no code implementations • 3 Apr 2024 • Siyi Wang, Zifan Wang, Xinlei Yi, Michael M. Zavlanos, Karl H. Johansson, Sandra Hirche
Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time.
no code implementations • 15 Mar 2024 • Nhan-Khanh Le, Erfaun Noorani, Sandra Hirche, John Baras
We study time-robust path planning for synthesizing robots' trajectories that adhere to spatial-temporal specifications expressed in Signal Temporal Logic (STL).
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 • 13 Feb 2024 • Siyi Wang, Sandra Hirche
Moreover, by the diagonal system matrix assumption, the optimal scheduling policy is shown to be of threshold type.
no code implementations • 5 Feb 2024 • Zewen Yang, Xiaobing Dai, Akshat Dubey, Sandra Hirche, Georges Hattab
This paper introduces an innovative approach to enhance distributed cooperative learning using Gaussian process (GP) regression in multi-agent systems (MASs).
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.
no code implementations • 5 Feb 2024 • Xiaobing Dai, Zewen Yang, Mengtian Xu, Fangzhou Liu, Georges Hattab, Sandra Hirche
Gaussian processes are harnessed to compensate for the unknown components of the multi-agent system.
no code implementations • 29 Jan 2024 • Kaikai Zheng, Dawei Shi, Sandra Hirche, Yang Shi
Two kinds of data selection mechanisms are proposed by online evaluating the innovation contained in the sampled data, wherein the innovation is quantified by its effect of shrinking the set of potential system dynamics that are compatible with the sampled data.
no code implementations • 19 Nov 2023 • Yuan Gao, Junjie Jiao, Zhongkui Li, Sandra Hirche
The aim is to design a distributed protocol by dynamic output feedback that achieves state/output containment control while the associated H2 cost is smaller than an a priori given upper bound.
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 • 2 Oct 2023 • Armin Lederer, Erfaun Noorani, John S. Baras, Sandra Hirche
We propose a method for learning these value functions using common techniques from reinforcement learning and derive sufficient conditions for its success.
no code implementations • 10 Jul 2023 • Armin Lederer, Jonas Umlauft, Sandra Hirche
We address this issue by deriving a Bayesian prediction error bound for GP regression, which we show to decay with the growth of a novel, kernel-based measure of data density.
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 • 14 May 2023 • Xiaobing Dai, Armin Lederer, Zewen Yang, Sandra Hirche
When the dynamics of systems are unknown, supervised machine learning techniques are commonly employed to infer models from data.
1 code implementation • 21 Apr 2023 • Cedric Donié, Neha Das, Satoshi Endo, Sandra Hirche
We used a random search to find the highest-scoring InceptionTime architecture and compared it to ROCKET with a ridge classifier and a multi-layer perceptron (MLP) on wrist motions of PD patients.
no code implementations • 12 Apr 2023 • Qingchen Liu, Zengjie Zhang, Nhan Khanh Le, Jiahu Qin, Fangzhou Liu, Sandra Hirche
This paper proposes a novel distributed coverage controller for a multi-agent system with constant-speed unicycle robots (CSUR).
no code implementations • 11 Apr 2023 • Xiaobing Dai, Huanzhuo Wu, Siyi Wang, Junjie Jiao, Giang T. Nguyen, Frank H. P. Fitzek, Sandra Hirche
We adopt the concept of field Kalman filtering, where the dual estimation problem is decomposed into a fast state estimation process and a computationally expensive parameter estimation process.
no code implementations • 11 Apr 2023 • Xiaobing Dai, Zewen Yang, Sandra Hirche
In the realm of the cooperative control of multi-agent systems (MASs) with unknown dynamics, Gaussian process (GP) regression is widely used to infer the uncertainties due to its modeling flexibility of nonlinear functions and the existence of a theoretical prediction error bound.
