Symon and Fluent Teamwork

Two people repeatedly performing an activity together naturally converge to a high level of coordination, resulting in a fluent meshing of their actions. In contrast, human-robot interaction is often structured in a rigid stop-and-go fashion. Aiming to design robots that are capable peers in human environments, we wish to attain a more fluent meshing of human and machine activity.

While the existence and complexity of joint action has been acknowledged for decades, the cognitive mechanisms underlying it have only received sparse attention, predominantly over the last few years. Among other factors, successful coordinated action has been linked to the formation of expectations of each partner's actions by the other, and the subsequent acting on these expectations. We argue that the same holds for collaborative robots --- if they are to go beyond stop-and-go interaction, robots must take into account not only past events and current perceived state, but also expectations of their human collaborators.

Theoretical Analysis -- We have developed an adaptive anticipatory action selection mechanism for a robotic teammate. We have analyzed our model of anticipatory action in a cost-based framework of coordinated shared-location action, and have compared it to a purely reactive agent, demonstrating a theoretical improvement in efficiency compared to a reactive agent.

Human Subjects Study -- We have tested the performance of the algorithm in a study involving untrained human subjects working with a simulated version of a robot (named Symon) using our anticipatory system. We found a significant improvement in task efficiency in this group when compared to a group of users working with a reactive agent, as well as a significant difference in several measures of the perceived commitment of the robot to the team and its contribution to the team's fluency and success. Grounding these perceptions in behavioral measures of the human-robot team, we found that the two groups to differ significantly in a number of proposed fluency metrics including the amount of concurrent motion of human and robot, the amount of human idle time, and the time between the the human's action and the robot's uptake on that action.