Automatic autopilot tuning framework using genetic algorithms and system identification

This paper presents a comprehensive framework for offline optimization of tuning parameters in unmanned aerial vehicle (UAV) flight controllers. The framework uses system identification to create a simplified flight dynamics model, followed by control law matching to ensure the simulated controller's output closely replicates real-world autopilot commands. The optimization phase employs genetic algorithms to tune parameters based on a defined cost function that incorporates performance requirements. Each stage, from flight dynamics model development to optimization, is validated to ensure enhanced controller performance. Finally, real-world flight tests confirm the effectiveness of the optimized controller, demonstrating the validity of the proposed framework for autopilot tuning optimization. • Genetic Algorithms optimize UAV autopilot tuning for enhanced flight performance. • System identification simplifies UAV flight dynamics model creation for tuning. • Real-world flight tests validate the proposed autopilot tuning framework. • The framework adapts to various UAV controllers and vehicle configurations. • Optimized controller parameters improve stability and performance in UAVs.