collaborators

6 papers

eess.SY2026

On the Existence of Quadratic Control Lyapunov Functions for Koopman-Operator based Bilinear Systems

Sami Leon Noel Aziz Hanna, Nicolas Hoischen, Sandra Hirche +1

Koopman operator-based methods enable data-driven bilinear representations of unknown nonlinear control systems. Accurate representations often demand significantly higher dimensio…

stat.ML2025

Operator Models for Continuous-Time Offline Reinforcement Learning

Nicolas Hoischen, Petar Bevanda, Max Beier +3

Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environmen…

math.OC2025

Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert Spaces

Nicolas Hoischen, Petar Bevanda, Stefan Sosnowski +2

This paper proposes a fully data-driven approach for optimal control of nonlinear control-affine systems represented by a stochastic diffusion. The focus is on the scenario where b…

eess.SY2025

Risk-Aware Trajectory Optimization and Control for an Underwater Suspended Robotic System

Yuki Origane, Nicolas Hoischen, Tzu-Yuan Huang +3

This paper focuses on the trajectory optimization of an underwater suspended robotic system comprising an uncrewed surface vessel (USV) and an uncrewed underwater vehicle (UUV) for…

eess.SY2025

Toward Near-Globally Optimal Nonlinear Model Predictive Control via Diffusion Models

Tzu-Yuan Huang, Armin Lederer, Nicolas Hoischen +4

Achieving global optimality in nonlinear model predictive control (NMPC) is challenging due to the non-convex nature of the underlying optimization problem. Since commonly employed…

math.OC2025

Kernel-Based Optimal Control: An Infinitesimal Generator Approach

Petar Bevanda, Nicolas Hoischen, Tobias Wittmann +3

This paper presents a novel operator-theoretic approach for optimal control of nonlinear stochastic systems within reproducing kernel Hilbert spaces. Our learning framework leverag…