Drone Behavior Inspired Optimization: A Multi-Agent Search Algorithm with Local Reconnaissance, Global Collaboration, and Environmental Perturbation

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: Zhang, Jincheng
Format: Recurso digital
Published: Zenodo 2025
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901563954429952
author Zhang, Jincheng
author_facet Zhang, Jincheng
contents <p><span>This paper proposes a new optimization algorithm, the core idea of</span> <span>which is derived from the behavioral characteristics of multiple UAVs flying and executing missions in complex environments. Unlike traditional particle swarm optimization, genetic algorithm, or ant colony algorithm, this algorithm fully simulates the local reconnaissance, global collaboration, airflow disturbance, and formation intelligence mechanisms of UAVs, mapping them into the optimization search process, thereby achieving efficient search for the global optimal solution. The algorithm design introduces a multi-level dynamic model and environmental perception mechanism, and proposes a complete set of mathematical formulas, including velocity update, position update, local reconnaissance attraction, global collaboration attraction, airflow disturbance, and formation collaboration mechanism. This paper elaborates on the algorithm's theoretical model, mathematical formula derivation, and multi-strategy adaptive control strategy, providing a systematic theoretical basis for the research of UAV heuristic optimization algorithms.</span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17493690
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Drone Behavior Inspired Optimization: A Multi-Agent Search Algorithm with Local Reconnaissance, Global Collaboration, and Environmental Perturbation
Zhang, Jincheng
<p><span>This paper proposes a new optimization algorithm, the core idea of</span> <span>which is derived from the behavioral characteristics of multiple UAVs flying and executing missions in complex environments. Unlike traditional particle swarm optimization, genetic algorithm, or ant colony algorithm, this algorithm fully simulates the local reconnaissance, global collaboration, airflow disturbance, and formation intelligence mechanisms of UAVs, mapping them into the optimization search process, thereby achieving efficient search for the global optimal solution. The algorithm design introduces a multi-level dynamic model and environmental perception mechanism, and proposes a complete set of mathematical formulas, including velocity update, position update, local reconnaissance attraction, global collaboration attraction, airflow disturbance, and formation collaboration mechanism. This paper elaborates on the algorithm's theoretical model, mathematical formula derivation, and multi-strategy adaptive control strategy, providing a systematic theoretical basis for the research of UAV heuristic optimization algorithms.</span></p>
title Drone Behavior Inspired Optimization: A Multi-Agent Search Algorithm with Local Reconnaissance, Global Collaboration, and Environmental Perturbation
url https://doi.org/10.5281/zenodo.17493690