Intelligent Control Systems

Search

EN

Invited Session Series on Learning-based Control

Organizers:
external page Angela P. Schoellig (University of Toronto, Canada)
external page Sebastian Trimpe (RWTH Aachen University, Germany)
Melanie N. Zeilinger (ETH Zürich, Switzerland)
external page Matthias Müller (Leibniz University Hannover, Germany)

Data science and machine learning have demonstrated tremendous success in the last decades in applications such as image recognition, recommender systems, or question answering. Compared to these applications, which can largely be subsumed as static problems, learning-based control systems take a special role within the world of statistical and machine learning. The coupling of a learning algorithm with a control loop requires a combined treatment as a dynamic process and raises fundamental questions about stability, robustness, and safety, which are generally less critical in most traditional application areas of machine learning. In order to leverage the potential of data-based and learning methods for control, we therefore believe that principled approaches integrating machine learning and control theory are needed, which extend beyond the methods and tools of the individual disciplines.

Based on the increasing interest in this domain, we have started a new Invited Session Series on Learning-based Control taking place yearly at the IEEE Conference on Decision and Control (CDC). The sessions in 2016 through 2025 were a great success and we are looking forward to your contributions and the next session at CDC'26. More info on our upcoming sessions will be posted here soon. 

a.schoellig

Angela Schoellig,
Angela Schoellig is an Assistant Professor at the University of Toronto Institute for Aerospace Studies (UTIAS), where she heads the Dynamic Systems Lab. She is also an Associate Director of the Center for Aerial Robotics Research and Education (CARRE) at the University of Toronto. With her team, she conducts research at the interface of robotics, controls and machine learning. Her goal is to enhance the performance and autonomy of robots by enabling them to learn from past experiments and from each other.

Sebastian Trimpe, external page
Sebastian is a Full Professor and Director of the Institute for Data Science in Mechanical Engineering (DSME) at RWTH Aachen University, Germany. DSME focusses on fundamental research at the intersection of control, machine learning, data science, and distributed systems, as well as innovative applications in cyber-physical systems, robotics, and industrycollaborations.


M.Zeilinger

Melanie Zeilinger,
Melanie is an Assistant Professor at the Department of Mechanical and Process Engineering at ETH Zurich, where she is leading the Intelligent Control Systems group at the Institute for Dynamic Systems and Control. Her research interests are centered around real-time and distributed control and optimization, as well as safe learning-based control, with applications to human-in-the-loop control.

M.Zeilinger

Matthias Müller,
Matthias is Full Professor and Director of the Institute of Automatic Control at the Leibniz University Hannover, Germany. His research interests include nonlinear control and estimation, model predictive control, data-based and distributed control, with application in different fields including biomedical engineering.

The Invited Session was very well received among CDC participants.  We thank all authors for contributing to this success.

Session overview:

The Invited Session was very well received among CDC participants.  We thank all authors for contributing to this success.

Session overview:

The Invited Session was very well received among CDC participants. We thank all authors for contributing to this success.

Session overview:

The Invited Sessions (WeA23, WeB23 and WeC23) were very well received by CDC participants. We thank all authors for contributing to this success.

Session Overviews:

WeA23 Invited Session: Learning-Based Controller Synthesis

 

The Invited Sessions (TuB13, WeB13, ThB13 and FrB13) were very well received by CDC participants. We thank all authors for contributing to this success.

Session Overviews:

TuB13: Learning-based Control I

external page Learning Control for Polynomial Systems using Sum of Squares (1)
Guo, Meichen (University of Groningen)
De Persis, Claudio (University of Groningen)
Tesi, Pietro (University of Florence)


external page Exploiting Differential Flatness for Robust Learning-based Tracking Control Using Gaussian Processes
Greeff, Melissa (University of Toronto)
Schoellig, Angela P (University of Toronto)


external page Safe Learning-based Model Predictive Control Under State and Input-dependent Uncertainty Using Scenario Trees (1)
Bonzanini, Angelico Domenico (UC Berkeley)
Paulson, Joel (Ohio State University)
Mesbah, Ali (UC Berkeley)


external page Constrained Optimal Tracking Control of Unknown Systems: A Multi-step Linear Programming Approach (1)
Tanzanakis, Alexandros (ETH Zurich)
Lygeros, John (ETH Zurich)

WeB13: Learning-based Control 11
external page Scenario Optimization with Relaxation: A New Tool for Design and Application to Machine Learning Problems (1)
Campi, MC (Universita’ Di Brescia)
Garatti, Simone (Politecnico Di Milano)

 

WeB13: Learning-based Control II

external page Control Barrier Functions for Unknown Non-Linear Systems Using Gaussian Processes (1)
Jagtap, Pushpak (KTH Royal Institute of Technology)
Pappas, George J (University of Pennsylvania)
Zamani, Majid (University of Colorado, Boulder)

external page A Convex Approach to Robust LQR (1)
Scampicchio, Anna (University of Padova)
Pillonetto, Gianluigi (University of Padova)

external page Controller Design Via Experimental Exploration with Robustness Guarantees
Holicki, Tobias (University of Stuttgart)
Scherer, Carsten W (University of Stuttgart)
Trimpe, Sabastian (RWTH Aachen University)


external page Learning Control Barrier Functions from Expert Demonstrations (1)
Robey, Alexander (University of Pennsylvania)
Hu, Haimin (University of Pennsylvania)
Lindemann, Lars (Royal Institute of Technology, KTH)
Zhang, Hanwen (University of Pennsylvania)
Dimarogonas, Dimos V (KTH Royal Institute of Technology)
Tu, Stephen (University of California, Berkeley)
Matni, Nikolai (University of Pennsylvania)


external page On the Robustness of Equilibria in Generalized Aggregative Games (1)
Fabiani, Filippo (University of Oxford)
Margellos, Kostas (University of Oxford)
Goulart, Paul J (University of Oxford)

