11 citations · 24 across the 4 of their papers we have counts for
8 papers
Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Control
Armin Lederer, Jonas Umlauft, Sandra Hirche
In application areas where data generation is expensive, Gaussian processes are a preferred supervised learning model due to their high data-efficiency. Particularly in model-based…
The Impact of Data on the Stability of Learning-Based Control- Extended Version
Armin Lederer, Alexandre Capone, Thomas Beckers +2
Despite the existence of formal guarantees for learning-based control approaches, the relationship between data and control performance is still poorly understood. In this paper, w…
Localized active learning of Gaussian process state space models
Alexandre Capone, Jonas Umlauft, Thomas Beckers +2
The performance of learning-based control techniques crucially depends on how effectively the system is explored. While most exploration techniques aim to achieve a globally accura…
How Training Data Impacts Performance in Learning-based Control
Armin Lederer, Alexandre Capone, Jonas Umlauft +1
When first principle models cannot be derived due to the complexity of the real system, data-driven methods allow us to build models from system observations. As these models are e…
Data selection for multi-task learning under dynamic constraints
Alexandre Capone, Armin Lederer, Jonas Umlauft +1
Learning-based techniques are increasingly effective at controlling complex systems using data-driven models. However, most work done so far has focused on learning individual task…
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…