Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Repositorio Instituc...arrow_drop_down
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
addClaim

Formación Adaptativa de Sistemas de Enjambres de Drones por Medio de la Técnica de Pastoreo

Authors: Macias Cifuentes, Edson Farid;

Formación Adaptativa de Sistemas de Enjambres de Drones por Medio de la Técnica de Pastoreo

Abstract

Este proyecto se basa en el diseño y la implementación de sistemas adaptativos de enjambres de drones utilizando técnicas de pastoreo. El objetivo principal es desarrollar métodos eficientes para controlar y coordinar múltiples drones, que puedan evadir obstáculos y que puedan ser guiados a un área de cobertura por otro grupo de agentes denominados pastores. Se utilizan algoritmos como Boids y técnicas de aprendizaje por refuerzo, incluyendo Q-learning y Aprendizaje por Refuerzo Multiagente (MARL). Del mismo modo se modificaron y se hicieron mejoras a los algoritmos con el fin de obtener mejores resultados. Las simulaciones se realizan en entornos como CoppeliaSIM, validando experimentalmente la eficacia de las técnicas propuestas. Los resultados demuestran mejoras significativas en la coordinación y eficiencia de los enjambres de drones comparados con metodologías tradicionales.

This project is based on the design and implementation of adaptive swarm systems of drones using herding techniques. The main objective is to develop efficient methods to control and coordinate multiple drones that can avoid obstacles and be guided to a coverage area by another group of agents called shepherds. Algorithms such as Boids and reinforcement learning techniques, including Q-learning and Multi-Agent Reinforcement Learning (MARL), are used. Similarly, modifications and improvements were made to the algorithms to achieve better results. Simulations are conducted in environments like CoppeliaSIM, experimentally validating the effectiveness of the proposed techniques. The results demonstrate significant improvements in the coordination and efficiency of drone swarms compared to traditional methodologies.

Magister en Ingeniería Electrónica

Maestría

Country
Colombia
Related Organizations
Keywords

MARL, Pastoreo de Drones, Algoritmos -- Boids, Ingeniería Electrónica, Drone Swarm, Boids, Diseño -- Drones, Aprendizaje por Refuerzo, Herding, Enjambres de Drones, Q-Learning, Reinforcement Learning

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!