21 citations · 69 across the 10 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
eess.SY2019
Feedback Linearization based on Gaussian Processes with event-triggered Online Learning
Jonas Umlauft, Sandra Hirche
Combining control engineering with nonparametric modeling techniques from machine learning allows to control systems without analytic description using data-driven models. Most exi…
cs.LG2019★ 10 cited
Posterior Variance Analysis of Gaussian Processes with Application to Average Learning Curves
Armin Lederer, Jonas Umlauft, Sandra Hirche
The posterior variance of Gaussian processes is a valuable measure of the learning error which is exploited in various applications such as safe reinforcement learning and control…
cs.LG2019★ 16 cited
Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control
Armin Lederer, Jonas Umlauft, Sandra Hirche
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 the…