Solving drone tasks in simulators

In this paper we present solutions to some of the tests included in drone competitions, in particular we consider the tests held in the Mexican Robotics Tournament of the Mexican Federation of Robotics in the virtual drone category. In this context, this work shows the development of some academic a...

Descripción completa

Detalles Bibliográficos
Autores: Cureño-Ramirez, Andres, Juárez-Terrazas, Aarón, Arellano-Aguilar, Rudyard Samuel, Ibarra-Zannatha, Juan Manuel
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:México
Institución:UNIVERSIDAD AUTÓNOMA DEL ESTADO DE HIDALGO
Repositorio:PÄDI Boletín Científico de Ciencias Básicas e Ingeniería del ICBI
Idioma:español
OAI Identifier:oai:repository.uaeh.edu.mx:article/9273
Acceso en línea:https://repository.uaeh.edu.mx/revistas/index.php/icbi/article/view/9273
Access Level:acceso abierto
Palabra clave:Autonomous Drones
Computer vision
Drone simulators
ROS
Drones autónomos
Visión por computadora
Simuladores de drones
Descripción
Sumario:In this paper we present solutions to some of the tests included in drone competitions, in particular we consider the tests held in the Mexican Robotics Tournament of the Mexican Federation of Robotics in the virtual drone category. In this context, this work shows the development of some academic applications that have been included in these competitions at national level. Thus, the tests included in this work are: flight over specific points along a path, 3D reconstruction of objects in the environment, flight between windows and formation flying. To solve these tests, computer vision, simultaneous localisation and mapping, traditional control, 3D reconstruction, route planning and machine learning techniques must be used. All of them have been working virtually in different simulators such as Gazebo and AirSim under ROS.