Dual-loop control and state prediction analysis of QUAV trajectory tracking based on biological swarm intelligent...

Area of Science:

• Robotics
• Control Systems Engineering
• Artificial Intelligence

Background:

• Quadrotor unmanned aerial vehicles (QUAVs) are crucial for applications requiring Vertical Take-Off and Landing (VTOL).
• Maintaining precise trajectory tracking in QUAVs is challenging due to external disturbances and system uncertainties.
• Existing control methods often struggle with adaptability and predictive error mitigation.

Purpose of the Study:

• To develop a robust, two-tier control system for QUAVs to ensure precise trajectory tracking.
• To enhance QUAV system stability and adaptability against external disturbances and mass variations.
• To improve mission operation reliability and safety through predictive error mitigation.

Main Methods:

• Implementation of a two-tier sliding mode control strategy for position and attitude subsystems.
• Utilization of adaptive mechanisms for mass and disturbance compensation in position control.
• Integration of a deep learning model (LSTM with PSO) for trajectory error prediction and mitigation.

Main Results:

• The proposed sliding mode control significantly enhances trajectory tracking precision.
• Adaptive mechanisms effectively compensate for system uncertainties and external disruptions.
• The deep learning approach successfully predicts and mitigates tracking errors, improving overall system performance.

Conclusions:

• The developed robust control system demonstrates superior performance in QUAV trajectory tracking.
• The combination of sliding mode control and deep learning offers a promising approach for enhancing UAV autonomy and safety.
• Numerical simulations validate the effectiveness and robustness of the proposed control strategy.