Adaptation of Genetic Algorithms in the Task of Optimizing Ground Robot Motion for UAV Group Control

Abstract

This article explores the possibilities of using genetic algorithms to optimize the trajectory of unmanned aerial vehicles (UAVs) in order to improve the accuracy and efficiency of air quality assessment under various conditions. One of the main objectives is to ensure adaptive autonomous navigation of UAVs in dynamic environments, where parameters related to air pollution can change in real-time under the influence of external factors, such as weather conditions, geographical features, or levels of anthropogenic impact.

Genetic algorithms, due to their ability to search for optimal solutions in complex data spaces, can be effectively used to determine the optimal routes for collecting information about air pollution. They allow UAVs to adapt their trajectories to the current environmental conditions, taking into account factors such as wind direction and speed, pollution levels in different areas, and the presence of natural or artificial obstacles in urban or rural environments. Thanks to this approach, the algorithms provide coordinated work within a group of UAVs, which allows for the division of monitoring zones, the collection of more accurate data, and faster responses to changes in the environment. The article also discusses how genetic algorithms can improve the process of data collection and processing for further air quality analysis. The optimization of trajectories reduces the energy consumption of UAVs, increases the volume and quality of collected data, which in turn enhances the accuracy of assessments of harmful substance concentrations in the air. This makes genetic algorithms a promising and effective tool for increasing the autonomy and overall efficiency of unmanned systems in the context of air quality monitoring in various environments, such as large cities, industrial zones, agricultural areas, or nature reserves.