ThB13: Learning-based Control III

external page Stability and Feasibility of Neural Network-based Controllers via Output Range Analysis (I)
Karg, Benjamin (TU Berlin)
Lucia, Sergio (TU Berlin)

external page Direct Data-driven Design of Neural Reference Governors (I)
Masti, Daniele (IMT School for Advanced Studies Lucca)
Breschi, Valentina (Politecnico di Milano)
Formentin, Simone (Politecnico Di Milano)
Bemporad, Alberto (IMT School for Advanced Studies Lucca)

external page Learning Nonlinear Feedback Controllers from Data via Optimal Policy Search and Stochastic Gradient Descent (I)
Ferrarotti, Laura (IMT School for Advanced Studies Lucca)
Bemporad, Alberto (IMT School for Advanced Studies Lucca)


external page How Training Impacts Performance in Learning-based Control
Lederer, Armin (Technical University of Munich)
Capone, Alexandre (Technical University of Munich)
Umlauft, Jonas (Technical University of Munich)
Hirche, Sandra (Technische Universität München)

external page To Share or Not to Share? Performance Guarantees and the Asymmetric Nature of Cross-Robot Experience Transfer
Sorocky, Michael Joseph (University of Toronto)
Zhou, Siqi (University of Toronto)
Schoellig, Angela P (University of Toronto)
 

FrB13: Learning-based Control IV

external page Active Exploration in Adaptive Model Predictive Control (I)
Parsi, Anilkumar (ETH Zurich)
Ianelli, Andrea (ETH Zurich)
Smith, Roy S (ETH Zurich)

external page Computing the Racing Line Using Bayesian Optimization (I)
Jain, Achin (University of Pennsylvania)
Morari, Manfred (University of Pennsylvania)

external page Trajectory Optimization for Non-linear Multi-agent Systems Using Decentralized Learning Model Predictive Control (I)
Zhu, Edward (University of California, Berkeley)
Stürz, Yvonne R (UC Berkeley)
Rosolia, Ugo (Caltech)
Borrelli, Francesco (University of California at Berkeley)

external page Learning to Satisfy Unknown Constraints in Iterative MPC (1)
Bujarbaruah, Monimoy (UC Berkeley)
Vallon, Charlott (University of California, Berkeley)
Borelli, Francesco (University of California at Berkeley)

external page Sample Complexity of Data-driven Stochastic LQR with Multiplicative Uncertainty (I)
Coppens, Peter (KU Leuven)
Patrinos, Panagiotis (KU Leuven)
 

 

The Invited Sessions (TuA01, TuB01, WeA01 and WeB01) were very well received by CDC participants. We thank all authors for contributing to this success.

Session Overviews:

TuA01: Learning-based Control: Data-driven Methods

external page Direct Data-Driven Model-reference Control with Lyapunov Stability Guarantees (I)

Breschi, Valentina (Politecnico Di Milano)
De Persis, Claudio (University of Groningen)
Formentin, Simone (Politecnico Di Milano)
Tesi, Pietro (University of Florence)

external page Trading-Off Safety, Exploration, and Exploitation in Learning-Based Optimization: A Set Membership Approach

Sabug, Lorenzo Jr. (Politecnico Di Milano)
Ruiz Fredy (Politecnico Di Milano)
Fagiano, Lorenzo (Politecnico Di Milano)

external page On the Consistency of the Risk Evaluation in the Scenario Approach (I)

Garatti, Simone (Politecnico Di Milano)
Campi, M. C. (Universita' Di Brescia)

external page System Theory without Transfer Functions and State-Space? Yes, It's Possible!

Markovsky, Ian (Vrije Universiteit Brussel)

external page From System Level Synthesis to Robust Closed-Loop Data-Enabled Predictive Control

Lian, Yingzhao (EPFL)
Jones, Colin (EPFL)

external page Data-Based System Analysis and Control of Flat Nonlinear Systems

Alsalti, Mohammen (Leibniz University Hannover)
Berberich, Julian (University of Stuttgart)
Lopez, Victor G (Leibnitz University of Hannover)
Allgöwer, Frank (University of Stuttgart)
Muller, Matthias A (Leibniz University Hannover)

TuB01: Learning-based Control: Model Predictive Control

external page Data to Controller for Nonlinear Systems: An Approximate Solution

Hendriks, Johannes (University of Newcastle)
Holdsworth, James Robert Zayas (University of Newcastle)
Wills, Adrian (University of Newcastle)
Schön, Thomas (bo) (Uppsala University)
Ninness, Brett (University of Newcastle)

external page Learning Convex Terminal Costs for Complexity Reduction in MPC (I)

Abdufattokhov, Shokhjakhon (IMT School for Advanced Studies Lucca)
Zanon, Mario (IMT School for Advanced Studies Lucca)
Bemporad, Alberto (IMT School for Advanced Studies Lucca)

external page Data-Driven Rollout for Deterministic Optimal Control (I)

Li, Yuchao (KTH Royal Institute of Technology)
Johansson, Karl H (KTH Royal Institute of Technology)
Martensson, Jonas (KTH Royal Institute of Technology)
Bertsekas, Dimitri P (MIT)

external page On the Stability Properties of Perception-Aware Chance-Constrained MPC in Uncertain Environments (I)

Bonzanini, Angelo Domenico (UC Berkeley)
Mesbah, Ali (UC Berkeley)
Di Cairano, Stefano (Mitsubishi Electric Research Labs)
 

external page RLO-MPC: Robust Learning-based Output Feedback MPC for Improving the performance of Uncertain Systems in Iterative Tasks (I)