1 code implementation • 31 Mar 2023 • Robert Lefringhausen, Supitsana Srithasan, Armin Lederer, Sandra Hirche
As control engineering methods are applied to increasingly complex systems, data-driven approaches for system identification appear as a promising alternative to physics-based modeling.
no code implementations • 13 Jan 2023 • Zengjie Zhang, Qingchen Liu, Mohammad H. Mamduhi, Sandra Hirche
Quantifying the average communication rate (ACR) of a networked event-triggered stochastic control system (NET-SCS) with deterministic thresholds is challenging due to the non-stationary nature of the system's stochastic processes.
no code implementations • 1 Dec 2022 • Armin Lederer, Azra Begzadić, Neha Das, Sandra Hirche
Ensuring safety is of paramount importance in physical human-robot interaction applications.
no code implementations • 4 Jul 2022 • Sebastian Curi, Armin Lederer, Sandra Hirche, Andreas Krause
Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems.
no code implementations • 24 Jun 2022 • Giulio Evangelisti, Sandra Hirche
This paper proposes a physically consistent Gaussian Process (GP) enabling the identification of uncertain Lagrangian systems.
no code implementations • 23 Feb 2022 • Armin Lederer, Mingmin Zhang, Samuel Tesfazgi, Sandra Hirche
Safety-critical technical systems operating in unknown environments require the ability to quickly adapt their behavior, which can be achieved in control by inferring a model online from the data stream generated during operation.
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 • 5 Nov 2021 • Alejandro J. Ordóñez-Conejo, Armin Lederer, Sandra Hirche
To reduce noise, low-pass filters are commonly employed in order to attenuate high frequency components in the incoming signal, regardless if they come from noise or the actual signal.
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 • 1 Oct 2021 • Samuel Tesfazgi, Armin Lederer, Johannes F. Kunz, Alejandro J. Ordóñez-Conejo, Sandra Hirche
The use of rehabilitation robotics in clinical applications gains increasing importance, due to therapeutic benefits and the ability to alleviate labor-intensive works.
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 • 16 Jul 2021 • Precious Ugo Abara, Sandra Hirche
In this paper we propose a distributed value of information (dVoI) metric for the joint design of control and schedulers for medium access in a multi-loop system and multi-hop network.
no code implementations • 20 Jun 2021 • Nhan Khanh Le, Yang Liu, Quang Minh Nguyen, Qingchen Liu, Fangzhou Liu, Quanwei Cai, Sandra Hirche
Federated learning is the distributed machine learning framework that enables collaborative training across multiple parties while ensuring data privacy.
no code implementations • 9 Apr 2021 • Pablo Budde gen. Dohmann, Armin Lederer, Marcel Dißemond, Sandra Hirche
To overcome this shortcoming, we propose a novel distributed learning framework for the exemplary task of cooperative manipulation using Bayesian principles.
no code implementations • 9 Apr 2021 • Samuel Tesfazgi, Armin Lederer, Sandra Hirche
A common approach to solve this problem is the framework of inverse reinforcement learning (IRL), where the observed agent, e. g., a human demonstrator, is assumed to behave according to an intrinsic cost function that reflects its intent and informs its control actions.
no code implementations • 7 Apr 2021 • Siyi Wang, Qingchen Liu, Precious Ugo Abara, John S. Baras, Sandra Hirche
In this paper, we study the trade-off between the transmission cost and the control performance of the multi-loop networked control system subject to network-induced delay.
no code implementations • 31 Mar 2021 • Thomas Beckers, Sandra Hirche, Leonardo Colombo
Formation control algorithms for multi-agent systems have gained much attention in the recent years due to the increasing amount of mobile and aerial robotic swarms.
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.
no code implementations • 13 Jan 2021 • Armin Lederer, Jonas Umlauft, Sandra Hirche
In application areas where data generation is expensive, Gaussian processes are a preferred supervised learning model due to their high data-efficiency.
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 • 6 Oct 2020 • Neha Das, Jonas Umlauft, Armin Lederer, Thomas Beckers, Sandra Hirche
Data-driven control in unknown environments requires a clear understanding of the involved uncertainties for ensuring safety and efficient exploration.
no code implementations • 14 Sep 2020 • Thomas Beckers, Leonardo Colombo, Sandra Hirche, George J. Pappas
To overcome this issue, we present a tracking control law for underactuated rigid-body dynamics using an online learning-based oracle for the prediction of the unknown dynamics.
