Two key challenges for robot learning in human-robot interaction: Understanding social contexts and scaling human supervision

Abstract, Marynel Vázquez:

In this talk, I will describe two key challenges that I believe are important to advance robot learning in Human-Robot Interaction (HRI).

The first challenge is about understanding social contexts in HRI. What exactly do we mean by context? How do we model it computationally?

The second challenge is about data scarcity in comparison to other related fields, like robot manipulation, computer vision or natural language processing. How can we increase human supervision in HRI?

While we don’t have all the answers to these questions yet, my talk will describe promising directions that we believe can help with both challenges. This includes thinking about context in terms of social situations, organizing context data into graph abstractions, and scaling supervision through interactive online surveys, in-the-wild robot deployments, and by leveraging nonverbal human communicative signals – a type of implicit human feedback.


Bio:

Marynel Vázquez is an Assistant Professor in Yale’s Computer Science Department, where she leads the Interactive Machines Group. Her research focuses on Human-Robot Interaction (HRI), especially in multi-party and group settings. Marynel is a recipient of the 2022 NSF CAREER Award, two Amazon Research Awards and a Google Research Scholar Award. Recently, her work has been recognized with best paper awards at HRI’23 and RO-MAN’22.

Prior to Yale, Marynel was a Post-Doctoral Scholar at the Stanford Vision & Learning Lab and obtained her M.S. and Ph.D. in Robotics from Carnegie Mellon University, where she was a collaborator of Disney Research. Before then, she received her bachelor's degree in Computer Engineering from Universidad Simón Bolívar in Caracas, Venezuela.