Influencing Human Robot Teams

Teams comprised of both humans and robots are increasingly becoming a reality. A key barrier to enabling teams fluently working together is that leadership roles of humans and robots are often determined a priori. In successful human-human teams, we find that leadership is an emergent behavior where team members can adaptively take, give up, or share leadership based on changing tasks or environments. To create human-robot teams capable of long-term interactions in dynamically changing environments, they need to be able to fluidly adapt leader and follower roles. To this end, we develop a mathematical framework that first models emergent leading and following behaviors and further leverages the learned predictive models to plan for intelligent robot teammates that influence the roles of other members for more efficient outcomes.