D. Sonnleithner
Papers
1
Total Citations
3
H-Index
1
About
D. Sonnleithner is a researcher whose work lies at the intersection of robotics, control systems, and machine learning. Their most notable contribution is a pioneering approach to controlling complex, nonlinear robotic systems through reinforcement learning. In their highly cited 2010 paper, Sonnleithner introduced a novel two-layer reinforcement learning framework for the control of a 2DOF manipulator. This work demonstrated how an on-policy temporal difference learning agent could effectively learn to control a robot’s movements by selecting appropriate torques for each joint, tackling the inherent challenges of highly nonlinear dynamics. While this paper has garnered 3 citations, its significance lies in its early application of reinforcement learning to physical robotic control, a field that has since exploded in popularity. Sonnleithner’s research bridges the gap between theoretical machine learning algorithms and practical robotic applications, offering a foundation for adaptive, learning-based control systems. Their work remains a valuable reference for students and researchers exploring the integration of AI with robotic manipulation, showcasing an innovative approach to solving real-world control problems.
Research Focus
Key Achievements
Top Papers
- 1