Fixed-time optimal time-varying formation control for unmanned surface vehicle systems based on reinforcement...

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Marine Engineering

Background:

• Unmanned Surface Vehicle Systems (USVSs) require robust control strategies for coordinated operations.
• Partially unmeasurable states and unknown dynamics pose significant challenges in USVS formation control.
• Existing control methods often struggle to guarantee fixed-time convergence and optimal performance simultaneously.

Purpose of the Study:

• To develop a distributed fixed-time optimal time-varying formation control (TVFC) strategy for USVSs.
• To address systems with partially unmeasurable states and unknown dynamics.
• To achieve both formation control and cost optimization objectives.

Main Methods:

• A fixed-time adaptive neural network state observer (FANNSO) was designed to reconstruct unknown dynamics and unmeasurable states.
• A distributed optimization performance index function with exponential terms was proposed.
• A distributed fixed-time optimal TVFC strategy was developed using an actor-critic reinforcement learning structure.

Main Results:

• The proposed control strategy ensures that error signals remain bounded within a fixed time.
• The reinforcement learning algorithm adaptively adjusts the controller for optimal performance.
• Simulation results validated the effectiveness and superiority of the developed method.

Conclusions:

• The novel RL-based TVFC strategy effectively handles USVSs with uncertainties.
• The FANNSO successfully reconstructs system states and dynamics.
• The approach provides a robust solution for fixed-time optimal formation control in USVSs.