Search Results for author: Sebastian Trimpe

Found 64 papers, 28 papers with code

Depth-Based Object Tracking Using a Robust Gaussian Filter

1 code implementation19 Feb 2016 Jan Issac, Manuel Wüthrich, Cristina Garcia Cifuentes, Jeannette Bohg, Sebastian Trimpe, Stefan Schaal

To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand.

Computational Efficiency Object +2

Probabilistic Recurrent State-Space Models

4 code implementations ICML 2018 Andreas Doerr, Christian Daniel, Martin Schiegg, Duy Nguyen-Tuong, Stefan Schaal, Marc Toussaint, Sebastian Trimpe

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification.

Gaussian Processes Time Series +2

On Controller Tuning with Time-Varying Bayesian Optimization

2 code implementations22 Jul 2022 Paul Brunzema, Alexander von Rohr, Sebastian Trimpe

Current TVBO methods do not explicitly account for these properties, resulting in poor tuning performance and many unstable controllers through over-exploration of the parameter space.

Bayesian Optimization

Trajectory-Based Off-Policy Deep Reinforcement Learning

2 code implementations14 May 2019 Andreas Doerr, Michael Volpp, Marc Toussaint, Sebastian Trimpe, Christian Daniel

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks.

Continuous Control Policy Gradient Methods +3

A Learnable Safety Measure

1 code implementation7 Oct 2019 Steve Heim, Alexander von Rohr, Sebastian Trimpe, Alexander Badri-Spröwitz

While safety can only be guaranteed after learning the safety measure, we show that failures can already be greatly reduced by using the estimated measure during learning.

Gaussian Processes

Safe Value Functions

1 code implementation25 May 2021 Pierre-François Massiani, Steve Heim, Friedrich Solowjow, Sebastian Trimpe

Although it is often not possible to compute the minimum required penalty, we reveal clear structure of how the penalty, rewards, discount factor, and dynamics interact.

Deep Reinforcement Learning for Event-Triggered Control

1 code implementation13 Sep 2018 Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe

Event-triggered control (ETC) methods can achieve high-performance control with a significantly lower number of samples compared to usual, time-triggered methods.

reinforcement-learning Reinforcement Learning (RL)

GoSafe: Globally Optimal Safe Robot Learning

1 code implementation27 May 2021 Dominik Baumann, Alonso Marco, Matteo Turchetta, Sebastian Trimpe

When learning policies for robotic systems from data, safety is a major concern, as violation of safety constraints may cause hardware damage.

Bayesian Optimization

GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems

1 code implementation24 Jan 2022 Bhavya Sukhija, Matteo Turchetta, David Lindner, Andreas Krause, Sebastian Trimpe, Dominik Baumann

Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.

Safe Exploration

Robot Learning with Crash Constraints

1 code implementation16 Oct 2020 Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe

We consider failing behaviors as those that violate a constraint and address the problem of learning with crash constraints, where no data is obtained upon constraint violation.

Bayesian Optimization

Probabilistic Robust Linear Quadratic Regulators with Gaussian Processes

1 code implementation17 May 2021 Alexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe

Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design.

Gaussian Processes Robust Design

Improving the Performance of Robust Control through Event-Triggered Learning

1 code implementation28 Jul 2022 Alexander von Rohr, Friedrich Solowjow, Sebastian Trimpe

However, in practice, many systems also exhibit uncertainty in the form of changes over time, e. g., due to weight shifts or wear and tear, leading to decreased performance or instability of the learning-based controller.

Approximate non-linear model predictive control with safety-augmented neural networks

1 code implementation19 Apr 2023 Henrik Hose, Johannes Köhler, Melanie N. Zeilinger, Sebastian Trimpe

Our method requires a single evaluation of the NN and forward integration of the input sequence online, which is fast to compute on resource-constrained systems.

Model Predictive Control

Learning an Approximate Model Predictive Controller with Guarantees

no code implementations11 Jun 2018 Michael Hertneck, Johannes Köhler, Sebastian Trimpe, Frank Allgöwer

A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction.

A Local Information Criterion for Dynamical Systems

no code implementations27 May 2018 Arash Mehrjou, Friedrich Solowjow, Sebastian Trimpe, Bernhard Schölkopf

Apart from its application for encoding a sequence of observations, we propose to use the compression achieved by this encoding as a criterion for model selection.

Model Selection

Event-triggered Learning for Resource-efficient Networked Control

no code implementations5 Mar 2018 Friedrich Solowjow, Dominik Baumann, Jochen Garcke, Sebastian Trimpe

Common event-triggered state estimation (ETSE) algorithms save communication in networked control systems by predicting agents' behavior, and transmitting updates only when the predictions deviate significantly.

