KIT | KIT-Bibliothek | Impressum | Datenschutz

ReACT: Reinforcement Learning for Controller Parametrization Using B-Spline Geometries

Rudolf, Thomas 1,2; Flögel, Daniel 1,2; Schürmann, Tobias ORCID iD icon 1,2; Süß, Simon 2; Schwab, Stefan 2; Hohmann, Sören 1,2
1 Institut für Regelungs- und Steuerungssysteme (IRS), Karlsruher Institut für Technologie (KIT)
2 FZI Forschungszentrum Informatik (FZI)

Abstract (englisch):

Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. ... mehr


Download
Originalveröffentlichung
DOI: 10.1109/SMC53992.2023.10394648
Dimensions
Zitationen: 2
Zugehörige Institution(en) am KIT FZI Forschungszentrum Informatik (FZI)
Institut für Regelungs- und Steuerungssysteme (IRS)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 03.10.2023
Sprache Englisch
Identifikator ISBN: 979-83-503-3702-0
KITopen-ID: 1000168279
Erschienen in 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Veranstaltung IEEE International Conference on Systems, Man, and Cybernetics (SMC 2023), Honolulu, HI, USA, 01.10.2023 – 04.10.2023
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 3385–3391
Schlagwörter Deep Reinforcement Learning, Industrial Control, Controller Parametrization, B-spline, Parameter-variant Systems, Gain-scheduling Control, Control Adaptation, Long Short-Term Memory, LSTM, Regularization, TQC, SAC, DroQ, Lookup Tables, Nonlinear Systems, Time-Series, Automatic Parametrization, Neural Networks, Reinforcement Learning, Control Design
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page