李普希茨连续性
高斯过程
高斯分布
计算机科学
概率逻辑
度量(数据仓库)
克里金
应用数学
过程(计算)
钥匙(锁)
上下界
动力系统理论
数学
数学优化
算法
人工智能
数据挖掘
机器学习
数学分析
物理
操作系统
量子力学
计算机安全
作者
Armin Lederer,Jonas Umlauft,Sandra Hirche
出处
期刊:Cornell University - arXiv
日期:2019-01-01
被引量:55
标识
DOI:10.48550/arxiv.1906.01376
摘要
Data-driven models are subject to model errors due to limited and noisy training data. Key to the application of such models in safety-critical domains is the quantification of their model error. Gaussian processes provide such a measure and uniform error bounds have been derived, which allow safe control based on these models. However, existing error bounds require restrictive assumptions. In this paper, we employ the Gaussian process distribution and continuity arguments to derive a novel uniform error bound under weaker assumptions. Furthermore, we demonstrate how this distribution can be used to derive probabilistic Lipschitz constants and analyze the asymptotic behavior of our bound. Finally, we derive safety conditions for the control of unknown dynamical systems based on Gaussian process models and evaluate them in simulations of a robotic manipulator.
科研通智能强力驱动
Strongly Powered by AbleSci AI