Adaptive learning-based tracking control for tilted-rotor UAVs under uncertain environments.

Area of Science:

• Robotics and Control Systems
• Aerospace Engineering
• Artificial Intelligence

Background:

• Unmanned aerial vehicles (UAVs) face challenges in complex environments due to nonlinear dynamics, disturbances, and model uncertainties.
• Repetitive tasks in the growing low-altitude economy demand robust trajectory tracking for UAVs.
• Existing control strategies often struggle with the combined complexities of UAV dynamics and external factors.

Purpose of the Study:

• To develop an adaptive learning-based trajectory tracking strategy for hexarotor UAVs.
• To address nonlinear dynamics, disturbances, model uncertainties, and input constraints in UAV control.
• To enhance tracking performance for repetitive tasks performed by UAVs.

Main Methods:

• Decoupling hexarotor dynamics into translational and rotational subsystems.
• Implementing a novel adaptive iterative learning control (AILC) for the translational subsystem.
• Utilizing adaptive update laws and an input-dependent auxiliary system for compensation.
• Analyzing closed-loop convergence with a composite energy function.

Main Results:

• The proposed AILC method demonstrates improved trajectory tracking for hexarotor UAVs.
• The strategy effectively compensates for system uncertainties and external disturbances.
• Simulations confirm the method's effectiveness, robustness, and potential for real-world applications.

Conclusions:

• The adaptive learning-based trajectory tracking strategy offers a robust solution for hexarotor UAVs.
• The AILC approach enhances performance in repetitive tasks within complex operational environments.
• The study highlights the potential of advanced control techniques for the expanding low-altitude economy.