Brunke, Lukas (University of Toronto)
Zhou, Siqi (University of Toronto)
Schoellig, Angela P (University of Toronto)
 

external page A Soft Constrained MPC Formulation Enabling Learning from Trajectories with Constraint Violations

Wabersich, Kim Peter (ETH Zurich)
Krishnadas, Raamadaas (ETH Zurich)
Zeilinger, Melanie N (ETH Zurich)
 

WeA01: Learning-based Control: Model Learning

external page Learning Accurate Long-Term Dynamics for Model-Based Reinforcement Learning (I)

Lambert, Nathan (UC Berkeley)
Wilcox, Albert (UC Berkeley)
Zhang, Howard (UC Berkeley)
Pister, Kristofer (UC Berkeley)
Calandra, Roberto (Facebook)
 

external page Distributed Bayesian Online Learning for Cooperative Manipulation

Budde genannt Dohmann, Pablo (Technical University of Munich)
Lederer, Armin (Technical University of Munich)
Dissemond, Marcel (Technical University of Munich)
Hirche, Sandra (Technical University of Munich)
 

external page Learning ODE Models with Qualitative Structure Using Gaussian Processes (I)

Ridderbusch, Steffen (University of Oxford)
Offen, Christian (Paderborn University)
Ober-Bloebaum, Sina (University of Oxford)
Goulart, Paul J (University of Oxford)
 

external page Linear Systems Can Be Hard to Learn (I)

Tsiamis, Anastasios (University of Pennsylvania)
Pappas, George J (University of Pennsylvania)
 

external page Distributed Bayesian Parameter Inference for Physics-Informed Neural Networks

Bai, He (Oklahoma State University)
Bhar, Kinjal (Oklahoma State University)
George, Jemin (U.S. Army Research Laboratory)
Busart, Carl (U.S. Army DEVCOM ARL)
 

external page Structured Hammerstein-Wiener Model Learning for Model Predictive Control

Moriyasu, Ryuta (Toyota Central R&D Labs)
Ikeda, Taro (Toyota Central R&D Labs)
Kawaguchi, Sho (Toyota Industries Corporation)
Kashima, Kenji (Kyoto University)
 

WeB01: Learning-based Control: Controller Learning

external page Learning-Based Repetitive Precision Motion Control with Mismatch Compensation (I)

Balta, Efe C (ETH Zurich)
Barton, Kira (University of Michigan, Ann Arbor)
Tilbury, Dawn M. (University of Michigan)
Rupenyan, Alisa (ETH Zurich)
Lygeros, John (ETH Zurich)
 

external page Linear systems with Neural Network Nonlinearities: Improved Stability Analysis Via Acausal Zames-Falb Multipliers (I)

Pauli, Patricia (University of Stuttgart)
Gramlich, Dennis (University of Stuttgart)
Barberich, Julian (University of Stuttgart)
Allgöwer, Frank (University of Stuttgart)
 

external page Communication Topology Co-design in Graph Recurrent Neural Network Based Distributed Control (I)

Yang, Fengjun (University of Pennsylvania)
Matni, Nicolai (University of Pennsylvania)
 

external page Inverse Reinforcement Learning: A Control Lyapunov Approach (I)

Tesfazgi, Samuel (Technical University of Munich)
Lederer, Armin (Technical University of Munich)
Hirche, Sandra (Technical University of Munich)
 

external page Probabilistically Robust Bayasian Optimization for Data-Driven Design of Arbitrary Controllers with Gaussian Process Emulators (I)

Paulson, Joel (The Ohio State University)
Shao, Ketong (UC Berkeley)
Mesbah, Ali (UC Berkeley)
 

external page Data-Driven Online Convex Optimization for Control of Dynamical Systems

Nonhoff, Marko (Leibniz University Hannover)
Muller, Matthias A (Leibniz University Hannover)
 

 

 

 

The Invited Sessions (WeAT05, WeBT05, WeCT05 and ThAT05) were very well received by CDC participants. We thank all authors for contributing to this success.


SESSION OVERVIEWS:


WeAT05 - Learning-Based Control I: Data-Driven Predictive Control

external page Data-Enabled Predictive Control with Instrumental Variables: The Direct Equivalence with Subspace Predictive Control

van Wingerden, Jan-Willem
Mulders, Sebastiaan P.
Dinkla, Rogier
Oomen, Tom
Verhaegen, Michel



external page Data-Driven Multiple Shooting for Stochastic Optimal Control

Ou, Ruchuan
Pan, Guanru
Faulwasser, Timm



external page An Offset-Free Nonlinear MPC Scheme for Systems Learned by Neural NARX Models

Bonassi, Fabio
Xie, Jing
Farina, Marcello
Scattolini, Riccardo



external page Data-Driven Nonlinear Model Reduction Using Koopman Theory: Integrated Control Form and NMPC Case Study

Schulze, Jan C.
Mitsos, Alexander



external page Compression at the Service of Learning: A Case Study for the Guaranteed Error Machine

Garatti, Simone
C. Campi, Marco



external page Learning Functions and Uncertainty Sets Using Geometrically Constrained Kernel Regression

Fiedler, Christian
Scherer, Carsten W.
Trimpe, Sebastian




WeBT05 - Learning-Based Control II: Analysis, Estimation and Control

external page On a Continuous-Time Version of Willems' Lemma

Lopez, Victor G.
Müller, Matthias A.



external page Neural System Level Synthesis: Learning Over All Stabilizing Policies for Nonlinear Systems

Furieri, Luca
Galimberti, Clara Lucía
Ferrari-Trecate, Giancarlo



external page Data-Driven Input Reconstruction and Experimental Validation

Shi, Jicheng
Lian, Yingzhao
Jones, Colin N.



