Hypernetwork-Conditioned Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Actuator Failures

TL;DR

This paper introduces a reinforcement learning controller for fixed-wing aircraft that uses hypernetworks to adapt to actuator failures, demonstrating improved robustness and generalization in simulations.

Contribution

It proposes a hypernetwork-conditioned reinforcement learning approach with FiLM and LoRA for robust control under actuator failures, validated in high-fidelity simulations.

Findings

Hypernetwork-conditioned policies outperform standard MLP policies in robustness.

The approach generalizes to unseen, time-varying actuator failure modes.

Validated effectiveness through high-fidelity aircraft simulations.

Abstract

This paper presents a reinforcement learning-based path-following controller for a fixed-wing small uncrewed aircraft system (sUAS) that is robust to certain actuator failures. The controller is conditioned on a parameterization of actuator faults using hypernetwork-based adaptation. We consider parameter-efficient formulations based on Feature-wise Linear Modulation (FiLM) and Low-Rank Adaptation (LoRA), trained using proximal policy optimization. We demonstrate that hypernetwork-conditioned policies can improve robustness compared to standard multilayer perceptron policies. In particular, hypernetwork-conditioned policies generalize effectively to time-varying actuator failure modes not encountered during training. The approach is validated through high-fidelity simulations, using a realistic six-degree-of-freedom fixed-wing aircraft model.