Events Detail

Speaker:
Prof. Katie Winkle, Uppsala University

Join the talk on Zoom

Participatory design has been put to good use in the design and deployment of socially assistive robots, but the automation of robot behaviours still happens "behind laboratory doors", typically involving engineers and computer scientists trying to leverage models of human psychology or machine learning based replications of video-recorded human-human interaction behaviours. This limits the potential for direct input from domain experts (teachers, healthcare practitioners, etc.) who are skilled in the use of social interaction in complex scenarios, and often fails to replicate the situational awareness and social intelligence such experts employ in their own interactions. How could we use in-situ learning to try and achieve more natural human-robot teaching interactions, whereby expert practitioners can teach their "robot colleagues" what to do? This talk will present two use cases: an expert-taught robot fitness instructor and a child-designed robot group assistant to demonstrate such an approach in practice.

Katie is an assistant professor at the Department for Information Technology at Uppsala University and is part of the Human Machine Interaction unit at the Division of Vi3, working at the social robotics lab and is part of the Human Machine Interaction unit at the Division of Vi3, working at the social robotics lab. Before joining Uppsala University, she completed a digital futures postdoctoral research fellowship at the KTH Royal Institute of Technology in Stockholm, and a PhD in robotics at the Bristol Robotics Lab in the UK. Her work draws from design and computer, cognitive and the social sciences to tackle technical and societal challenges relating to human-machine interaction.