Modular and Domain-guided Multi-robot Planning for Assembly Processes

Abstract

Smart factories of the future will be equipped with dynamic and task-specific teams of robots in order to manufacture custom-tailored products. For this, it is necessary to facilitate the planning of appropriate task sequences for cooperating robots. In this paper, we introduce a modular and domain-guided planning approach for multiple robots. Due to its modularity, the approach can be adapted to different assembly problems. Moreover, domain knowledge is used to guide the planning towards feasible solutions. We evaluate the approach with different examples from the blocks world domain (i. e. LEGO R DUPLO R). This evaluation shows that this domain-guided approach outperforms classical planning based on state space search such as A * .