Conformal Koopman for Embedded Nonlinear Control with Statistical Robustness: Theory and Real-World Validation
共形Koopman用于嵌入非线性控制的统计鲁棒性:理论与现实验证
机构 * Department of Aerospace Engineering, The Grainger College of Engineering, University of Illinois Urbana-Champaign(航空航天工程系,格拉inger工程学院,伊利诺伊大学厄巴纳-香槟分校)
AI总结 本文提出一种基于Koopman的全数据驱动框架,用于具有线性嵌入的离散时间非线性系统的统计鲁棒控制,通过共形预测提供分布无关的概率界限,确保安全性和鲁棒性。
Comments 8 pages, 6 figures. Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA). The final published version will be available via IEEE Xplore