Improving INDI for Input Nonaffine Systems via Learning-Based Nonlinear Control Allocation

TL;DR

This paper identifies limitations of standard INDI with ICA for input nonaffine systems and introduces a supervised learning-based nonlinear control allocation method as an effective, computationally efficient alternative.

Contribution

The paper proposes a novel learning-based control allocation approach to improve INDI for input nonaffine systems, addressing computational challenges of nonlinear programming.

Findings

Standard INDI + ICA relies on linear actuator model approximation.

The proposed learning-based method effectively handles nonlinear control allocation.

Numerical experiments validate the method's effectiveness and computational efficiency.

Abstract

This paper first demonstrates that applying standard incremental nonlinear dynamic inversion (INDI) with incremental control allocation (ICA) to input nonaffine systems relies on an untenable linear approximation of the actuator model. It then shows that avoiding this issue, while retaining the static control allocation paradigm, generally requires solving a nonlinear programming (NLP) problem. To address the associated online computational challenges, the paper subsequently presents a supervised learning-based approach. Numerical experiments on an example problem validate the identified limitations of standard INDI + ICA for input nonaffine systems, while also demonstrating that the proposed learning-based method provides an effective and computationally tractable alternative.