external page Linear Observer Learning by Temporal Difference

Menchetti, Stefano
Zanon, Mario
Bemporad, Alberto



external page Data-Driven Analysis and Design Beyond Common Lyapunov Functions

van Waarde, Henk J.
Camlibel, M. Kanat
Trentelman, Harry L.



external page Finite-Sample Guarantees for State-Space System Identification under Full State Measurements

Baggio, Giacomo
Carè, Algo
Pillonetto, Gianluigi




WeCT05 - Learning-Based Control III: Robustness and Safety

external page A System Level Approach to Regret Optimal Control

Didier, Alexandre
Sieber, Jerome
Zeilinger, Melanie N.



external page Improved Rates for Derivative Free Gradient Play in Strongly Monotone Games

Drusvyatskiy, Dmitriy
Fazel, Maryam
Ratliff, Lillian J.



external page Safe Reinforcement Learning Via Confidence-Based Filters

Curi, Sebastian
Lederer, Armin
Hirche, Sandra
Krause, Andreas



external page Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control

Lee, Bruce D.
Zhang, Thomas T.C.K.
Hassani, Hamed
Matni, Nikolai



external page Improving the Performance of Robust Control through Event-Triggered Learning

von Rohr, Alexander
Solowjow, Friedrich
Trimpe, Sebastian



external page Scalable Estimation of Invariant Sets for Mixed-Integer Nonlinear Systems Using Active Deep Learning

Bonzanini, Angelo D.
Paulson, Joel A.
Makrygiorgos, Georgios
Mesbah, Ali




ThAT05 - Learning-Based Control IV: Controller Design and Applications

external page On Controller Tuning with Time-Varying Bayesian Optimization

Brunzema, Paul
von Rohr, Alexander
Trimpe, Sebastian



external page Neural Energy Casimir Control for Port-Hamiltonian Systems

Xu, Liang
Zakwan, Muhammad
Ferrari-Trecate, Giancarlo



external page Structured-Policy Q-Learning: An LMI-Based Design Strategy for Distributed Reinforcement Learning

Sforni, Lorenzo
Camisa, Andrea
Notarstefano, Giuseppe



external page Convex Analytic Theory for Convex Q-Learning

Lu, Fan
Mehta, Prashant G.
Meyn, Sean P.
Neu, Gergely



external page Multi-Agent Deep Reinforcement Learning for Shock Wave Detection and Dissipation Using Vehicle-To-Vehicle Communication

Suriyarachchi, Nilesh
Noorani, Erfaun
Tariq, Faizan M.
Baras, John S.



external page Physically Consistent Learning of Conservative Lagrangian Systems with Gaussian Processes

Evangelisti, Giulio
Hirche, Sandra

 

The Invited Sessions (WeA02, WeB02, ThA02 and ThB02) were very well received by CDC participants. We thank all authors for contributing to this success.


SESSION OVERVIEWS:


WeA02: Learning-Based Control I: Policy Learning and Optimization

external page Differentiable Sparse Optimal Control

Shima, Ryotaro (Toyota Central R&D Labs)
Moriyasu, Ryuta (Toyota Central R&D Labs)
Kawaguchi, Sho (Toyota Industries Corporation)
Kashima, Kenji (Kyoto University)


external page An Efficient Off-Policy Reinforcement Learning Algorithm for the Continuous-Time LQR Problem (I)

Lopez, Victor G. (Leibniz University Hannover)
Müller, Matthias A. (Leibniz University Hannover)


external page No-Regret Bayesian Optimization with Gradients Using Local Optimality-Based Constraints: Application to Closed-Loop Policy Search (I)

Makrygiorgos, Georgios (University of California, Berkeley)
Paulson, Joel (The Ohio State University)
Mesbah, Ali (University of California, Berkeley)


external page Scenario Optimization with Constraint Relaxation in a Non-Convex Setup: A Flexible and General Framework for Data-Driven Design (I)

Garatti, Simone (Politecnico Di Milano)
Campi, M. C. (Universita' Di Brescia)


external page On-Policy Data-Driven Linear Quadratic Regulator Via Model Reference Adaptive Reinforcement Learning (I)

Borghesi, Marco (University of Bologna)
Bosso, Alessandro (University of Bologna)
Notarstefano, Giuseppe (University of Bologna)


external page Learning Optimal Policies in Mean Field Models with Kullback-Leibler Regularization (I)

Busic, Ana (Inria)
Meyn, Sean P. (Univ. of Florida)
Cammardella, Neil (University of Florida)



WeB02: Learning-Based Control II: Safety and Robustness

external page A Computationally Lightweight Safe Learning Algorithm (I)

Baumann, Dominik (Aalto University)
Kowalczyk, Krzysztof (Wroclaw University of Science and Technology)
Tiels, Koen (Eindhoven University of Technology)
Wachel, PawelWroclaw (University of Science and Technology, Poland)


external page Learning Over Contracting and Lipschitz Closed-Loops for Partially-Observed Nonlinear Systems (I)

Barbara, Nicholas H. (The University of Sydney
Wang, Ruigang (The University of Sydney)
Manchester, Ian R. (University of Sydney)


external page An Online Learning Analysis of Minimax Adaptive Control (I)

Renganathan, Venkatraman (Lund University)
Iannelli, Andrea (University of Stuttgart)
Rantzer, Anders (Lund University)


external page Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning (I)