Robust Gaussian Filtering using a Pseudo Measurement

no code implementations14 Sep 2015 Manuel Wüthrich, Cristina Garcia Cifuentes, Sebastian Trimpe, Franziska Meier, Jeannette Bohg, Jan Issac, Stefan Schaal

The contribution of this paper is to show that any Gaussian filter can be made compatible with fat-tailed sensor models by applying one simple change: Instead of filtering with the physical measurement, we propose to filter with a pseudo measurement obtained by applying a feature function to the physical measurement.

Automatic LQR Tuning Based on Gaussian Process Global Optimization

no code implementations6 May 2016 Alonso Marco, Philipp Hennig, Jeannette Bohg, Stefan Schaal, Sebastian Trimpe

With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data.

Bayesian Optimization

Gait learning for soft microrobots controlled by light fields

no code implementations10 Sep 2018 Alexander von Rohr, Sebastian Trimpe, Alonso Marco, Peer Fischer, Stefano Palagi

Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits.

Bayesian Optimization Gaussian Processes

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties

no code implementations24 Jul 2019 Alonso Marco, Dominik Baumann, Philipp Hennig, Sebastian Trimpe

Learning robot controllers by minimizing a black-box objective cost using Bayesian optimization (BO) can be time-consuming and challenging.

Bayesian Optimization regression

Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization

no code implementations29 Oct 2019 Matteo Turchetta, Andreas Krause, Sebastian Trimpe

In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment.

Bayesian Optimization reinforcement-learning +1

Actively Learning Gaussian Process Dynamics

1 code implementation L4DC 2020 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 way.

Active Learning regression

A Kernel Two-sample Test for Dynamical Systems

no code implementations23 Apr 2020 Friedrich Solowjow, Dominik Baumann, Christian Fiedler, Andreas Jocham, Thomas Seel, Sebastian Trimpe

Evaluating whether data streams are drawn from the same distribution is at the heart of various machine learning problems.

Anomaly Detection Feature Engineering +1

Structured learning of rigid-body dynamics: A survey and unified view from a robotics perspective

no code implementations11 Dec 2020 A. René Geist, Sebastian Trimpe

Accurate models of mechanical system dynamics are often critical for model-based control and reinforcement learning.

Gaussian Processes regression

Structure-preserving Gaussian Process Dynamics

no code implementations2 Feb 2021 Katharina Ensinger, Friedrich Solowjow, Sebastian Ziesche, Michael Tiemann, Sebastian Trimpe

On the other hand, classical numerical integrators are specifically designed to preserve these crucial properties through time.

Variational Inference

Scaling Beyond Bandwidth Limitations: Wireless Control With Stability Guarantees Under Overload

no code implementations16 Apr 2021 Fabian Mager, Dominik Baumann, Carsten Herrmann, Sebastian Trimpe, Marco Zimmerling

An important class of cyber-physical systems relies on multiple agents that jointly perform a task by coordinating their actions over a wireless network.

Self-Driving Cars

Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression

1 code implementation6 May 2021 Christian Fiedler, Carsten W. Scherer, Sebastian Trimpe

However, these estimates are of a Bayesian nature, whereas for some important applications, like learning-based control with safety guarantees, frequentist uncertainty bounds are required.

Gaussian Processes regression

Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees

no code implementations7 May 2021 Christian Fiedler, Carsten W. Scherer, Sebastian Trimpe

The combination of machine learning with control offers many opportunities, in particular for robust control.

On exploration requirements for learning safety constraints

1 code implementation17 May 2021 Pierre-François Massiani, Steve Heim, Sebastian Trimpe

In particular, we discuss the family of constraints that enforce safety in the context of a nominal control policy, and expose that these constraints do not need to be accurate everywhere.

Parameter Filter-based Event-triggered Learning

no code implementations5 Apr 2022 Sebastian Schlor, Friedrich Solowjow, Sebastian Trimpe

However, they usually come with a critical assumption - access to an accurate model of the system.

Active Learning Model Predictive Control

ECLAD: Extracting Concepts with Local Aggregated Descriptors

no code implementations9 Jun 2022 Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe

Further, we introduce a process for the validation of concept-extraction techniques based on synthetic datasets with pixel-wise annotations of their main components, reducing the need for human intervention.

Explainable artificial intelligence

Event-Triggered Time-Varying Bayesian Optimization

no code implementations23 Aug 2022 Paul Brunzema, Alexander von Rohr, Friedrich Solowjow, Sebastian Trimpe

The results demonstrate that ET-GP-UCB is readily applicable without prior knowledge on the rate of change.

