当前位置: X-MOL 学术arXiv.cs.SY › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
arXiv - CS - Systems and Control Pub Date : 2021-05-07 , DOI: arxiv-2105.03397
Christian Fiedler, Carsten W. Scherer, Sebastian Trimpe

The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and state-of-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.

中文翻译:

具有严格统计和控制理论保证的学习增强型鲁棒控制器综合

机器学习与控制的结合提供了很多机会,特别是对于稳健的控制。但是,由于在许多实际应用中对安全性和可靠性的要求很高,因此提供严格的统计和控制理论保证极为重要,但对于基于学习的控制方案却很难实现。我们为学习增强型鲁棒控制提供了一个通用框架,该框架允许对现有工程知识进行系统集成,与现代鲁棒控制完全兼容,并且仍然具有严格而实用的保证​​。在已建立的线性分数表示和积分二次约束框架的基础上,我们将高斯过程回归作为学习组件和最新的鲁棒控制器综合在一起。
更新日期:2021-05-10
down
wechat
bug