Lederer, Armin (Technical University of Munich)
Noorani, Erfaun (University of Maryland College Park)
Baras, John S. (University of Maryland)
Hirche, Sandra (Technische Universität München)


external page Learning Safety Filters for Unknown Discrete-Time Linear Systems

Farokhi, Farhad (The University of Melbourne)
Leong, Alex S. (DST Group)
Zamani, Mohammad (University of Melbourne)
Shames, Iman (Australian National University)


external page Data-Driven Synthesis of Safety Controllers for Partially-Observable Systems with Unknown Models (I)

Jahanshahi, Niloofar (Ludwig Maximilian University of Munich)
Zamani, Majid (University of Colorado Boulder)

 

ThA02: Learning-Based Control III: Model Learning, Analysis and Control

external page Physically Consistent Multiple-Step Data-Driven Predictions Using Physics-Based Filters

Lian, YingzhaoEPFLShi, JichengEPFLJones, Colin N.EPFL 10:20-10:40, Paper ThA02.2 Add to


external page Data-Driven Feedback Linearization with Complete Dictionaries (I)

De Persis, Claudio (University of Groningen)
Gadginmath, Darshan (University of California, Riverside)
Pasqualetti, Fabio (University of California, Riverside)
Tesi, Pietro (Università Degli Studi Di Firenze)


external page Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations (I)

Martinelli, Daniele (EPFL)
Galimberti, Clara Lucía (EPFL)
Manchester, Ian R. (University of Sydney)
Furieri, Luca (EPFL)
Ferrari-Trecate, Giancarlo (EPFL)


external page Abstracting Linear Stochastic Systems Via Knowledge Filtering (I)

Engelaar, Maico Hendrikus Wilhelmus (Eindhoven University of Technology)
Romao, Licio (University of Oxford)
Gao, Yulong (University of Oxford)
Lazar, Mircea (Eindhoven University of Technology)
Abate, Alessandro (University of Oxford)
Haesaert, Sofie (Eindhoven University of Technology)


external page Learning Control of Second-Order Systems Via Nonlinearity Cancellation (I)

Guo, Meichen (Delft University of Technology)
De Persis, Claudio (University of Groningen)
Tesi, Pietro (University of Florence)


external page On the Impact of Regularization in Data-Driven Predictive Control (I)

Breschi, Valentina (Eindhoven University of Technology)
Chiuso, Alessandro (University of Padua)
Fabris, Marco (University of Padua)
Formentin, Simone (Politecnico Di Milano)



ThB02: Learning-Based Control IV: Data-Driven Controller Design

external page Data-Driven Model-Reference Control with Closed-Loop Stability: The Output-Feedback Case

de Jong, Thomas O. (Eindhoven University of Technology)
Breschi, Valentina (Eindhoven University of Technology)
Schoukens, Maarten (Eindhoven University of Technology)
Formentin, Simone (Politecnico Di Milano)


external page Model-Free Data-Driven Predictive Control Using Reinforcement Learning (I)

Sawant, Shambhuraj (NTNU Trondheim)
Reinhardt, Dirk Peter (Norwegian University of Science and Technology)
Bahari Kordabad, Arash (Norwegian University of Science and Technology)
Gros, Sebastien (NTNU)


external page The Fundamental Limitations of Learning Linear-Quadratic Regulators (I)

Lee, Bruce (University of Pennsylvania)
Ziemann, Ingvar (University of Pennsylvania)
Tsiamis, Anastasios (ETH Zurich)
Sandberg, Henrik (KTH Royal Institute of Technology)
Matni, Nikolai (University of Pennsylvania)


external page On the Design of Persistently Exciting Inputs for Data-Driven Control of Linear and Nonlinear Systems

Alsalti, Mohammad (Leibniz University Hannover)
Lopez, Victor G. (Leibniz University Hannover)
Müller, Matthias A. (Leibniz University Hannover)


external page Online Control for Adaptive Tapering of Medications (I)

Gradu, Paula (University of California, Berkeley)
Recht, Benjamin (University of California, Berkeley)


external page Differentially Flat Learning-Based Model Predictive Control Using a Stability, State, and Input Constraining Safety Filter

Hall, Adam W. (University of Toronto)
Greeff, Melissa (University of Toronto)
Schoellig, Angela P. (University of Toronto)

The Invited Sessions (2024: TuB02, TuC02, ThA02, ThB02, ThC02) were very well received by CDC participants. We thank all authors for contributing to this success.

SESSION OVERVIEWS:

Session TuB02: Learning-Based Control I: Model Learning and System Identification

Chair: Müller, Matthias A., Leibniz University Hannover
Co-Chair: Trimpe, Sebastian, RWTH Aachen University
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Schoellig, Angela P., Technical University of Munich & University of Toronto
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
 For all paper details [abstracts, PDFs], please see the external page CSS 2024 Program: Session TuB02

A Least-Square Method for Non-Asymptotic Identification in Linear Switching Control (I)
Sun, Haoyuan, Massachusetts Institute of Technology
Jadbabaie, Ali, Massachusetts Institute of Technology 

Learning-Based Prescribed-Time Safety for Control of Unknown Systems with Control Barrier Functions
Huang, Tzu-Yuan, Technical University of Munich (TUM)
Zhang, Sihua, Beijing Institute of Technology
Dai, Xiaobing, Technical University of Munich
Capone, Alexandre, Technical University of Munich
Todorovski, Velimi, University of California San Diego
Sosnowski, Stefan, Technical University of Munich
Hirche, Sandra, Technische Universität München 

Modeling and Predictive Control of Networked Systems Via Physics-Informed Neural Networks (I)
Boca de Giuli, Laura, Politecnico Di Milano
La Bella, Alessio, Politecnico Di Milano
Farina, Marcello, Politecnico Di Milano
Scattolini, Riccardo, Politecnico Di Milano

