Search Results for author: Sina Ober-Blöbaum

Found 7 papers, 4 papers with code

Hamiltonian Neural Networks with Automatic Symmetry Detection

1 code implementation19 Jan 2023 Eva Dierkes, Christian Offen, Sina Ober-Blöbaum, Kathrin Flaßkamp

Recently, Hamiltonian neural networks (HNN) have been introduced to incorporate prior physical knowledge when learning the dynamical equations of Hamiltonian systems.

Symmetry Detection Total Energy

Multi-objective low-thrust spacecraft trajectory design using reachability analysis

no code implementations14 Dec 2022 Nikolaus Vertovec, Sina Ober-Blöbaum, Kostas Margellos

One of the fundamental problems in spacecraft trajectory design is finding the optimal transfer trajectory that minimizes the propellant consumption and transfer time simultaneously.

The Past Does Matter: Correlation of Subsequent States in Trajectory Predictions of Gaussian Process Models

no code implementations20 Nov 2022 Steffen Ridderbusch, Sina Ober-Blöbaum, Paul Goulart

Computing the distribution of trajectories from a Gaussian Process model of a dynamical system is an important challenge in utilizing such models.

Gaussian Processes

Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery

1 code implementation20 Nov 2022 Yana Lishkova, Paul Scherer, Steffen Ridderbusch, Mateja Jamnik, Pietro Liò, Sina Ober-Blöbaum, Christian Offen

By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional.

Verification of safety critical control policies using kernel methods

no code implementations23 Mar 2022 Nikolaus Vertovec, Sina Ober-Blöbaum, Kostas Margellos

Hamilton-Jacobi reachability methods for safety-critical control have been well studied, but the safety guarantees derived rely on the accuracy of the numerical computation.

Efficient time stepping for numerical integration using reinforcement learning

1 code implementation8 Apr 2021 Michael Dellnitz, Eyke Hüllermeier, Marvin Lücke, Sina Ober-Blöbaum, Christian Offen, Sebastian Peitz, Karlson Pfannschmidt

While the classical schemes apply very generally and are highly efficient on regular systems, they can behave sub-optimal when an inefficient step rejection mechanism is triggered by structurally complex systems such as chaotic systems.

Meta-Learning Numerical Integration +2

Learning ODE Models with Qualitative Structure Using Gaussian Processes

1 code implementation10 Nov 2020 Steffen Ridderbusch, Christian Offen, Sina Ober-Blöbaum, Paul Goulart

Recent advances in learning techniques have enabled the modelling of dynamical systems for scientific and engineering applications directly from data.

Gaussian Processes

Cannot find the paper you are looking for? You can Submit a new open access paper.