Learning-based Observer for Coupled Disturbance

TL;DR

This paper presents a novel learning-based observer that accurately estimates coupled disturbances in robotic systems by combining Chebyshev series expansion, regularized least squares, and polynomial disturbance estimation, validated through simulations and flight tests.

Contribution

It introduces a convergent algorithm that decomposes and learns coupled disturbances using historical data, enhancing high-precision control in robotics.

Findings

Effective disturbance decomposition and learning demonstrated

High-precision disturbance estimation achieved

Validated through extensive simulations and flight tests

Abstract

Achieving high-precision control for robotic systems is hindered by the low-fidelity dynamical model and external disturbances. Especially, the intricate coupling between internal uncertainties and external disturbances further exacerbates this challenge. This study introduces an effective and convergent algorithm enabling accurate estimation of the coupled disturbance via combining control and learning philosophies. Concretely, by resorting to Chebyshev series expansion, the coupled disturbance is firstly decomposed into an unknown parameter matrix and two known structures dependent on system state and external disturbance respectively. A regularized least squares algorithm is subsequently formalized to learn the parameter matrix using historical time-series data. Finally, a polynomial disturbance observer is specifically devised to achieve a high-precision estimation of the coupled disturbance by utilizing the learned portion. The proposed algorithm is evaluated through extensive simulations and real flight tests. We believe this work can offer a new pathway to integrate learning approaches into control frameworks for addressing longstanding challenges in robotic applications.