Simulation and Mission Planning for Unmanned Aerial Vehicles using Evolutionary Computation based Algorithms
DOI:
https://doi.org/10.5281/zenodo.14668137Abstract
Effective mission planning is essential for optimizing the operational efficiency of Unmanned Aerial Vehicle (UAV) swarms. Selecting the appropriate algorithms for mission planning poses a challenge, as it involves strategic decision-making on how best to coordinate UAVs to complete complex tasks. Evolutionary computational algorithms have shown superior performance in this context, thanks to their adaptive, iterative nature, which enables efficient navigation through complex problem spaces. This adaptability enhances both the performance and flexibility of UAV swarm mission planning. Typically, mission planning starts with a simulation phase to mitigate inefficiencies and safety risks before applying strategies to a live swarm. However, many existing UAV simulators are designed for specific use cases, which limits their broader applicability. To address these gaps, we developed two integrated software solutions: one for simulation and another for mission planning using evolutionary computation algorithms. These tools work together to simulate and optimize UAV swarm missions effectively. This paper describes the design and implementation of these solutions and validates them through experiments with algorithms like SPEA-2, AGE-MOEA, NSGA-2, and SMS-EMOA. The findings provide insights into the performance of these algorithms and highlight their suitability for complex UAV swarm mission planning tasks.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Tunc Asuroglu, Metehan Aydın, Erkan Bostancı (Author)

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.