A Hierarchical Planner Based On Set-Theoretic Models: Towards Automating The Automation For Autonomous Systems

The complexity of today's autonomous systems renders the manual engineering of control strategies or behaviors for all possible system states infeasible. Therefore, planning algorithms are required that match the capabilities of the system to the tasks at hand. Solutions to typical problems with robotic systems combine aspects of symbolic action planning with sub-symbolic motion planning and control. The problem complexity of this combination currently prohibits online planning without task specific, manually defined heuristics. To counter that we use a set-theoretic approach to model declarative and procedural knowledge which allows for flexible hierarchies of planning tasks. The coordination of the planning tasks on different levels, the classification of information and various views on data are the core functions of hierarchical planning. We propose suitable graph structures to capture all relevant information and discuss the elements of our hierarchical planning algorithm in this paper. Furthermore, we present two use-cases of an autonomous manufacturing system to highlight the capabilities of our system.