Bayesian Optimization

Towards remote fault detection by analyzing communication priorities

no code implementations30 Sep 2022 Alexander Gräfe, Dominik Baumann, Sebastian Trimpe

We propose a fault detection method that uses these priorities to detect errors in other agents.

Fault Detection

Data-Driven Observability Analysis for Nonlinear Stochastic Systems

1 code implementation23 Feb 2023 Pierre-François Massiani, Mona Buisson-Fenet, Friedrich Solowjow, Florent Di Meglio, Sebastian Trimpe

Establishing these properties is challenging, especially when no analytical model is available and they are to be inferred directly from measurement data.

Combining Slow and Fast: Complementary Filtering for Dynamics Learning

no code implementations27 Feb 2023 Katharina Ensinger, Sebastian Ziesche, Barbara Rakitsch, Michael Tiemann, Sebastian Trimpe

This filtering technique combines two signals by applying a high-pass filter to one signal, and low-pass filtering the other.

Sensor Fusion

Reproducing kernel Hilbert spaces in the mean field limit

no code implementations28 Feb 2023 Christian Fiedler, Michael Herty, Michael Rom, Chiara Segala, Sebastian Trimpe

Kernel methods, being supported by a well-developed theory and coming with efficient algorithms, are among the most popular and successful machine learning techniques.

Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test

1 code implementation8 Mar 2023 Behnam Khojasteh, Friedrich Solowjow, Sebastian Trimpe, Katherine J. Kuchenbecker

Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data.

Benchmarking Time Series +3

Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations

no code implementations16 Jul 2023 Shamil Mamedov, A. René Geist, Jan Swevers, Sebastian Trimpe

Accurate prediction of deformable linear object (DLO) dynamics is challenging if the task at hand requires a human-interpretable yet computationally fast model.

Scale-Preserving Automatic Concept Extraction (SPACE)

1 code implementation11 Aug 2023 Andrés Felipe Posada-Moreno, Lukas Kreisköther, Tassilo Glander, Sebastian Trimpe

Convolutional Neural Networks (CNN) have become a common choice for industrial quality control, as well as other critical applications in the Industry 4. 0.

Decision Making Image Classification

Learning Hybrid Dynamics Models With Simulator-Informed Latent States

no code implementations6 Sep 2023 Katharina Ensinger, Sebastian Ziesche, Sebastian Trimpe

In this paper, we propose a new approach to hybrid modeling, where we inform the latent states of a learned model via a black-box simulator.

On kernel-based statistical learning in the mean field limit

no code implementations27 Oct 2023 Christian Fiedler, Michael Herty, Sebastian Trimpe

In many applications of machine learning, a large number of variables are considered.

Learning Theory

Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control

no code implementations30 Nov 2023 Bernd Frauenknecht, Tobias Ehlgen, Sebastian Trimpe

We find that in the case of trajectory control, the standard model-based RL formulation used in approaches like PETS-MPPI and MBPO is not suitable.

Autonomous Driving Q-Learning +2

Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)

no code implementations1 Dec 2023 Emma Cramer, Jonas Reiher, Sebastian Trimpe

However, whether an SAE is actually able to track objects in the scene and thus yields a spatial state representation well suited for RL tasks has rarely been examined due to a lack of established metrics.

Keypoint Detection Reinforcement Learning (RL)

Mean field limits for discrete-time dynamical systems via kernel mean embeddings

no code implementations11 Dec 2023 Christian Fiedler, Michael Herty, Sebastian Trimpe

Mean field limits are an important tool in the context of large-scale dynamical systems, in particular, when studying multiagent and interacting particle systems.

Event-Triggered Safe Bayesian Optimization on Quadcopters

1 code implementation13 Dec 2023 Antonia Holzapfel, Paul Brunzema, Sebastian Trimpe

Utilizing standard safe BO strategies that do not address time-variations can result in failure as previous safe decisions may become unsafe over time, which we demonstrate herein.

Bayesian Optimization

Automatic nonlinear MPC approximation with closed-loop guarantees

no code implementations15 Dec 2023 Abdullah Tokmak, Christian Fiedler, Melanie N. Zeilinger, Sebastian Trimpe, Johannes Köhler

In this paper, we address the problem of automatically approximating nonlinear model predictive control (MPC) schemes with closed-loop guarantees.

Model Predictive Control

On Safety in Safe Bayesian Optimization

no code implementations19 Mar 2024 Christian Fiedler, Johanna Menn, Lukas Kreisköther, Sebastian Trimpe

To overcome this challenge, we introduce the Lipschitz-only Safe Bayesian Optimization (LoSBO) algorithm, which guarantees safety without an assumption on the RKHS bound, and empirically show that this algorithm is not only safe, but also exhibits superior performance compared to the state-of-the-art on several function classes.

Bayesian Optimization

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