activity
20242026
collaborators

8 papers

eess.SY2026

Beyond Asymptotics: Targeted exploration with finite-sample guarantees

Janani Venkatasubramanian, Johannes Köhler, Frank Allgöwer

In this paper, we introduce a targeted exploration strategy for the non-asymptotic, finite-time case. The proposed strategy is applicable to uncertain linear time-invariant systems…

math.OC2026

Robust targeted exploration for systems with non-stochastic disturbances

Janani Venkatasubramanian, Johannes Köhler, Mark Cannon +1

We propose a novel targeted exploration strategy designed specifically for uncertain linear time-invariant systems with energy-bounded disturbances, i.e., without any assumptions o…

eess.SY2025

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

Henrik Hose, Johannes Köhler, Melanie N. Zeilinger +1

Model predictive control (MPC) achieves stability and constraint satisfaction for general nonlinear systems, but requires computationally expensive online optimization. This paper…

eess.SY2025

Output-feedback model predictive control under dynamic uncertainties using integral quadratic constraints

Lukas Schwenkel, Johannes Köhler, Matthias A. Müller +1

In this work, we propose an output-feedback tube-based model predictive control (MPC) scheme for linear systems under dynamic uncertainties that are described via integral quadrati…

math.OC2025

Robust Nonlinear Optimal Control via System Level Synthesis

Antoine P. Leeman, Johannes Köhler, Andrea Zanelli +2

This paper addresses the problem of finite horizon constrained robust optimal control for nonlinear systems subject to norm-bounded disturbances. To this end, the underlying uncert…

eess.SY2025

Multi-objective robust controller synthesis with integral quadratic constraints in discrete-time

Lukas Schwenkel, Johannes Köhler, Matthias A. Müller +2

This article presents a novel framework for the robust controller synthesis problem in discrete-time systems using dynamic Integral Quadratic Constraints (IQCs). We present an algo…