Person:
Prieto Míguez, Manuel

Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Prieto Míguez

First Name

Manuel

person.page.departamento

Automática y Computación

ORCID

0000-0002-7183-0883

person.page.upna

2689

Name

Filters

20232
Reset filters

Settings

Author: Astrain Escola, José Javier × Start date: 2022 ×

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    VTOL UAV digital twin for take-off, hovering and landing in different wind conditions
    (Elsevier, 2023) Aláez Gómez, Daniel; Olaz Moratinos, Xabier; Prieto Míguez, Manuel; Villadangos Alonso, Jesús; Astrain Escola, José Javier; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Gobierno de Navarra / Nafarroako Gobernua
    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.
  • No Thumbnail Available
    PublicationEmbargo
    Quadcopter neural controller for take-off and landing in windy environments
    (Elsevier, 2023) Olaz Moratinos, Xabier; Aláez Gómez, Daniel; Prieto Míguez, Manuel; Villadangos Alonso, Jesús; Astrain Escola, José Javier; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
    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.