Fast Graphical Task Modelling for Flexible Human-Robot Teaming

Abstract:
Human-robot cooperation is a trending topic in robotics research. Recent works mainly focus the execution phase, where human and robot actions need to be planned and coordinated based on given task models. In contrast, we discuss an approach to fast creation of task models suitable for flexible human-robot teaming: Inspired by graphical robot application programming, non-experts may parametrize domain-dependent parts and operations within a 3D representation of the workplace. Operations are then ordered to form a task represented as assembly precedence graph using an icon-based editor. This editor moreover supports proper workplace setup, so that the resulting model is ready for small-batch execution by human-robot teams. We show that our contribution provides a fast and powerful approach to flexibly setup shared tasks for complex pick&place jobs by measuring intuitiveness and average modelling times in a user study.