Feryal Behbahani
Papers
3
Total Citations
35
H-Index
3
About
Feryal Behbahani is a leading researcher at the intersection of robotics and artificial intelligence, with a primary focus on deep reinforcement learning (DRL) and its application to real-world robotic systems. Her work addresses a critical challenge in the field: training robots that can operate reliably in the physical world without requiring perfect models of their environment. Behbahani is best known for her pioneering analysis of agents trained with domain randomisation, a technique that bridges the simulation-to-reality gap. Her most-cited paper (2022, 21 citations) provides a deep investigation into the explainability of DRL agents, revealing how these black-box models make decisions after being trained in varied simulated environments. This work is essential for building trust and transparency in autonomous systems. Earlier, Behbahani contributed to the field of assistive robotics with her research on haptic SLAM for prosthetic hands (2015, 7 citations), where she developed particle-filter methods that allow prosthetics to infer object shape and hand pose from touch alone—mimicking human haptic perception. Her research is shaping the future of robust, interpretable, and context-aware robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3