Reinforcement Learning for Social Human-Robot Interaction

Speaker:  Dr. Shane Saunderson |DeGroote School of Business,
Information Systems, McMaster University.

Date: November 7, 2024
Time: 4 pm
Room: LH3058 (Lazaridis Hall (Math Boardroom), Room 3058) & Hybrid

Abstract:  As robots and AI agents become more embedded into our
workplaces and lives, they will increasingly require adaptive intelligence to learn
how to behave when interacting with a specific individual around a particular
context. This talk will outline the challenge of designing systems to engage in
the complexity of human social interaction (with a focus on persuasion) before
giving an overview of new approaches to human-centric reinforcement learning
that focus on the states and preferences of an individual and learn to adapt to
their needs. Social HRI explores the challenges of essentially trying to create a
a new type of 'person', however, in doing so, can often teach us things about
ourselves.

Bio:  Dr. Shane Saunderson is an Assistant Professor of Information Systems with
the Degroote School of Business at McMaster University. He also lectures with the
Schulich School of Business Executive Education Center at York University and
advises several technology startups and non-profit organizations. Shane received
a B.Eng. in mechanical engineering from McGill University, an MBA in technology and
innovation from the Ted Rogers School of Management at Toronto Metropolitan
University, and a PhD in robotics with a specialization in psychology from the
University of Toronto. He is a former Vanier scholar and Junior Fellow with Massey
College. Previously, Shane has spent time in the industry running his startups and
consulting for Fortune 500 companies such as Microsoft Canada, Ford, Samsung, Eli Lilly,
and many more. Shane’s research focuses on the social and organizational implications
of humanlike technologies, such as robotics and AI, with particular interest in topics such
as trust, persuasion, and anthropomorphism.