Event-Based Finite-Time Neural Control for Human-in-the-Loop UAV Attitude Systems

Area of Science:

• Robotics and Control Systems
• Aerospace Engineering
• Artificial Intelligence

Background:

• Consensus control is crucial for multi-agent systems like unmanned aerial vehicles (UAVs).
• Addressing unknown disturbances and nonlinear dynamics in UAV control is challenging.
• Finite-time control offers faster convergence compared to traditional control methods.

Purpose of the Study:

• To develop an event-based finite-time neural attitude consensus control strategy for six-rotor UAVs.
• To handle unknown external disturbances and uncertain nonlinear dynamics.
• To mitigate the communication burden in practical UAV systems.

Main Methods:

• Utilizing a disturbance observer to estimate and compensate for unknown external disturbances.
• Employing radial basis function neural networks (RBF NNs) to approximate uncertain nonlinear dynamics.
• Implementing a finite-time command filtered (FTCF) backstepping approach with an error compensation mechanism to avoid complexity explosion.
• Integrating an event-triggered mechanism to optimize controller-actuator communication.

Main Results:

• The proposed control scheme ensures all signals within the six-rotor UAV systems remain bounded.
• Consensus errors are demonstrated to converge to a small neighborhood of the origin within a finite time.
• Simulation results validate the effectiveness and robustness of the developed control strategy.

Conclusions:

• The event-based finite-time neural attitude consensus control is effective for six-rotor UAVs.
• The approach successfully addresses unknown disturbances, nonlinear dynamics, and communication constraints.
• This research contributes to the advancement of robust and efficient UAV control systems.