Maymoonah Toubeh
Papers
2
Total Citations
4
H-Index
2
About
Maymoonah Toubeh is a robotics researcher whose work sits at the intersection of deep learning, uncertainty estimation, and autonomous systems planning. Her research addresses one of the most pressing challenges in modern robotics: bridging the gap between controlled experimental environments and real-world deployment, where unreliable perception can have critical consequences. Toubeh's most notable contributions center on risk-aware planning frameworks that integrate deep learning-based perception with classical robotics techniques. Her pioneering work leverages Bayesian approximations to quantify uncertainty in deep learning models, enabling robotic planners to make more cautious, safety-conscious decisions in high-stakes scenarios. A compelling case study running through her research involves a cooperative aerial-ground robot system, where an aerial scout robot must reliably interpret its environment before guiding a ground counterpart — a setup that vividly illustrates the real-world stakes of perception failures. With cited publications from 2018 and 2019, Toubeh has contributed foundational ideas to the emerging field of uncertainty-aware autonomous systems. Her work is particularly relevant for researchers and students interested in making AI-driven robots not just capable, but genuinely trustworthy in safety-critical applications — a challenge that remains central to the future of autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2