Generating and Executing Hierarchical Mobile Manipulation Plans

Abstract

To execute complex tasks with a mobile robot in challenging environments, task planning and execution monitoring play a decisive role. This paper presents the integration of an off-the-shelf HTN planner into a robotic system which is aimed at enabling a service robot to learn from experiences. For plan execution, a state-machine-based approach is employed. The system has successfully been demonstrated on a PR2 robot in a restaurant scenario.