Michael Yuhas

Papers

Total Citations

H-Index

About

Michael Yuhas is a leading researcher at the intersection of machine learning and safety-critical cyber-physical systems (CPS), with a primary focus on ensuring the reliability of autonomous platforms. His key research areas include out-of-distribution (OOD) detection, real-time embedded systems, and trustworthy AI for robotics. Yuhas’s major contribution is the development of a design methodology for deep OOD detectors that can operate within the stringent timing constraints of real-time CPS—a critical advancement for applications like autonomous vehicles. His most cited work, "Embedded out-of-distribution detection on an autonomous robot platform" (2021, 13 citations), demonstrates the practical deployment of OOD detection on a mobile robot, directly addressing the catastrophic failure risk when ML models encounter novel data. This was followed by his 2022 paper formalizing the design methodology (7 citations) and a demo abstract showcasing real-time implementation (4 citations). Collectively, his work bridges the gap between theoretical ML robustness and practical embedded system constraints, making autonomous systems safer. Yuhas’s research is essential reading for anyone working on dependable AI in resource-limited, real-world environments.