Active Learning for Control-Oriented Identification of Nonlinear Systems (I)
Lee, Bruce, University of Pennsylvania
Ziemann, Ingvar, University of Pennsylvania
Pappas, George J., University of Pennsylvania
Matni, Nikolai, University of Pennsylvania 

Single Trajectory Conformal Prediction
Lee, Brian, University of Pennsylvania
Matni, Nikolai, University of Pennsylvania

Finite Sample Frequency Domain Identification (I)
Tsiamis, Anastasios, ETH Zurich
Abdalmoaty, Mohamed, ETH Zurich
Smith, Roy S., ETH Zurich
Lygeros, John, ETH Zurich

***
Session TuC02: Learning-Based Control II: Control Policy Learning
 For all paper details [abstracts, PDFs], please see the external page CSS 2024 Program: Session TuC02

Chair: Trimpe, Sebastian, RWTH Aachen University
Co-Chair: Zeilinger, Melanie N., ETH Zurich
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Schoellig, Angela P., Technical University of Munich & University of Toronto
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 

Early Stopping Bayesian Optimization for Controller Tuning (I)
Stenger, David, RWTH Aachen University
Scheurenberg, Dominik, RWTH Aachen University
Vallery, Heike, ETH Zürich
Trimpe, Sebastian, RWTH Aachen University 

Markovian Foundations for Quasi-Stochastic Approximation in Two Timescales (I)
Kalil Lauand, Caio, University of Florida
Meyn, Sean P., Univ. of Florida

Coordinating Planning and Tracking in Layered Control Policies Via Actor-Critic Learning (I)
Yang, Fengjun, University of Pennsylvania
Matni, Nikolai, University of Pennsylvania 

Meta-Learning of Data-Driven Controllers with Automatic Model Reference Tuning: Theory and Experimental Case Study
Busetto, Riccardo, Politecnico Di Milano
Breschi, Valentina, Eindhoven University of Technology
Baracchi, Federica, Politecnico Di Milano
Formentin, Simone, Politecnico Di Milano

Optimal Distributed Control with Stability Guarantees by Training a Network of Neural Closed-Loop Maps (I)
Saccani, Danilo, EPFL
Massai, Leonardo, Politecnico Di Torino
Furieri, Luca, EPFL
Ferrari-Trecate, Giancarlo, Ecole Polytechnique Fédérale De Lausanne 

Lipschitz Safe Bayesian Optimization for Automotive Control
Menn, Johanna, Institute for Data Science in Mechanical Engineering, RWTH Aache
Pelizzari, Pietro, ZF Engineering Solutions, ZF Friedrichshafen AG
Fleps-Dezasse, Michael, ZF Friedrichshafen AG
Trimpe, Sebastian, RWTH Aachen University

***
Session ThA02: Learning-Based Control III: Data-Driven Control

Chair: Schoellig, Angela P., Technical University of Munich & University of Toronto
Co-Chair: Zeilinger, Melanie N., ETH Zurich
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Schoellig, Angela P., Technical University of Munich & University of Toronto
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
 For all paper details [abstracts, PDFs], please see the external page CSS 2024 Program: Session ThA02

Data-Based System Representation and Synchronization for Multiagent Systems (I)
Lopez, Victor G., Leibniz University Hannover
Müller, Matthias A., Leibniz University Hannover 

Exploring the Links between the Fundamental Lemma and Kernel Regression
Molodchyk, Oleksii, Hamburg University of Technology
Faulwasser, Timm, Hamburg University of Technology

Data-Enabled Predictive Repetitive Control (I)
Dinkla, Rogier, Delft University of Technology
Oomen, Tom, Eindhoven University of Technology
Mulders, Sebastiaan Paul, Delft University of Technology
van Wingerden, Jan-Willem, Delft University of Technology 

On the Equivalence of Direct and Indirect Data-Driven Predictive Control Approaches
Mattsson, Per, Uppsala University
Bonassi, Fabio, Uppsala University
Breschi, Valentina, Eindhoven University of Technology
Schön, Thomas (Bo), Uppsala University 

Decoupling Parameter Variation from Noise: Biquadratic Lyapunov Forms in Data-Driven LPV Control (I)
Verhoek, Chris, Eindhoven University of Technology
Eising, Jaap, ETH Zurich
Dörfler, Florian, Swiss Federal Institute of Technology (ETH) Zurich
Tóth, Roland, Eindhoven University of Technology 1

Optimal Data-Driven Prediction and Predictive Control Using Signal Matrix Models (I)
Smith, Roy S., ETH Zurich
Abdalmoaty, Mohamed, ETH Zurich
Yin, Mingzhou, Leibniz University Hannover 

***
Session ThB02: Learning-Based Control IV: Predictive Control

Chair: Zeilinger, Melanie N., ETH Zurich
Co-Chair: Müller, Matthias A., Leibniz University Hannover
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Schoellig, Angela P, Technical University of Munich & University of Toronto
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
For all paper details [abstracts, PDFs], please see the CSS 2024 Program: external page Session ThB02

Towards Safe and Tractable Gaussian Process-Based MPC: Efficient Sampling within a Sequential Quadratic Programming Framework (I)
 Prajapat, Manish, ETH Zurich
Lahr, Amon, ETH Zürich
Köhler, Johannes, ETH Zurich
Krause, Andreas, ETH Zurich
Zeilinger, Melanie N., ETH Zurich 

Constraints-Informed Neural-Laguerre Approximation of Nonlinear MPC with Application in Power Electronics (I)
 Xu, Duo, Eindhoven University of Technology
Aerts, Rody Johannes Cornelis, University of Technology Eindhoven
Karamanakos, Petros, Tampere University
Lazar, Mircea, Eindhoven University of Technology

