Autonomous flight and computer vision system for a quadcopter in ROS 2

A software in the loop framework is proposed and implemented, focused on the simulation of a gate detection algorithm via computer vision, based on morphological operations for color segmentation, and a flight mission algorithm with trajectory tracking via waypoints, for a virtual autonomous quadcop...

Descripción completa

Detalles Bibliográficos
Autores: Ramírez-Linarez, Áxel, Torres-Rivera, Moisés
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/9021
Acceso en línea:https://repository.uaeh.edu.mx/revistas/index.php/icbi/article/view/9021
Access Level:acceso abierto
Palabra clave:computer vision
flight mission
waypoints
software in the loop
quadcopter
visión artificial
misión de vuelo
cuadricóptero
Descripción
Sumario:A software in the loop framework is proposed and implemented, focused on the simulation of a gate detection algorithm via computer vision, based on morphological operations for color segmentation, and a flight mission algorithm with trajectory tracking via waypoints, for a virtual autonomous quadcopter. In addition, a state-of-the-art open-source software set is integrated to validate the operation of the proposed algorithms within a flight circuit developed in a 3D simulation environment. It is observed that the performance of the artificial vision algorithm is acceptable under ideal conditions and at short distances, and that the quadcopter is capable of completing the flight circuit using the proposed methodology for trajectory management.