Gradient-based adaptive PID-SMC control tuned by ant colony optimization for autonomous underwater vehicle

Area of Science:

• Robotics and Control Systems
• Marine Engineering
• Artificial Intelligence

Background:

• Autonomous Underwater Vehicles (AUVs) require robust control for accurate trajectory tracking.
• Conventional controllers like Sliding Mode Control (SMC) and PID often struggle with external disturbances and uncertainties.
• Enhancing AUV control performance is crucial for complex marine operations.

Purpose of the Study:

• To propose and evaluate an Adaptive PID-based Sliding Mode Controller (APID-SMC) for AUVs.
• To optimize the APID-SMC using Ant Colony Optimization (ACO) for improved trajectory tracking.
• To demonstrate the controller's enhanced robustness against external disturbances and uncertainties.

Main Methods:

• Development of an APID-SMC integrating SMC robustness with PID smooth control.
• Online tuning of PID gains using a Gradient Descent Algorithm (GDA).
• Optimization of learning rates and sliding surface coefficients via ACO to minimize trajectory-tracking error.

Main Results:

• APID-SMC significantly reduced Integral Absolute Error (IAE) by up to 27.97% and Integral Time Absolute Error (ITAE) by up to 82.84% compared to conventional methods.
• The controller exhibited superior transient performance and reduced control signal chattering.
• Demonstrated stability and effectiveness under extreme noise and uncertainties in simulated marine environments.

Conclusions:

• The proposed APID-SMC offers a highly effective and practical control solution for AUVs.
• ACO-based optimization enhances convergence speed and performance consistency.
• APID-SMC provides improved trajectory-tracking accuracy and robustness in complex marine settings.