activity
20242026
collaborators

10 papers

cs.RO2026

SOCC-ICP: Semantics-Assisted Odometry based on Occupancy Grids and ICP

Johannes Scherer, Sebastian Hirt, Henri Meeß

Reliable pose estimation in previously unseen environments is a fundamental capability of autonomous systems. Existing LiDAR odometry methods typically employ point-, surfel-, or N…

cs.LG2026

Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Models

Lukas Theiner, Maik Pfefferkorn, Yongpeng Zhao +2

Tuning control policies manually to meet high-level objectives is often time-consuming. Bayesian optimization provides a data-efficient framework for automating this process using…

cs.LG2025

High-Dimensional Surrogate Modeling for Closed-Loop Learning of Neural-Network-Parameterized Model Predictive Control

Sebastian Hirt, Valentinus Suwanto, Hendrik Alsmeier +2

Learning controller parameters from closed-loop data has been shown to improve closed-loop performance. Bayesian optimization, a widely used black-box and sample-efficient learning…

eess.SY2025

Time-Series-Informed Closed-loop Learning for Sequential Decision Making and Control

Sebastian Hirt, Lukas Theiner, Rolf Findeisen

Closed-loop performance of sequential decision making algorithms, such as model predictive control, depends strongly on the choice of controller parameters. Bayesian optimization a…

eess.SY2025

A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Control

Sebastian Hirt, Lukas Theiner, Maik Pfefferkorn +1

Many control problems require repeated tuning and adaptation of controllers across distinct closed-loop tasks, where data efficiency and adaptability are critical. We propose a hie…

eess.SY2025

Exploiting Prior Knowledge in Preferential Learning of Individualized Autonomous Vehicle Driving Styles

Lukas Theiner, Sebastian Hirt, Alexander Steinke +1

Trajectory planning for automated vehicles commonly employs optimization over a moving horizon - Model Predictive Control - where the cost function critically influences the result…