WSINDy for Model Predictive Control with Applications to Fusion, Drones, and Chaos

TL;DR

This paper introduces WSINDYc, a robust data-driven modeling method integrated with MPC, demonstrating improved control performance in noisy, complex systems like fusion devices, drones, and chaotic models.

Contribution

The paper develops WSINDYc within an MPC framework, enhancing dynamic identification robustness and control accuracy under high noise conditions compared to existing methods.

Findings

WSINDYc improves model accuracy in noisy environments.

The framework enables longer prediction horizons and lower tracking errors.

It achieves lower control costs and better obstacle clearance in tested systems.

Abstract

The control of complex dynamical systems remains a fundamental challenge in science and engineering, where strong nonlinearities, the presence of noise, and computational constraints often pose significant obstacles in traditional control approaches. Recent advances in data-driven methods, particularly system identification techniques, have shown a powerful alternative by providing fast, parsimonious, interpretable models that are well-suited for model predictive control (MPC). Building on these developments, the present article embeds WSINDy with actuation inputs (WSINDYc) within a MPC framework. Compared to benchmark data-driven methods, WSINDYc enables a more robust identification of the governing dynamics, particularly in the presence of high noise levels, resulting in more accurate and efficient control. The capabilities of the proposed WSINDY-MPC framework are demonstrated on a range of problems, including a tokamak plasma boundary model that includes main ion gas puff actuation, drone tracking and collision avoidance, the chaotic Lorenz system, and a simplified flight control model for an F-8 aircraft. The proposed framework achieves superior performance in the presence of noise, enabling longer prediction horizons, lower trajectory tracking error, and a more reliable obstacle clearance, while simultaneously achieving lower MPC cost values compared to the baseline methods.