Preferred Interaction Styles for Human-Robot Collaboration Vary Over Tasks With Different Action Types

Abstract

How do humans want to interact with collaborative robots? As robots become more common and useful not only in industry but also in the home, they will need to interact with humans to complete many varied tasks. Previous studies have demonstrated that autonomous robots are often more efficient and preferred over those that need to be commanded, or those that give instructions to humans. We believe that the types of actions that make up a task affect the preference of participants for different interaction styles. In this work, our goal is to explore tasks with different action types together with different interaction styles to find the specific situations in which different interaction styles are preferred. We have identified several classifications for table-top tasks and have developed a set of tasks that vary along two of these dimensions together with a set of different interaction styles that the robot can use to choose actions. We report on results from a series of human-robot interaction studies involving a PR2 completing table-top tasks with a human. The results suggest that people prefer robot-led interactions for tasks with a higher cognitive load and human-led interactions for joint actions.