Combining Task and Motion Planning through Rapidly-Exploring Random Trees

Abstract

Combined task and motion planning is a relevant issue in robotics. In path and motion planning, Rapidly-exploring Random Trees (RRTs) have been proposed as effective methods to efficiently search high-dimensional spaces. On the other hand, the deployment of these techniques to symbolic task planning problems has been partially investigated. In this paper, we explore this issue proposing a method to combine task and motion planning based on RRTs. Our approach relies on a metric space where both symbolic (task) and sub-symbolic (motion) spaces are represented. The associated notion of distance is then exploited by a RRT-based planner to generate a plan that includes both symbolic actions and obstacle-free trajectories. The proposed method is assessed in several case studies provided by a real-world hospital logistic scenario, where an omni-directional mobile robot is involved in pick-carry-and-place tasks.