Using Plan Libraries for Improved Plan Execution

Abstract

The difficulty of task planning for robotic agents arises from the stochastic nature of their environment and the high cost of a failure during execution meaning frequent replanning is required. One way to address this problem is to make use of a pre-defined plan library. In this paper, we present work that combines a plan library with task planning. Initial results show that such an approach alleviates the computational burden of synthesising plans, while providing the same level of autonomy as using a planner that starts from scratch.