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

Abstract

This paper proposes an adaptive PID-based sliding mode controller (APID-SMC) for autonomous underwater vehicles (AUVs), optimized using ant colony optimization (ACO), to enhance trajectory-tracking accuracy and robustness under external disturbances. The proposed controller demonstrates significant improvements over conventional SMC, STA, and PID controllers across multiple performance indices. Specifically, the APID-SMC reduces the integral absolute error (IAE) in the surge, sway, and yaw channels by 14.50%, 27.97%, and 26.39%, respectively, and improves ITAE by 66.80%, 80.17%, and 82.84%, highlighting its superior transient performance. The controller also generates smoother control signals with reduced chattering and maintains stability under extreme noise and uncertainties. The framework integrates the robustness of sliding mode control with the smooth corrective action of a PID controller, whose gains are dynamically tuned online via a gradient descent algorithm (GDA). Additionally, ACO optimally selects learning rates and sliding surface coefficients by minimizing a trajectory-tracking cost function, ensuring rapid convergence and consistent performance. These results confirm that APID-SMC is a highly effective and practical control solution for complex and uncertain marine environments.

Keywords: Adaptive PID control; Autonomous underwater vehicle; Gradient descent algorithm; Sliding mode control; Trajectory tracking.