Jack Umenberger

Papers

Total Citations

H-Index

About

Jack Umenberger is a researcher working at the intersection of robotics, control theory, and machine learning. His work addresses fundamental challenges in making robotic systems safer and more capable in real-world environments. In his most-cited contribution, "Identifying External Contacts from Joint Torque Measurements on Serial Robotic Arms and Its Limitations" (2021, 12 citations), Umenberger tackles the critical problem of contact detection in robot arms operating alongside humans — leveraging existing joint torque sensors rather than requiring additional hardware, while rigorously characterizing the boundaries of this approach. This work has direct implications for human-robot collaboration and safety in unstructured settings. Complementing this, his 2018 paper "Learning Convex Bounds for Linear Quadratic Control Policy Synthesis" (7 citations) addresses the challenge of learning reliable control policies for systems with unknown dynamics — a problem of broad relevance across robotics, finance, and medicine. By developing convex optimization frameworks for policy synthesis from data, Umenberger contributes principled, computationally tractable methods to the emerging field of data-driven control. Together, his research reflects a commitment to bridging theoretical rigor with practical robotics applications, making him a notable voice in modern autonomous systems research.