Moritz Reuss

About

Moritz Reuss is a robotics researcher whose work bridges the gap between model-based control and data-driven learning, with a primary focus on achieving precise and compliant robot manipulation. His most cited work, "End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control" (2022, 11 citations), addresses a fundamental challenge in robotics: combining the well-understood physics of rigid body dynamics with the complex, hard-to-model effects like stick-slip friction. Reuss’s key contribution lies in developing a hybrid framework that seamlessly integrates analytical models with neural networks, enabling robots to achieve superior tracking accuracy while maintaining the compliance necessary for safe human-robot interaction. This approach represents a significant step toward more adaptable and robust control systems, moving beyond purely model-based or purely learning-based paradigms. Though early in his career, Reuss’s work is already shaping how researchers think about fusing classical dynamics with modern machine learning, offering a practical pathway for robots to operate with both precision and flexibility in real-world environments.

Research Focus

Key Achievements

Top Papers

1. 1
   End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

   11 citations · 2022

Key Collaborators

Contact & Links