Aaquib Tabrez
Papers
7
Total Citations
211
H-Index
4
About
Aaquib Tabrez is a leading researcher at the intersection of artificial intelligence, human-robot interaction, and explainable decision-making. His work focuses on building collaborative autonomy—designing robots that can understand, explain, and adapt to human teammates in real time. Tabrez’s foundational survey on mental modeling in human-robot teaming (89 citations) established a critical framework for how robots can infer and align with human beliefs during joint tasks. He pioneered explanation-based reward coaching, a novel reinforcement learning mechanism that uses structured feedback to improve human performance—a contribution that has shaped how autonomous systems provide actionable guidance rather than raw data. His research on explainable reinforcement learning (40 citations) and autonomous justification (2023) addresses the fundamental challenge of when and how robots should communicate their decisions to avoid overwhelming human operators. Tabrez has also explored cognitive biases in human-robot trust, showing how recency effects in performance history skew perceptions of robot competence. His applied work extends to autonomous vehicle safety, where he developed automated failure-mode clustering for informed car-to-driver handovers. With over 200 total citations and a growing portfolio of high-impact publications, Tabrez is shaping the future of transparent, trustworthy human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1A Survey of Mental Modeling Techniques in Human–Robot Teaming89 citations · 2020
- 2
- 3Improving Human-Robot Interaction Through Explainable Reinforcement Learning40 citations · 2019
- 4
- 5
- 6
- 7