Martin Schuck

Technical University of Munich, University of Toronto

Papers

Total Citations

H-Index

About

Martin Schuck is a robotics researcher whose work sits at the intersection of reinforcement learning, geometric machine learning, and reproducible robotics. His major contributions include pioneering methods for mathematically correct handling of orientations in learning pipelines—specifically through the integration of Lie group theory into reinforcement learning frameworks. This work addresses a critical gap in robotics, where improper orientation representation often leads to instabilities or failures in real-world tasks. Schuck’s paper on this topic has already garnered attention for its foundational approach. He is also a driving force behind the advancement of reproducible robotics research, notably through his work on remote sim2real transfer. By enabling researchers to seamlessly transition from simulation to real hardware without physical access, his contributions lower barriers to entry and promote standardized benchmarking across the field. Schuck’s efforts in education and open science further amplify his impact, making complex robotic systems more accessible. With his focus on both theoretical rigor and practical reproducibility, Schuck is shaping a more robust and inclusive future for intelligent robotics.