Michael Meindl

Michael Meindl

Auto-generated profile, based on publicly available information

Michael Meindl

Institute of Mechatronic Systems, Leibniz Universitt Hannover, Garbsen, Germany

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2021 in IEEE Transactions on Control Systems Technology
Verified
Journal Article
Closed access
MMMichael Meindl
Michael Meindl
FMFabio Molinari
Fabio Molinari
DLDustin Lehmann
Dustin Lehmann
TSThomas Seel
Thomas Seel
Multi-agent systems (MASs) can autonomously learn to solve previously unknown tasks by means of each agent’s individual intelligence as well as by collaborating and exploiting collective intelligence. This article considers a group of autonomous agents learning to track the same given reference trajectory in a possibly small number of trials. We propose a novel collective learning control method that combines iterative learning control (ILC) with a collective update strategy. We derive conditions for desirable convergence properties of such systems. We show that the proposed method allows the collective to combine the advantages of the agents’ individual learning strategies and thereby overcomes trade-offs and limitations of single-agent ILC. This benefit is achieved by designing a heterogeneous collective, i.e., a different learning law is assigned to each agent. All theoretical results are confirmed in simulations and experiments with two-wheeled-inverted-pendulum robots (TWIPRs) that jointly learn to perform the desired maneuver.

6 June 2025 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
MMMichael Meindl
Michael Meindl
SBSimon Bachhuber
Simon Bachhuber
TSThomas Seel
Thomas Seel
Accurate reference tracking is essential in control tasks, and, in repetitive systems, Model-Based Iterative Learning Control (MB-ILC) is a standard solution. However, MB-ILC suffers from two downsides: MB-ILC not only requires prior model information but also learning parameters that have to be manually tuned, which poses an inherent design effort. To overcome the requirement of model information, Data-Driven ILC (DD-ILC) methods have been proposed which, nonetheless, still require manual parameter tuning and also do not preserve the modularity and theoretical guarantees of MB-ILC. To overcome these issues, we propose the two frameworks of Iterative Model Learning (IML) and Dual Iterative Learning Control (DILC). The IML framework enables iterative learning of unknown dynamics in repetitive systems using input/output trajectory pairs, and we formally prove the duality of IML and ILC, i.e., an IML system is equivalent to an ILC system with a trial-varying reference and trial-varying but known dynamics. Hence, existing MB-ILC methods can be utilized within the IML framework to learn models of unknown dynamics. The proposed DILC framework combines IML and MB-ILC to modularly employ various MB-ILC methods and to relieve them of requiring prior model information. To overcome the need for manual parameter tuning, we propose systematic self-parametrization schemes that enable the proposed methods to self-reliantly determine necessary learning parameters. We formally investigate the convergence of the proposed methods, and both IML and DILC are validated in extensive simulations and real-world experiments. A comparison using simulations demonstrates that by means of self-parametrization the proposed DILC framework significantly outperforms two state-of-the-art DD-ILC methods.

9 February 2024 in Control Engineering Practice
Verified
Journal Article
Closed access
MMMichael Meindl
Michael Meindl
SBSimon Bachhuber
Simon Bachhuber
TSThomas Seel
Thomas Seel

7 June 2024 in TechRxiv
Verified
Preprint
Open access
PDF file
MMMichael Meindl
Michael Meindl
SBSimon Bachhuber
Simon Bachhuber
TSThomas Seel
Thomas Seel
Accurate reference tracking is essential in control tasks in a variety of applications, and, in repetitive systems, model-based Iterative Learning Control (ILC) is a standard solution that is underpinned by formal stability and convergence guarantees. To overcome the limitations of model-based ILC design, data-driven ILC methods have been introduced which lead to a patchwork of several, very different approaches that do not preserve the modularity and theoretical guarantees of the many, well-established model-based ILC methods. We, for the first time, propose a unifying framework for data-driven ILC that preserves the modularity and formally proven properties of model-based ILC. Specifically, we propose Iterative Model Learning (IML) and Dual Iterative Learning Control (DILC). The IML framework enables iterative learning of unknown dynamics in repetitive systems using input/output trajectory pairs. We formally prove the duality between IML and ILC, i.e., an IML system is equivalent to an ILC system with a trial-varying reference and trial-varying but known dynamics. We further provide generic conditions to guarantee the convergence of the model and prove the duality of monotonic convergence in ILC and IML. This duality allows arbitrary, established, model-based ILC methods to be effectively applied within the IML framework to learn models of unknown dynamics. Unlike existing data-driven ILC approaches which only combine specific model learning schemes with specific model-based ILC approaches, the proposed DILC framework combines IML with model-based ILC such that established, model-based ILC methods can be arbitrarily combined for simultaneous model and control learning with a formally proven separation principle. The proposed DILC is a unified framework for data-driven ILC that not only relieves model-based ILC of a priori model requirement but also preserves the modularity and theoretical guarantees of model-based ILC. Both IML and DILC are validated by extensive simulations and real-world experiments.

1 May 2024 in at - Automatisierungstechnik
Verified
Journal Article
Closed access
APAlexander Pawluchin
Alexander Pawluchin
MMMichael Meindl
Michael Meindl
IWIve Weygers
Ive Weygers
TSThomas Seel
Thomas Seel
IBIvo Boblan
Ivo Boblan
Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation in situ. We utilize a short interaction maneuver, recorded a priori, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25–50 s of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.

22 July 2021 in TechRxiv
Verified
Preprint
Open access
PDF file
MMMichael Meindl
Michael Meindl
DLDustin Lehmann
Dustin Lehmann
TSThomas Seel
Thomas Seel
This work addresses the problem of reference tracking in autonomously learning agents with unknown, nonlinear dynamics. Existing solutions require model information or extensive parameter tuning, and have rarely been validated in real-world experiments. We propose a learning control scheme that learns to approximate the unknown dynamics by a Gaussian Process (GP), which is used to optimize and apply a feedforward control input on each trial. Unlike existing approaches, the proposed method neither requires knowledge of the system states and their dynamics nor knowledge of an effective feedback control structure. All algorithm parameters are chosen automatically, i.e. the learning method works plug and play. The proposed method is validated in extensive simulations and real-world experiments. In contrast to most existing work, we study learning dynamics for more than one motion task as well as the robustness of performance across a large range of learning parameters. The method’s plug and play applicability is demonstrated by experiments with a balancing robot, in which the proposed method rapidly learns to track the desired output. Due to its model-agnostic and plug and play properties, the proposed method is expected to have high potential for application to a large class of reference tracking problems in systems with unknown, nonlinear dynamics.