Ant colony optimization algorithm for industrial robot programming in a digital twin

Advanced manufacturing that is adaptable to constantly changing product designs often requires dynamic changes on the factory floor to enable manufacture. The integration of robotic manufacture with machine learning approaches offers the possibility to enable such dynamic changes on the factory floor. While ensuring safety and the possibility of losses of components and waste of material are against their usage. Furthermore, developments in design of virtual environments makes it possible to perform simulations in a virtual environment, to enable human-in-the-loop production of parts correctly the first time like never before. Such powerful simulation and control software provides the means to design a digital twin of manufacturing environment in which trials are completed at almost at no cost. In this paper, ant colony optimization is used to program an industrial robot to avoid obstacles and find its way to pick and place objects during an assembly task in an environment containing obstacles that must be avoided. The optimization is completed in a digital twin environment first and movements transferred to the real robot after human inspection. It is shown that the proposed methodology can find the optimal solution, in addition to avoiding collisions, for an assembly task with minimum human intervention.