LMI-Based Design of a Robust Model Predictive Controller for a Class of Recurrent Neural Networks with Guaranteed Properties
 Ravasio, Daniele, Politecnico Di Milano
Farina, Marcello, Politecnico Di Milano
Ballarino, Andrea, Stiima - Cnr

Adaptive Nonlinear Model Predictive Control for a Real-World Labyrinth Game (I)
 Gaber, Johannes, ETH Zurich
Bi, Thomas, ETH Zurich
D'Andrea, Raffaello, ETH Zurich

SelfMPC: Automated Data-Driven MPC Design for a Class of Nonlinear Systems (I)
 Yang, Guitao, Imperial College London
Scandella, Matteo, University of Bergamo
Formentin, Simone, Politecnico Di Milano
Parisini, Thomas, Imperial C., Aalborg U. & Univ. of Trieste

Adaptive Economic Model Predictive Control for Linear Systems with Performance Guarantees
 Degner, Maximilian, ETH Zurich
Soloperto, Raffaele, ETH Zurich
Zeilinger, Melanie N., ETH Zurich
Lygeros, John, ETH Zurich
Köhler, Johannes, ETH Zurich 

***
Session ThC02: Learning-Based Control V: Safety and Convergence Guarantees

Chair: Müller, Matthias A., Leibniz University Hannover
Co-Chair: Trimpe, Sebastian, RWTH Aachen University
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Schoellig, Angela P, Technical University of Munich & University of Toronto
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
For all paper details [abstracts, PDFs], please see the CSS 2024 Program: external page Session ThC02

Providing Safety Assurances for Systems with Unknown Dynamics
 Wang, Hao, University of Southern California
Borquez, Javier, University of Southern California
Bansal, Somil, University of Southern California

Deterministic Safety Guarantees for Learning-Based Control of Monotone Nonlinear Systems under Uncertainty
 Adamek, Joshua, TU Dortmund
Heinlein, Moritz, TU Dortmund
Lüken, Lukas, TU Dortmund
Lucia, Sergio, TU Dortmund 

A PAC-Bayesian Framework for Optimal Control with Stability Guarantees (I)
 Ghoddousi Boroujeni, Mahrokh, École Polytechnique Fédérale De Lausanne
Galimberti, Clara Lucía, École Polytechnique Fédérale De Lausanne
Krause, Andreas, ETH Zurich
Ferrari-Trecate, Giancarlo, Ecole Polytechnique Fédérale De Lausanne

Average Number of Mistakes in Sequential Risk-Averse Scenario Decision-Making (I)
 Garatti, Simone, Politecnico Di Milano
Care', Algo, University of Brescia
Campi, M. C., University of Brescia

Regret Minimization in Scalar, Static, Non-Linear Optimization Problems (I)
 Wang, Ying, KTH Royal Institute of Technology
Pasquini, Mirko, KTH Royal Institute of Technology
Colin, Kévin, KTH Royal Institute of Technology
Hjalmarsson, Håkan, KTH Royal Institute of Technology

Convergence of a Model-Free Entropy-Regularized Inverse Reinforcement Learning Algorithm (I)
 Renard, Titouan, EPFL
Schlaginhaufen, Andreas, EPFL
Ni, Tingting, EPFL
Kamgarpour, Maryam, EPFL

The Invited Sessions (2025: WeA02, WeB02, WeC02) were very well received by CDC participants. We thank all authors for contributing to this success.

SESSION OVERVIEWS:

Session WeA02: Learning-Based Control I: Learning

Chair: Zeilinger, Melanie N., ETH Zurich
Co-Chair: Ozay, Necmiye, Univ. of Michigan
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Schoellig, Angela P, Technical University of Munich & University of Toronto
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
 For all paper details [abstracts, PDFs], please see the CSS 2025 Program: external page Session WeA02 

System Identification under Bounded Noise: Optimal Rates Beyond Least Squares
Zeng, Xiong, University of Michigan, Ann Arbor
Yu, Jing, University of Washington
Ozay, NecmiyeUniv. of Michigan

How to Represent and Identify Affine Time-Invariant Systems?
 Markovsky, Ivan, International Centre for Numerical Methods in Engineering and Ca
Eising, Jaap, ETH Zurich
Padoan, Alberto, University of British Columbia

Hidden Convexity in Active Learning: A Convexified Online Input Design for ARX Systems (I)
Chatzikiriakos, Nicolas, University of Stuttgart
Song, Bowen, University of Stuttgart
Rank, Philipp, University of Stuttgart
Iannelli, Andrea, University of Stuttgart

Minimal Order Recovery through Rank-Adaptive Identification (I)
 Zheng, Frédéric, KTH Stockholm
Jedra, Yassir, MIT
Proutiere, Alexandre, KTH

Beyond Asymptotics: Targeted Exploration with Finite-Sample Guarantees (I)
Venkatasubramanian, Janani, University of Stuttgart
Köhler, Johannes, ETH Zurich
Allgöwer, Frank, University of Stuttgart

Learning with Imperfect Models: When Multi-Step Prediction Mitigates Compounding Error (I)
 Somalwar, Anne, University of Pennsylvania
Lee, Bruce, University of Pennsylvania
Pappas, George J., University of Pennsylvania
Matni, Nikolai, University of Pennsylvania

Local Observability of a Class of Feedforward Neural Networks (I)
 Yang, Yi, Leibniz University Hannover
Lopez, Victor G., Leibniz University Hannover
Müller, Matthias A., Leibniz University Hannover

Sailing towards Zero-Shot State Estimation Using Foundation Models Combined with a UKF (I)
 Holtmann, Tobin, RWTH Aachen University
Stenger, David, RWTH Aachen University
Posada, Andres, RWTH Aachen University
Solowjow, Friedrich, RWTH Aachen University
Trimpe, Sebastian, RWTH Aachen University

