with fewer compuational fluid dynamics (CFD) simulations. The obtained performance is evaluated using four 2-D test functions and an experimental CFD case, indicating that the proposed active learning approach outperforms classical random sampling techniques. Thanks to this architecture, the development process of a new commercial UAV can be significantly streamlined by expediting the testing phase through the use of DTs modeled more efficiently., This work was supported in part by European Union NextGenerationEU/PRTRMCIN/AEI/10.13039/501100011033, Holistic power lines predictive maintenance system under Grant PLEC2021-007997, in part by the CONDOR-Connected under Grant TED2021-131716B-C21 SARA and Grant PID2021-127409OB-C31, and in part by the Government of Navarre (Departamento de Desarrollo Economico) under the research Grant PC109-110 NAITEST. Paper no. TII-24-2116.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Dronetology: a domain ontology for UAS applications

  • Martín Lammerding, David
  • Astrain Escola, José Javier
  • Córdoba Izaguirre, Alberto
The increasing importance of Unmanned Aerial Systems (UAS) has led to the development of various applications, resulting in significant fragmentation in technologies, components, and data formats. The UAS domain must meet stringent requirements regarding safety, regulatory compliance, and interoperability with other systems. It also faces challenges such as efficiency, airspace sharing, scalability, awareness of other aircraft, and effective data analysis. Semantic technologies provide solutions for these challenges, offering interoperability and intelligent decision-making. Ontologies stand out for their ability to model knowledge and facilitate understanding within the UAS domain. This paper introduces Dronetology, https://dronetology.net/dronetology, a domain ontology designed to provide a common framework for UAS concepts. It aims to improve interoperability, data quality, and knowledge integration. Dronetology has been implemented in a decision support prototype using an expert system architecture to address complex UAS use cases, including flight efficiency, collision avoidance, and compliance with regulations. We also outline how Dronetology can be specialized to create application ontologies for specific UAS needs., This work has been supported in part by the Ministerio de Ciencia e Innovaci\u00F3n (Spain), Agencia Estatal de Investigaci\u00F3n (Spain) and European Union NextGenerationEU under the research grants TED2021-131716B-C21: SARA (SAfe and Reliable flights for superesolution image Analysis) and PLEC 2021\u2013007997:Holistic power lines predictive maintenance system; and in part by Agencia Estatal de Investigaci\u00F3n (Spain) and European Union (European Regional Development Fund) under the research grant PID2021-127409OB-C31: Condor-Connected.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Digital twin modelling of open category UAV radio communications: a case study

  • Aláez Gómez, Daniel
  • Iturri López, Peio
  • Celaya Echarri, Mikel
  • Azpilicueta Fernández de las Heras, Leyre
  • Falcone Lanas, Francisco
  • Villadangos Alonso, Jesús
  • Astrain Escola, José Javier
The modeling of radio links plays a crucial role in achieving mission success of unmanned aerial vehicles (UAVs). By simulating and analyzing communication performance, operators can anticipate and address potential challenges. In this paper, we propose a full-featured UAV software-in-the-loop digital twin (SITL-DT) for a heavy-lifting hexacopter that integrates a radio link module based on an experimental path loss model for ‘Open’ category Visual Line of Sight (VLOS) conditions and drone-antenna radiation diagrams obtained via electromagnetic simulation. The main purpose of integrating and simulating a radio link is to characterize when the communication link can be conflicting due to distance, the attitude of the aircraft relative to the pilot, and other phenomena. The system architecture, including the communications module, is implemented and validated based upon experimental flight data., This work has been supported in part by Grant No. RYC2021-031949-I funded by MCIN/AEI/10.13039/501100011033, Spain and NextGeneration EU/PRTR; in part by the Ministerio de Ciencia e Innovación (Spain) under the research grants TED2021-131716B-C21 SARA, CONDOR-Connected PID2021-127409OB-C31; and in part by the Government of Navarre (Departamento de Desarrollo Económico), Spain under the research grant PC109-110 NAITEST. Open access funding provided by Universidad Pública de Navarra.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Quadcopter neural controller for take-off and landing in windy environments

  • Olaz Moratinos, Xabier
  • Aláez Gómez, Daniel
  • Prieto Míguez, Manuel
  • Villadangos Alonso, Jesús
  • Astrain Escola, José Javier
This paper proposes the design of a quadcopter neural controller based on Reinforcement Learning (RL) for controlling the complete maneuvers of landing and take-off, even in variable windy conditions. To facilitate RL training, a wind model is designed, and two RL algorithms, Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO), are adapted and compared. The first phases of the learning process consider extended exploration states as a warm-up, and a novel neural network controller architecture is proposed with the addition of an adaptation layer. The neural network’s output is defined as the forces and momentum desired for the UAV, and the adaptation layer transforms forces and momentum into motor velocities. By decoupling attitude from motor velocities, the adaptation layer enhances a more straightforward interpretation of the neural network output and helps refine the rewards. The successful neural controller training has been tested up to 36 km/h wind speed., This work has been supported in part by the Ministerio de Ciencia e Innovación (Spain) and European Union NextGenerationEU, Spain under the research grant TED2021-131716B-C21 SARA (Data processing by superresolution algorithms); in part by Agencia Estatal de Investigación (AEI), Spain and European Union NextGenerationEU/PRTR, Spain PLEC2021-007997: Holistic power lines predictive maintenance system; and in part by the Government of Navarre (Departamento de Desarrollo Económico), Spain under the research grants 0011-1411-2021-000021 EMERAL: Emergency UAVs for long range operations, 0011-1365-2020-000078 DIVA, and 0011-1411-2021-000025 MOSIC: Plataforma logística de largo alcance, eléctrica y conectada.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Uniform expansions of the third symmetric standard elliptic integral

  • Bujanda Cirauqui, Blanca
  • López García, José Luis
  • Pagola Martínez, Pedro Jesús
  • Palacios Herrero, Pablo
We consider the third symmetric standard elliptic integral RJ (x, y, z, p) for complex values of its variables. By homogeneity arguments, this function is indeed a function of only three variables, and we derive two different integral representations of RJ (x, y, z, p) which only involve three variables. Both integral representations are suitable for the analysis introduced in [Lopez, Pagola and Palacios, 2021] to derive uniform expansions of parametric integrals. Using this theory, we derive six convergent expansions of this function in terms of elementary functions; two of these expansions also involve the other two symmetric standard elliptic integrals RF (x, y, z) and RD(x, y, z). These expansions hold uniformly for one or two of the variables in large closed unbounded subsets of C \ (−∞, 0]. These expansions are accompanied by error bounds, and their accuracy and uniform features are illustrated by means of some numerical experiments., Open Access funding provided by Universidad Pública de Navarra. This research was supported by the projects TED2021-131716B-C21 and PC109-110 NAITEST, and also by the Spanish Ministerio de Ciencia, Innovación y Universidades through the projects PID2022-136441NB-I00 and PID2021-127409OB-C31.