Improving Action Smoothness for a Cascaded Online Learning Flight Control System

TL;DR

This paper enhances the action smoothness of a cascaded online learning flight control system by introducing an online temporal smoothness technique and a low-pass filter, validated through FFT analysis and simulations.

Contribution

It proposes novel online smoothing methods and frequency analysis for improved stability and control action smoothness in cascaded flight control systems.

Findings

Control oscillations are reduced by the proposed techniques.

FFT analysis shows decreased amplitude and frequency of control actions.

Simulation results confirm improved control smoothness.

Abstract

This paper aims to improve the action smoothness of a cascaded online learning flight control system. Although the cascaded structure is widely used in flight control design, its stability can be compromised by oscillatory control actions, which poses challenges for practical engineering applications. To address this issue, we introduce an online temporal smoothness technique and a low-pass filter to reduce the amplitude and frequency of the control actions. Fast Fourier Transform (FFT) is used to analyze policy performance in the frequency domain. Simulation results demonstrate the improvements achieved by the two proposed techniques.