no code implementations • 12 May 2024 • Petar Bevanda, Bas Driessen, Lucian Cristian Iacob, Roland Toth, Stefan Sosnowski, Sandra Hirche
Linearity of Koopman operators and simplicity of their estimators coupled with model-reduction capabilities has lead to their great popularity in applications for learning dynamical systems.
no code implementations • 12 Mar 2024 • Tzu-Yuan Huang, Xiaobing Dai, Sihua Zhang, Alexandre Capone, Velimir Todorovski, Stefan Sosnowski, Sandra Hirche
In many control system applications, state constraint satisfaction needs to be guaranteed within a prescribed time.
no code implementations • 5 Feb 2024 • Zewen Yang, Songbo Dong, Armin Lederer, Xiaobing Dai, Siyu Chen, Stefan Sosnowski, Georges Hattab, Sandra Hirche
This work presents an innovative learning-based approach to tackle the tracking control problem of Euler-Lagrange multi-agent systems with partially unknown dynamics operating under switching communication topologies.
1 code implementation • NeurIPS 2023 • Petar Bevanda, Max Beier, Armin Lederer, Stefan Sosnowski, Eyke Hüllermeier, Sandra Hirche
Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e. g., the state of an agent or the reward of a policy.
no code implementations • 27 Jan 2022 • Petar Bevanda, Max Beier, Shahab Heshmati-Alamdari, Stefan Sosnowski, Sandra Hirche
To utilize it for efficient LTI control design, we learn a finite representation of the Koopman operator that is linear in controls while concurrently learning meaningful lifting coordinates.
no code implementations • 10 Dec 2021 • Jan Brüdigam, Martin Schuck, Alexandre Capone, Stefan Sosnowski, Sandra Hirche
When using Gaussian process regression to learn unknown systems, a commonly considered approach consists of learning the residual dynamics after applying some generic discretization technique, which might however disregard properties of the underlying physical system.
1 code implementation • 8 Dec 2021 • Petar Bevanda, Max Beier, Sebastian Kerz, Armin Lederer, Stefan Sosnowski, Sandra Hirche
System representations inspired by the infinite-dimensional Koopman operator (generator) are increasingly considered for predictive modeling.
no code implementations • 15 Oct 2021 • Petar Bevanda, Johannes Kirmayr, Stefan Sosnowski, Sandra Hirche
We present a novel data-driven approach for learning linear representations of a class of stable nonlinear systems using Koopman eigenfunctions.
no code implementations • 29 Mar 2021 • Zewen Yang, Stefan Sosnowski, Qingchen Liu, Junjie Jiao, Armin Lederer, Sandra Hirche
In this paper, a distributed learning leader-follower consensus protocol based on Gaussian process regression for a class of nonlinear multi-agent systems with unknown dynamics is designed.
no code implementations • 4 Feb 2021 • Petar Bevanda, Stefan Sosnowski, Sandra Hirche
The Koopman operator allows for handling nonlinear systems through a (globally) linear representation.