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

2026-04-03

AI Summary

This work addresses the challenge of robust path-following for fixed-wing small unmanned aircraft systems under actuator faults by proposing a hypernetwork-based adaptive reinforcement learning control approach. The method leverages a parameter-efficient hypernetwork architecture that integrates Feature-wise Linear Modulation (FiLM) and Low-Rank Adaptation (LoRA) to conditionally model time-varying actuator failures, including those unseen during training. The entire policy is trained end-to-end using Proximal Policy Optimization. High-fidelity six-degree-of-freedom simulation results demonstrate that the proposed approach significantly outperforms conventional multilayer perceptron policies in terms of generalization to unknown actuator faults and tracking robustness.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• reinforcement learning
• actuator failures
• robust control
• fixed-wing aircraft
• path-following

Innovation

• Hypernetwork
• Reinforcement Learning
• Actuator Failure
• FiLM
• LoRA