Task planning based on human-robot interaction for autonomous mobile robots

Abstract

We propose a new method of task planning for autonomous mobile robots based on the properties of human-robot interaction. First, we present a planning method under restricted time for interaction and planning. We divide the planning process into two phases: phase 1 (during human interaction) and phase 2 (after human interaction). Second, we describe an algorithm to generate a plan that realizes simultaneous execution of multiple tasks. These tasks are constructed by a sequence of subtasks, and a new plan is generated by merging a task to the intermediate plan in the incremental planning process. Finally, we examine the effectiveness of this planning method through simulation.