BUSCADOR RECOLECTA

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.

With UAVs becoming increasingly popular in the industry, vertical take-off and landing
(VTOL) convertiplanes are emerging as a compromise between the advantages of planes and
multicopters. Due to their large wing surface area, VTOL convertiplanes are subject to a strong
wind dependence on critical phases such as take-off, landing, and hovering. Developing a
new and improved unmanned aerial vehicle (UAV) is often expensive and associated with
failures and accidents. This paper proposes the dynamic characterization of a commercial VTOL
convertiplane UAV in copter mode and provides a novel method to estimate the aerodynamic
forces and moments for any possible wind speed and direction. Starting from Euler’s equations
of rigid body dynamics, we have derived the mathematical formulation to precisely consider
aerodynamic forces and moments caused by any wind speed and direction. This unique
approach will allow for VTOL convertiplane UAVs to be trained and tested digitally in takeoff, hovering, and landing maneuvers without the cost and hassle of physical testing, and the
dependence on existing wind conditions. A digital twin of a VTOL convertiplane UAV in copter
mode has been modeled and tested in the Gazebo robotics simulator. Take-off, hovering and
landing maneuvers have been compared with and without the wind physics model. Finally, the
simulator has been tested against real flight conditions (reproducing the mean wind speed and
direction only), showing a natural and realistic behavior., This work has been supported in part by the Ministerio de Ciencia e Innovación (Spain) under the research grant RTI2018-095499-B-C31 IoTrain;
in part by Agencia Estatal de Investigación (AEI) and European Union NextGenerationEU/PRTR PLEC2021-007997: Holistic power lines predictive maintenance
system; and in part by the Government of Navarre (Departamento de Desarrollo Económico) 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.

New Unmanned Aerial Systems (UAS) applications will increase air traffic densities in metropolitan regions. Collision avoidance systems (CAS) are a key component in integrating a high number of UAS into the airspace in a safe way. This paper presents a distributed, autonomous, and knowledge-based CAS, called Dronetology System (DroS), for UASs. The CAS proposed here is managed using a novel ontology, called Dronetology-cas, which allows to make autonomous decisions according to the knowledge inferred from the data gathered by the UAS.

DroS is deployed as part of the payload of the UAS. So, it is designed to run in an embedded platform with limited processing capacity and low battery consumption. DroS collects data from sensors and collaborative elements to make smart decisions using knowledge obtained from collaborative UASs, adapting the maneuvers of the aerial vehicles to their original flight plans, their kind of vehicle, and the collision scenario. DroS accountability involves recording its internal operation to assist with reconstructing the circumstances surrounding an autonomous maneuver or the details previous to a collision. DroS has been verified using the hardware in the loop (HIL) technique with a UAS traffic environment simulator. Results obtained show a significant improvement in terms of safety by avoiding collisions., This work has been supported in part by the Ministerio de Ciencia e Innovación (Spain) under the research grant RTI2018-095499-B-C31 IoTrain; in part by Agencia Estatal de Investigación (AEI) and European Union NextGeneration EU/PRTR PLEC2021-007997: Holistic power lines predictive maintenance system; and in part by the Government of Navarre (Departamento de Desarrollo Económico) 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.

With the increasing popularity of vertical take-off and landing unmanned aerial vehicles (VTOL UAVs), a new problem arises: pilot training. Most conventional pilot training simulators are designed for full-scale aircrafts, while most UAV simulators are just focused on conceptual testing and design validation. The X-Plane flight simulator was extended to include new functionalities such as complex wind dynamics, ground effect, and accurate real-time weather. A commercial HIL flight controller was coupled with a VTOL convertiplane UAV model to provide realistic flight control. A real flight case scenario was tested in simulation to show the importance of including an accurate wind model. The result is a complete simulation environment that has been successfully deployed for pilot training of the Marvin aircraft manufactured by FuVeX., This work has been supported in part by the Ministerio de Ciencia e Innovación (Spain) under the research grants HOLISTIC PLEC2021-007997, CONDOR-Connected PID2021-127409OB-C31; in part by the Government of Navarre under the research grants PC109-110 NAITEST, DroneVC 0011-4218-2022-000006.

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.