arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.12097eess.SYcs.LGcs.SY
收藏

具有元学习的不确定非线性系统MPC以实现神经预测模型的快速适应

MPC of Uncertain Nonlinear Systems with Meta-Learning for Fast Adaptation of Neural Predictive Models

Automatic Control Laboratory, ETH Zurich(瑞士苏黎世联邦理工学院自动控制实验室);Mitsubishi Electric Research Laboratories(三菱电机研究实验室);ZHAW Centre for Artificial Intelligence, Zurich University of Applied Sciences(瑞士应用科学大学人工智能中心)

Jiaqi Yan, Ankush Chakrabarty, Alisa Rupenyan, John Lygeros

AI总结:

本文提出一种基于元学习的MPC方法,通过聚合神经状态空间模型快速适应非线性系统,提升控制性能。

摘要:

在本文中,我们考虑了在不确定非线性系统中进行参考跟踪的问题。使用神经状态空间模型(NSSM)来近似非线性系统,其中深度编码器网络从数据中学习非线性特性,而状态空间组件捕捉时间关系。这将非线性系统转换为潜在空间中的线性系统,从而可以应用模型预测控制(MPC)来确定有效的控制动作。我们的目标是利用目标系统(感兴趣的系统)的有限数据设计最优控制器。为此,我们采用隐式模型无关元学习(iMAML)框架,利用源系统(与目标系统相似的系统)的信息来加快目标系统的训练并提高其控制性能。该框架分为两个阶段:(离线)元训练阶段使用源系统的数据学习聚合NSSM,(在线)元推断阶段仅使用少量数据点和少量在线训练迭代,基于局部损失函数梯度,快速适应此聚合模型到目标系统。iMAML算法利用隐函数定理精确计算训练过程中的梯度,而不依赖于整个优化路径。通过专注于最优解,而不是路径,我们可以在存储复杂性和近似程度上比其他当代元学习算法更少地进行元训练。通过数值示例,我们证明了所提出的方法可以通过适应生成准确的预测模型,从而在下游MPC中优于几个基线。

英文摘要:

In this paper, we consider the problem of reference tracking in uncertain nonlinear systems. A neural State-Space Model (NSSM) is used to approximate the nonlinear system, where a deep encoder network learns the nonlinearity from data, and a state-space component captures the temporal relationship. This transforms the nonlinear system into a linear system in a latent space, enabling the application of model predictive control (MPC) to determine effective control actions. Our objective is to design the optimal controller using limited data from the \textit{target system} (the system of interest). To this end, we employ an implicit model-agnostic meta-learning (iMAML) framework that leverages information from \textit{source systems} (systems that share similarities with the target system) to expedite training in the target system and enhance its control performance. The framework consists of two phases: the (offine) meta-training phase learns a aggregated NSSM using data from source systems, and the (online) meta-inference phase quickly adapts this aggregated model to the target system using only a few data points and few online training iterations, based on local loss function gradients. The iMAML algorithm exploits the implicit function theorem to exactly compute the gradient during training, without relying on the entire optimization path. By focusing solely on the optimal solution, rather than the path, we can meta-train with less storage complexity and fewer approximations than other contemporary meta-learning algorithms. We demonstrate through numerical examples that our proposed method can yield accurate predictive models by adaptation, resulting in a downstream MPC that outperforms several baselines.

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。

↑