Session: 06-11-01 Ocean Engineering Technology

Submission Number: 156242

Toward Robust Tracking Control of Unmanned Surface Vehicles in Complex Aquatic Environments: Online Data-Driven Model Predictive Control via Sparse Gaussian Process Regression 

Recently, nonlinear model predictive control (NMPC) exhibits its superiority for time-critical tracking in the autonomous navigation of unmanned surface vehicles (USVs), while strictly adhering to operational and actuator constraints. Nevertheless, the complexity of hydrodynamic forces in harsh marine environments, coupled with time-variant system dynamics pose significant challenges to achieving high-precision tracking. These challenges arise from the deterministic model assumption and the omission of external disturbances. To address these issues, this paper proposes a Gaussian process regression (GPR)-based online system identification and data-driven model predictive control scheme for enhanced trajectory tracking accuracy and robustness. Given that the true dynamic model is inaccessible, it is decomposed into nominal and uncertain components. A sparse Gaussian process regression (GPR) framework, employing fully independent training conditional (FITC) approximation, captures the nonlinear uncertainty in the system dynamics, ensuring computational tractability within the receding-horizon optimal control scheme. An efficient kernel matrix update method, incorporating new observations without recalculating historic ones, accelerates the data-driven system identification process, making the proposed sparse GPR-NMPC control scheme instantaneously adaptable to environmental disturbances and model changes. To validate the approach, experiments were conducted on USV tracking of circular, lemniscate, and arbitrary trajectories in real-world waters with significant disturbances. Compared with the state-of-the-art offline method, sparse identification of nonlinear dynamics (SINDy), the proposed online identification and control scheme outperforms in accuracy, robustness, supporting rapid deployment across various USVs in complex environments.

Presenting Author: Jiarong Liu Shanghai Jiao Tong University

Presenting Author Biography: I am currently a doctoral student under the supervision of Prof. Yongsheng Zhao at the Marine Equipment and Innovation Design Lab in Shanghai Jiao Tong University.Before I completed my Bachelor Studies in Shanghai Jiao Tong University.
My major is ship and ocean engineering, and my personal reseach interest lies in automation of unmanned surface vehicles, including multi-sensor sensing, motion planning and tracking control.