Fuzzy logic controller for UAV with gains optimized via genetic algorithm

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Aerospace Engineering

Background:

• Unmanned Aerial Vehicles (UAVs) require efficient control systems for navigation and energy management.
• Fuzzy controllers offer adaptability but often need precise gain tuning for optimal performance.
• Metaheuristic algorithms provide robust optimization capabilities for complex control parameters.

Purpose of the Study:

• To develop a gains optimizer for a fuzzy controller system in UAVs.
• To enhance UAV energy efficiency and trajectory tracking precision.
• To leverage the Genetic Algorithm (GA) for tuning fuzzy controller input gains.

Main Methods:

• Modeling and designing a fuzzy controller using the Newton-Euler methodology.
• Implementing the fuzzy controller within a mathematical model in Matlab-Simulink.
• Optimizing fuzzy controller gains using a metaheuristic algorithm, specifically the Genetic Algorithm (GA).

Main Results:

• The Genetic Algorithm successfully tuned the fuzzy controller gains to minimize UAV energy consumption.
• Trajectory tracking errors were reduced by up to 30% in specific tasks.
• The optimized controller enabled successful execution of trajectories that were previously unachievable.

Conclusions:

• The GA-based fuzzy controller significantly enhances UAV performance in terms of energy efficiency and trajectory following.
• This approach offers a viable solution for improving the operational capabilities of UAVs.
• The developed gains optimizer demonstrates the effectiveness of metaheuristic algorithms in advanced control system design.