42 citations · 138 across the 22 of their papers we have counts for
27 papers
A Decade of Learning-Based Control: From Theoretic Foundations to Practical Deployment
Angela P. Schoellig, Matthias A. Müller, Sebastian Trimpe +8
Motivated by ten years of Learning-Based Control Invited Sessions at the IEEE Conference on Decision and Control (CDC), this tutorial paper reviews key advances at the intersection…
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele +2
Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data effic…
Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow +1
Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly…
Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
Tobin Holtmann, David Stenger, Andres Posada-Moreno +2
State estimation in control and systems engineering traditionally requires extensive manual system identification or data-collection effort. However, transformer-based foundation m…
Kernel conditional tests from learning-theoretic bounds
Pierre-François Massiani, Christian Fiedler, Lukas Haverbeck +2
We propose a framework for hypothesis testing on conditional probability distributions, which we then use to construct statistical tests of functionals of conditional distributions…
On Rollouts in Model-Based Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow +1
Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated mo…
On Foundation Models for Dynamical Systems from Purely Synthetic Data
Martin Ziegler, Andres Felipe Posada-Moreno, Friedrich Solowjow +1
Foundation models have demonstrated remarkable generalization, data efficiency, and robustness properties across various domains. In this paper, we explore the feasibility of found…
Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
Bernd Frauenknecht, Artur Eisele, Devdutt Subhasish +2
Dyna-style model-based reinforcement learning (MBRL) combines model-free agents with predictive transition models through model-based rollouts. This combination raises a critical q…
On the Consistency of Kernel Methods with Dependent Observations
Pierre-François Massiani, Sebastian Trimpe, Friedrich Solowjow
The consistency of a learning method is usually established under the assumption that the observations are a realization of an independent and identically distributed (i.i.d.) or m…
Scalable Concept Extraction in Industry 4.0
Andrés Felipe Posada-Moreno, Kai Müller, Florian Brillowski +3
The industry 4.0 is leveraging digital technologies and machine learning techniques to connect and optimize manufacturing processes. Central to this idea is the ability to transfor…
Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test
Behnam Khojasteh, Friedrich Solowjow, Sebastian Trimpe +1
Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data. However, these methods rely on human expert…
Data-Driven Observability Analysis for Nonlinear Stochastic Systems
Pierre-François Massiani, Mona Buisson-Fenet, Friedrich Solowjow +2
Distinguishability and, by extension, observability are key properties of dynamical systems. Establishing these properties is challenging, especially when no analytical model is av…
Event-Triggered Time-Varying Bayesian Optimization
Paul Brunzema, Alexander von Rohr, Friedrich Solowjow +1
We consider the problem of sequentially optimizing a time-varying objective function using time-varying Bayesian optimization (TVBO). Current approaches to TVBO require prior knowl…
Improving the Performance of Robust Control through Event-Triggered Learning
Alexander von Rohr, Friedrich Solowjow, Sebastian Trimpe
Robust controllers ensure stability in feedback loops designed under uncertainty but at the cost of performance. Model uncertainty in time-invariant systems can be reduced by recen…
Parameter Filter-based Event-triggered Learning
Sebastian Schlor, Friedrich Solowjow, Sebastian Trimpe
Model-based algorithms are deeply rooted in modern control and systems theory. However, they usually come with a critical assumption - access to an accurate model of the system. In…
Safe Value Functions
Pierre-François Massiani, Steve Heim, Friedrich Solowjow +1
Safety constraints and optimality are important, but sometimes conflicting criteria for controllers. Although these criteria are often solved separately with different tools to mai…
Structure-preserving Gaussian Process Dynamics
Katharina Ensinger, Friedrich Solowjow, Sebastian Ziesche +2
Most physical processes posses structural properties such as constant energies, volumes, and other invariants over time. When learning models of such dynamical systems, it is criti…
Identifying Causal Structure in Dynamical Systems
Dominik Baumann, Friedrich Solowjow, Karl H. Johansson +1
Mathematical models are fundamental building blocks in the design of dynamical control systems. As control systems are becoming increasingly complex and networked, approaches for o…
A Kernel Two-sample Test for Dynamical Systems
Friedrich Solowjow, Dominik Baumann, Christian Fiedler +3
Evaluating whether data streams are drawn from the same distribution is at the heart of various machine learning problems. This is particularly relevant for data generated by dynam…
Actively Learning Gaussian Process Dynamics
Mona Buisson-Fenet, Friedrich Solowjow, Sebastian Trimpe
Despite the availability of ever more data enabled through modern sensor and computer technology, it still remains an open problem to learn dynamical systems in a sample-efficient…
Event-triggered Learning for Linear Quadratic Control
Henning Schlüter, Friedrich Solowjow, Sebastian Trimpe
When models are inaccurate, the performance of model-based control will degrade. For linear quadratic control, an event-triggered learning framework is proposed that automatically…
Hierarchical Event-triggered Learning for Cyclically Excited Systems with Application to Wireless Sensor Networks
Jonas Beuchert, Friedrich Solowjow, Jörg Raisch +2
Communication load is a limiting factor in many real-time systems. Event-triggered state estimation and event-triggered learning methods reduce network communication by sending inf…
Event-triggered Learning
Friedrich Solowjow, Sebastian Trimpe
The efficient exchange of information is an essential aspect of intelligent collective behavior. Event-triggered control and estimation achieve some efficiency by replacing continu…
Event-triggered Pulse Control with Model Learning (if Necessary)
Dominik Baumann, Friedrich Solowjow, Karl Henrik Johansson +1
In networked control systems, communication is a shared and therefore scarce resource. Event-triggered control (ETC) can achieve high performance control with a significantly reduc…