collaborators

5 papers

math.OC2026

Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control

Andrea Ghezzi, Rudolf Reiter, Katrin Baumgärtner +2

We propose a computationally efficient rollout-then-optimize method to improve a learned control policy at deployment time. A learned policy provides a nominal trajectory, which is…

eess.SY2026

Gauss-Newton accelerated MPPI Control

Hannes Homburger, Katrin Baumgärtner, Moritz Diehl +1

Model Predictive Path Integral (MPPI) control is a sampling-based optimization method that has recently attracted attention, particularly in the robotics and reinforcement learning…

math.OC2025

Differentiable Nonlinear Model Predictive Control

Jonathan Frey, Katrin Baumgärtner, Gianluca Frison +5

The efficient computation of parametric solution sensitivities is a key challenge in the integration of learning-enhanced methods with nonlinear model predictive control (MPC), as…

eess.SY2025

Incorporating a Deep Neural Network into Moving Horizon Estimation for Embedded Thermal Torque Derating of an Electric Machine

Alexander Winkler, Pranav Shah, Katrin Baumgärtner +3

This study presents a novel state estimation approach integrating Deep Neural Networks (DNNs) into Moving Horizon Estimation (MHE). This is a shift from using traditional physics-b…

eess.SY2025

Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification

Rudolf Reiter, Jasper Hoffmann, Dirk Reinhardt +6

The fields of MPC and RL consider two successful control techniques for Markov decision processes. Both approaches are derived from similar fundamental principles, and both are wid…