Arbac, Sefa (Siemens), Mumcu, Tarık Veli (Istanbul University-Cerrahpasa)

Multi-Objective Genetic Algorithm Framework in Swarm UAV Systems with Real-Time Simulation

Scheduled for presentation during the Regular Session "Cooperative Multi-Robot Control" (WeCT4), Wednesday, July 16, 2025, 17:10−17:30, Room 108

Joint 10th IFAC Symposium on Mechatronic Systems and 14th Symposium on Robotics, July 15-18, 2025, Paris, France

This information is tentative and subject to change. Compiled on July 16, 2025

Abstract

This study presents a Multi-Objective Genetic Algorithm (MOGA) framework for task planning and assignment in swarm UAV systems. Various genetic algorithm methodologies, including selection, crossover, and mutation techniques, are implemented to analyze their individual contributions to system performance. Specifically, simple inversion and scramble mutation techniques are compared to evaluate their impact on task efficiency and resource optimization.

The framework leverages the Robot Operating System (ROS) to facilitate real-time control and communication between UAVs and integrates a hybrid simulation environment using MATLAB and Gazebo. ROS enables data exchange and coordination within the swarm, enhancing the realism and scalability of the simulation. Simulation results demonstrate the effectiveness of the proposed framework in optimizing key objectives such as power consumption and mission distance. Furthermore, this work introduces a simulation platform capable of supporting diverse operational scenarios for swarm UAVs, providing a valuable tool for future research and applications.