A Data-Driven Autopilot for Fixed-Wing Aircraft Based on Model Predictive Control

TL;DR

This paper introduces a novel autopilot for fixed-wing aircraft that employs model predictive control combined with recursive least squares for online system identification, eliminating the need for pre-existing aerodynamic models.

Contribution

It presents a data-driven autopilot approach based on predictive cost adaptive control that adapts in real-time without relying on traditional aerodynamic modeling.

Findings

Effective online system identification for fixed-wing aircraft.

Autopilot operates without pre-collected aerodynamic data.

Demonstrates robustness in unmodeled aerodynamic conditions.

Abstract

Autopilots for fixed-wing aircraft are typically designed based on linearized aerodynamic models consisting of stability and control derivatives obtained from wind-tunnel testing. The resulting local controllers are then pieced together using gain scheduling. For applications in which the aerodynamics are unmodeled, the present paper proposes an autopilot based on predictive cost adaptive control (PCAC). As an indirect adaptive control extension of model predictive control, PCAC uses recursive least squares (RLS) with variable-rate forgetting for online, closed-loop system identification. At each time step, RLS-based system identification updates the coefficients of an input-output model whose order is a hyperparameter specified by the user. For MPC, the receding-horizon optimization can be performed by either the backward-propagating Riccati equation or quadratic programming. The present paper investigates the performance of PCAC for fixed-wing aircraft without the use of any aerodynamic modeling or offline/prior data collection.