用超网络自适应调节，让无人机在舵面故障时仍能稳定飞行。
Hypernetwork-Conditioned Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Actuator Failures
- 通过超网络动态调整控制策略，实现对故障的快速响应。
- 在未训练过的故障模式下仍保持良好性能，泛化能力显著提升。
- 适合需要高鲁棒性的无人机自主飞行系统研究者参考。
本文提出一种基于强化学习的固定翼小型无人航空系统（sUAS）路径跟踪控制器，具备对特定执行器故障的鲁棒性。控制器通过超网络对执行器故障进行参数化建模并实现自适应调节，采用特征式线性调制（FiLM）和低秩微调（LoRA）等参数高效方法，结合近端策略优化（PPO）进行训练。实验表明，相较于标准多层感知机策略，超网络条件化策略在应对训练中未遇到的时间变化型执行器故障时具有更强的泛化能力。该方法在高保真六自由度固定翼飞机模型上通过仿真验证，表现出优异的鲁棒性与适应性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。