Mediating Trust and Influence in Human-Robot Teams via Multimodal Communication and Explanation for Mental Model Alignment

Abstract: Effective communication is a foundational aspect of collaboration and teaming. Good communication enables and sustains the shared situational awareness necessary for adaptation and coordination during uncertain situations in human-robot teaming and helps identify and remedy potential misunderstandings caused by mismatched expectations or behavior. Given the opaque nature of decision-making in autonomous systems and robots, it is crucial that these agents can explain their decision-making rationale to both experts and novices for safe and trustworthy deployment in real-world applications. Therefore, in this talk, I will discuss how to leverage visual (augmented reality) and semantic (spoken language) modalities to empower autonomous agents to: 1) communicate insights into their capabilities and limitations to human collaborators, 2) coach and influence human teammates' behavior during joint task execution, and 3) successfully convince and mediate trust in human-robot interactions.

Bio: Aaquib is a Ph.D. candidate in the Collaborative AI and Robotics Lab, advised by Brad Hayes. He works at the intersection of explainability and human-robot interaction, aiming to leverage and enhance multimodal human-machine communication for value alignment and fostering appropriate trust within human-robot teams. He received a B.Tech. in Mechanical Engineering from NITK Surathkal (India) and a master’s in mechanical engineering from CU Boulder. Aaquib is an RSS and HRI Pioneer, and his work has earned best paper nomination awards from the HRI and AAMAS communities. In the fall, he will be joining the University of Southern California as a postdoctoral researcher, advised by Stefanos Nikolaidis. When he is not working on robots, Aaquib enjoys hiking, dancing, movies, and reading philosophy and poetry.