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 • 25 Jun 2020 • Thomas Beckers, Sandra Hirche
The modeling and simulation of dynamical systems is a necessary step for many control approaches.
no code implementations • 16 Jun 2020 • Armin Lederer, Alejandro Jose Ordonez Conejo, Korbinian Maier, Wenxin Xiao, Jonas Umlauft, Sandra Hirche
The increased demand for online prediction and the growing availability of large data sets drives the need for computationally efficient models.
no code implementations • 14 Jun 2020 • Wenxin Xiao, Armin Lederer, Sandra Hirche
Modelling real world systems involving humans such as biological processes for disease treatment or human behavior for robotic rehabilitation is a challenging problem because labeled training data is sparse and expensive, while high prediction accuracy is required from models of these dynamical systems.
no code implementations • 14 Jun 2020 • Armin Lederer, Markus Kessler, Sandra Hirche
In order to overcome this issue, we propose a novel framework called GP3, general purpose computation on graphics processing units for Gaussian processes, which allows to solve many of the existing problems efficiently.
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.
no code implementations • 12 Sep 2019 • Thomas Beckers, Somil Bansal, Claire J. Tomlin, Sandra Hirche
In this work, we present a framework to optimize the kernel and hyperparameters of a kernel-based model directly with respect to the closed-loop performance of the model.
no code implementations • 4 Jun 2019 • Armin Lederer, Jonas Umlauft, Sandra Hirche
The posterior variance of Gaussian processes is a valuable measure of the learning error which is exploited in various applications such as safe reinforcement learning and control design.
no code implementations • NeurIPS 2019 • Armin Lederer, Jonas Umlauft, Sandra Hirche
Finally, we derive safety conditions for the control of unknown dynamical systems based on Gaussian process models and evaluate them in simulations of a robotic manipulator.
no code implementations • 16 Nov 2018 • Thomas Beckers, Jonas Umlauft, Sandra Hirche
A naturally provided model confidence is highly relevant for system-theoretical considerations to provide guarantees for application scenarios.
no code implementations • 31 Aug 2018 • Muriel Lang, Franz M. J. Pfister, Jakob Fröhner, Kian Abedinpour, Daniel Pichler, Urban Fietzek, Terry T. Um, Dana Kulić, Satoshi Endo, Sandra Hirche
The assessment of Parkinson's disease (PD) poses a significant challenge as it is influenced by various factors which lead to a complex and fluctuating symptom manifestation.
1 code implementation • 8 Aug 2018 • Terry Taewoong Um, Franz Michael Josef Pfister, Daniel Christian Pichler, Satoshi Endo, Muriel Lang, Sandra Hirche, Urban Fietzek, Dana Kulić
Parkinson's Disease (PD) is characterized by disorders in motor function such as freezing of gait, rest tremor, rigidity, and slowed and hyposcaled movements.
1 code implementation • 19 Jun 2018 • Thomas Beckers, Dana Kulić, Sandra Hirche
The model fidelity is used to adapt the feedback gains allowing low feedback gains in state space regions of high model confidence.
2 code implementations • 21 Mar 2018 • Wanxin Jin, Dana Kulić, Shaoshuai Mou, Sandra Hirche
We handle the problem by proposing the recovery matrix, which establishes a relationship between available observations of the trajectory and weights of given candidate features.
Robotics Systems and Control
no code implementations • ICML 2017 • Jonas Umlauft, Sandra Hirche
A data-driven identification of dynamical systems requiring only minimal prior knowledge is promising whenever no analytically derived model structure is available, e. g., from first principles in physics.
2 code implementations • 2 Jun 2017 • Terry Taewoong Um, Franz Michael Josef Pfister, Daniel Pichler, Satoshi Endo, Muriel Lang, Sandra Hirche, Urban Fietzek, Dana Kulić
While convolutional neural networks (CNNs) have been successfully applied to many challenging classification applications, they typically require large datasets for training.