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 • 3 Nov 2023 • Alexandre Capone, Ryan Cosner, Aaron Ames, Sandra Hirche
Our approach requires no prior model and corresponds, to the best of our knowledge, to the first algorithm that guarantees safety in settings with occasionally infeasible safety certificates without requiring a backup non-learning-based controller.
no code implementations • 4 Oct 2023 • Alexandre Capone, Tim Brüdigam, Sandra Hirche
Solving chance-constrained stochastic optimal control problems is a significant challenge in control.
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 • 6 Sep 2021 • Alexandre Capone, Armin Lederer, Sandra Hirche
Our approach computes a confidence region in the space of hyperparameters, which enables us to obtain a probabilistic upper bound for the model error of a Gaussian process with arbitrary hyperparameters.
no code implementations • 20 Nov 2020 • Armin Lederer, Alexandre Capone, Thomas Beckers, Jonas Umlauft, Sandra Hirche
In this paper, we propose a Lyapunov-based measure for quantifying the impact of data on the certifiable control performance.
no code implementations • 24 Jul 2020 • Alexandre Capone, Sandra Hirche
Control schemes that learn using measurement data collected online are increasingly promising for the control of complex and uncertain systems.
no code implementations • L4DC 2020 • Armin Lederer, Alexandre Capone, Sandra Hirche
By relaxing the problem through scenario optimization we derive a provably optimal method for control parameter tuning.
no code implementations • L4DC 2020 • Jonas Umlauft, Thomas Beckers, Alexandre Capone, Armin Lederer, Sandra Hirche
The identification of unknown dynamical systems using supervised learning enables model-based control of systems that cannot be modeled based on first principles.
no code implementations • 25 May 2020 • Armin Lederer, Alexandre Capone, Jonas Umlauft, Sandra Hirche
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.
no code implementations • L4DC 2020 • Alexandre Capone, Jonas Umlauft, Thomas Beckers, Armin Lederer, Sandra Hirche
We apply the proposed method to explore the state space of various dynamical systems and compare our approach to a commonly used entropy-based exploration strategy.