arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03392eess.SYcs.LGcs.SY
收藏

基于超网络的强化学习用于应对飞机构型失效的稳健控制

Learning Families of Fixed-Wing Aircraft Control Policies with Hypernetwork-Conditioned Reinforcement Learning

Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Tech(弗吉尼亚理工大学凯文·T·克罗夫顿航空航天与海洋工程系)

Dennis Marquis, Mazen Farhood

AI总结:

本文提出一种基于强化学习的路径跟随控制器,用于应对无人机飞机构型失效问题,通过超网络实现参数高效适应,提升鲁棒性。

摘要:

本文提出了一种基于强化学习的路径跟随控制器,用于固定翼小型无人驾驶航空器系统(sUAS)在特定作动器故障下的稳健控制。控制器通过基于超网络的适应方法对作动器故障参数进行参数化。我们考虑了基于特征线性调制(FiLM)和低秩适应(LoRA)的参数高效方法,并通过近端策略优化进行训练。我们证明了超网络条件策略相比标准多层感知机策略在鲁棒性上有所提升。特别是,超网络条件策略能够有效泛化到训练过程中未遇到的时间变化作动器故障模式。该方法通过高保真度的仿真验证,使用了现实中的六自由度固定翼航空器模型进行测试。

英文摘要:

This paper investigates whether it is more effective to condition reinforcement learning policies across changing dynamics using standard input augmentation or hypernetwork-based parameter modulation. We use a small fixed-wing uncrewed aircraft under actuator failures as a demanding test case, as these failures introduce distinctly different closed-loop dynamics. We evaluate parameter-efficient hypernetwork formulations based on Feature-wise Linear Modulation (FiLM) and Low-Rank Adaptation (LoRA), trained using proximal policy optimization. High-fidelity six-degree-of-freedom simulations demonstrate that hypernetwork-conditioned policies improve robustness compared to standard multilayer perceptron policies trained with augmented inputs. Most notably, the hypernetwork policies generalize effectively to time-varying actuator failure modes not encountered during training, indicating that modulating internal parameters provides significant advantages over standard input augmentation for this class of highly coupled dynamics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