Moritz Nakatenus
Papers
1
Total Citations
84
H-Index
1
About
Moritz Nakatenus is a researcher whose work sits at the intersection of robotics, machine learning, and control theory, with a particular focus on learning complex dynamical systems. His most-cited contribution, "Learning inverse dynamics models in O(n) time with LSTM networks" (2017, 84 citations), addresses a fundamental challenge in modern robotics: accurately modeling the nonlinear dynamics of compliant actuators, elasticities, and frictional effects that analytic models cannot capture. By demonstrating that Long Short-Term Memory networks can learn these inverse dynamics models in linear time, Nakatenus provided a computationally efficient solution for robots requiring high-fidelity control. This work has significant implications for the development of more adaptive and responsive robotic systems, particularly those with elastic or compliant components. While his citation count reflects a focused but impactful contribution, Nakatenus’s research is notable for bridging the gap between deep learning and practical robotics, offering a scalable approach to a problem that has long hindered the deployment of advanced robotic manipulators. His work continues to inform efforts in data-efficient learning for control.
Research Focus
Key Achievements
Top Papers
- 1Learning inverse dynamics models in O(n) time with LSTM networks84 citations · 2017