Publications

You can also find my publications on Google Scholar.

Conference Papers

Failure Prediction at Runtime for Generative Robot Policies

R. Römer*, A. Kobras*, L. Worbis, A. P. Schoellig

Conference on Neural Information Processing Systems (NeurIPS), 2025

[Website] [Paper] [arXiv]

Diffusion Predictive Control with Constraints

R. Römer, A. von Rohr, A. P. Schoellig

Learning for Dynamics & Control Conference (L4DC), 2025

[PDF] [arXiv]

Flying through Moving Gates without Full State Estimation

R. Römer, T. Emmert, A. P. Schoellig

IEEE International Conference on Robotics and Automation (ICRA), 2025

[arXiv]

Is Data All That Matters? The Role of Control Frequency for Learning-Based Sampled-Data Control of Uncertain Systems

R. Römer, L. Brunke, S. Zhou, A. P. Schoellig

American Control Conference (ACC), 2024

[PDF] [arXiv] [Video]

Catching Objects with a Robot Arm using Model Predictive Control

T. Gold, R. Römer, A. Völz, K. Graichen

American Control Conference (ACC), 2022

[PDF] [Video]

Journal Articles

Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguard

L. Brunke, Y. Zhang, R. Römer, J. Naimer, S. Zhou, A. P. Schoellig

IEEE Robotics and Automation Letters (RA-L), 2025

[PDF] [arXiv] [Video] [Website]

Vision-Based Uncertainty-Aware Motion Planning based on Probabilistic Semantic Segmentation

R. Römer*, A. Lederer*, S. Tesfazgi, S. Hirche

IEEE Robotics and Automation Letters (RA-L), 2023

[PDF] [arXiv] [Video]

Preprints

CRISP - Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation

D. San José Pro, O. Hausdörfer, R. Römer, M. Dösch, M. Schuck, A. P. Schoellig

Under review, 2025

[PDF] [Website] [Code]

ARMimic: Learning Robotic Manipulation from Passive Human Demonstrations in Augmented Reality

R. Walia, Y. Wang, R. Römer, M. Nishio, A. P. Schoellig, J. Ota

Under review, 2025

[arXiv]

Workshop Papers

Safe Offline Reinforcement Learning using Trajectory-Level Diffusion Models

R. Römer, L. Brunke, M. Schuck, A. P. Schoellig

ICRA Workshop—Back to the Future: Robot Learning Going Probabilistic, 2024

[PDF]

Theses

The Role of Control Frequency for the Stability and Closed-Loop Performance of Uncertain Systems

R. Römer

Master Thesis at TU Munich, 2023