Dynamic guidance control for UAV landing on autonomous surface vessel.

Area of Science:

• Robotics and Control Systems
• Autonomous Systems Engineering
• Aerospace Engineering

Background:

• Autonomous surface vessels (ASVs) and unmanned aerial vehicles (UAVs) are increasingly vital for maritime operations.
• Cooperative missions between ASVs and UAVs require robust landing strategies for UAVs onto moving vessels.
• Existing control methods face challenges in ensuring stability and efficiency during dynamic landing scenarios.

Purpose of the Study:

• To develop an optimization strategy for tail-sitter UAVs landing on ASVs.
• To achieve minimal risk, shortest time, and lowest energy consumption during the landing process.
• To enhance the cooperative capabilities of UAV-ASV systems in complex maritime environments.

Main Methods:

• Sliding mode control (SMC) for system stability under nonlinear and dynamic conditions.
• A two-player game model with Nash equilibrium to minimize risk and energy.
• Pareto optimal theory for multi-objective trade-offs, verified by Karush-Kuhn-Tucker conditions.
• Actor-Critic neural network for adaptive online learning of landing strategies.

Main Results:

• The proposed strategy enables UAVs to dynamically adjust to ASV motion.
• Successful achievement of precise, energy-efficient, and low-risk landings.
• Demonstrated stability and robustness in simulated dynamic environments.
• Validation of the optimization approach through adaptive learning.

Conclusions:

• The developed optimization strategy provides a viable solution for UAV-ASV cooperative landings.
• This research offers practical technical support and theoretical foundations for future unmanned maritime operations.
• The approach enhances the reliability and efficiency of autonomous systems in challenging conditions.