Date: Wednesday, November 12, 2025
Speaker: Aaquib Tabrez, Postdoctoral Associate, Cornell University
Title: Explainable Human-Robot Collaboration via Mental Model Alignment
Abstract: In this talk, I will share my research on developing robots and autonomous agents that are transparent, communicative, and reliable teammates. My work focuses on improving human-robot teaming through explainability and multimodal communication, enabling humans and robots to align their mental models, adapt under uncertainty, and resolve misunderstandings that arise during collaboration. I design computational frameworks that integrate models of human reasoning and communication, drawing from cognitive, psychological, and social sciences into robot planning and learning, allowing robots to explain their intent, uncertainty, and limitations through natural language and augmented reality interfaces. More recently, I have extended this work towards building robust and reliable robotic systems by leveraging foundation models and Quality Diversity (QD) algorithms.
Bio: Aaquib Tabrez is a Postdoctoral Associate at Cornell University, where he works on failure recovery of foundation models for robotics. He received his Ph.D. in Computer Science from the University of Colorado Boulder, where his research focused on trust, explainability, and communication in human-robot collaboration. Before Cornell, he was a Postdoctoral Scholar at the University of Southern California. His work has been recognized with Best Paper nominations at HRI and AAMAS and selections as an RSS and HRI Pioneer. Outside of research, he enjoys hiking, dancing, movies, and reading philosophy and poetry.