*****

Session WeB02: Learning-Based Control II: Control 

Chair: Zeilinger, Melanie N., ETH Zurich
Co-Chair: Berger, Guillaume O., UCLouvain
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Schoellig, Angela P, Technical University of Munich & University of Toronto
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Zeilinger, Melanie N., ETH Zurich 

Papers: 
For all paper details [abstracts, PDFs], please see the CSS 2025 Program: external page Session WeB02

Optimality and Suboptimality of MPPI Control in Stochastic and Deterministic Settings
Homburger, Hannes, HTWG Konstanz - University of Applied Sciences, Institute of Sys
Messerer, Florian, University of Freiburg
Diehl, Moritz, University of Freiburg
Reuter, Johannes, Constance University of Applied Sciences

Inverse Optimal Control with Constraint Relaxation
 Rickenbach, Rahel, ETH Zurich
Lahr, Amon, ETH Zürich
Zeilinger, Melanie N., ETH Zurich

Revisiting Dynamic Programming for Exploration: Insights from a Simple Dual Control Problem (I)
 Wang, Ying, KTH Royal Institute of Technology
Colin, Kévin, CRAN, Université De Lorraine, UMR CNRS 7039
Ju, Yue, KTH Royal Institute of Technology
Pasquini, Mirko, (Former) KTH - Royal Institute of Technology
Hjalmarsson, Håkan, KTH Royal Inst. of Tech

Data-Driven Nonlinear Optimal Control Via Feedback-Based Extremum Seeking (I)
 Carnevale, Guido, University of Bologna
Notarstefano, Giuseppe, University of Bologna

Periodic Disturbance Learning Model Predictive Control
 Shah, Syed Hassan Ahmed, Politecnico Di Milano
Bonetti, Tommaso, Politecnico Di Milano
Fagiano, Lorenzo, Politecnico Di Milano

Insights into the Explainability of Lasso-Based DeePC for Nonlinear Systems (I)
 Giacomelli, Gianluca, Eindhoven University of Technology, Eindhoven, the Netherlands
Formentin, Simone, Politecnico Di Milano
Lopez, Victor G., Leibniz University Hannover
Müller, Matthias A., Leibniz University Hannover
Breschi, Valentina, Eindhoven University of Technology

Bilinear Data-Driven Min-Max MPC: Designing Rational Controllers Via Sum-Of-Squares Optimization (I)
 Xie, Yifan, University of Stuttgart
Berberich, Julian, University of Stuttgart
Strässer, Robin, University of Stuttgart
Allgöwer, Frank, University of Stuttgart

MPCritic: A Plug-And-Play MPC Architecture for Reinforcement Learning (I)
 Lawrence, Nathan P., University of California, Berkeley
Banker, Thomas, University of California, Berkeley
Mesbah, Ali, University of California, Berkeley

*****

Session WeC02: Learning-Based Control III: Data-Driven Methods 

Chair: Berger, Guillaume O., UCLouvain
Co-Chair: Zeilinger, Melanie N., ETH Zurich
Organizer: Müller, Matthias A., Leibniz University Hannover
Organizer: Schoellig, Angela P, Technical University of Munich & University of Toronto
Organizer: Trimpe, Sebastian, RWTH Aachen University
Organizer: Zeilinger, Melanie N., ETH Zurich

Papers: 
 For all paper details [abstracts, PDFs], please see the CSS 2025 Program: external page Session WeC02

A New Perspective on Willems' Fundamental Lemma: Universality of Persistently Exciting Inputs
Shakouri, Amir, University of Groningen
van Waarde, Henk J., University of Groningen
Camlibel, M. Kanat, University of Groningen

Data-Driven Performance Guarantees for Parametric Optimization Problems (I)
Huang, Jingyi, University of Oxford
Goulart, Paul J., University of Oxford
Margellos, Kostas, University of Oxford

A Stochastic-Optimization-Based Adaptive-Sampling Scheme for Data-Driven Stability Analysis of Switched Linear Systems (I)
Vuille, Alexis, UCLouvain
Berger, Guillaume O., UCLouvain
Jungers, Raphaël M., University of Louvain

Pick-To-Learn for Systems and Control: Theoretical Review with a Showcase in Reachability Analysis (I)
Paccagnan, Dario, Imperial College London
Marks, Daniel, Imperial College London
Campi, M. C., University of Brescia
Garatti, Simone, Politecnico Di Milano

System Level Synthesis for Affine Control Policies: Model-Based and Data-Driven Settings
Schüepp, Lukas, ETH Zürich
De Pasquale, Giulia, TU Eindhoven
Dörfler, Florian, ETH Zurich
Amo Alonso, Carmen, Stanford University

Gaussian Behaviors: Representations and Data-Driven Control (I)
Sasfi, Andras, ETH
Markovsky, Ivan, International Centre for Numerical Methods in Engineering and Ca
Padoan, Alberto, University of British Columbia
Dörfler, Florian, ETH Zurich

A Modified Adaptive Data-Enabled Policy Optimization Control to Resolve State Perturbations
Kaheni, Mojtaba, Mälardalen University
Persson, Niklas, Mälardalens University
De Iuliis, Vittorio, University of L'Aquila
Manes, Costanzo, Universita' Dell'Aquila
Papadopoulos, Alessandro Vittorio, Mälardalen University

A Model-Based Approach to Imitation Learning through Multi-Step Predictions
Balim, Haldun, Harvard University
Hu, Yang, Harvard University
Zhang, Yuyang, Harvard University
Li, Na, Harvard University

Co-Organizers

JavaScript has been disabled in your browser